{"$schema":"https://json.schemastore.org/sarif-2.1.0.json","version":"2.1.0","runs":[{"tool":{"driver":{"name":"codehealth","informationUri":"https://codehealth.canine.dev","rules":[{"id":"D1","name":"Cyclomatic Complexity","shortDescription":{"text":"Cyclomatic Complexity"},"helpUri":"https://codehealth.canine.dev/dimensions/D1"},{"id":"D2","name":"Cognitive Complexity","shortDescription":{"text":"Cognitive Complexity"},"helpUri":"https://codehealth.canine.dev/dimensions/D2"},{"id":"D3","name":"God Classes","shortDescription":{"text":"God Classes"},"helpUri":"https://codehealth.canine.dev/dimensions/D3"},{"id":"D4","name":"Code Duplication","shortDescription":{"text":"Code Duplication"},"helpUri":"https://codehealth.canine.dev/dimensions/D4"},{"id":"D5","name":"Coupling","shortDescription":{"text":"Coupling"},"helpUri":"https://codehealth.canine.dev/dimensions/D5"},{"id":"D6","name":"Cohesion (LCOM4)","shortDescription":{"text":"Cohesion (LCOM4)"},"helpUri":"https://codehealth.canine.dev/dimensions/D6"},{"id":"D8","name":"Code Coverage","shortDescription":{"text":"Code Coverage"},"helpUri":"https://codehealth.canine.dev/dimensions/D8"},{"id":"D10","name":"Test Quality","shortDescription":{"text":"Test Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D10"},{"id":"D11","name":"Test Reliability","shortDescription":{"text":"Test Reliability"},"helpUri":"https://codehealth.canine.dev/dimensions/D11"},{"id":"D12","name":"Dependency Hygiene","shortDescription":{"text":"Dependency Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/D12"},{"id":"D13","name":"Secret Scanning","shortDescription":{"text":"Secret Scanning"},"helpUri":"https://codehealth.canine.dev/dimensions/D13","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D14","name":"License Compliance","shortDescription":{"text":"License Compliance"},"helpUri":"https://codehealth.canine.dev/dimensions/D14"},{"id":"D15","name":"Churn \u00D7 Complexity Hotspots","shortDescription":{"text":"Churn \u00D7 Complexity Hotspots"},"helpUri":"https://codehealth.canine.dev/dimensions/D15"},{"id":"D16","name":"Bus Factor","shortDescription":{"text":"Bus Factor"},"helpUri":"https://codehealth.canine.dev/dimensions/D16"},{"id":"D17","name":"Explicit Debt","shortDescription":{"text":"Explicit Debt"},"helpUri":"https://codehealth.canine.dev/dimensions/D17"},{"id":"D19","name":"Documentation Quality","shortDescription":{"text":"Documentation Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D19"},{"id":"D20","name":"ADR Quality","shortDescription":{"text":"ADR Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D20"},{"id":"D21","name":"Naming Consistency","shortDescription":{"text":"Naming Consistency"},"helpUri":"https://codehealth.canine.dev/dimensions/D21"},{"id":"D24","name":"Comment Value","shortDescription":{"text":"Comment Value"},"helpUri":"https://codehealth.canine.dev/dimensions/D24"},{"id":"D26","name":"Project Cohesion","shortDescription":{"text":"Project Cohesion"},"helpUri":"https://codehealth.canine.dev/dimensions/D26"},{"id":"D28","name":"Secrets (history)","shortDescription":{"text":"Secrets (history)"},"helpUri":"https://codehealth.canine.dev/dimensions/D28","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D29","name":"Static Analysis (SAST)","shortDescription":{"text":"Static Analysis (SAST)"},"helpUri":"https://codehealth.canine.dev/dimensions/D29","relationships":[{"target":{"id":"CWE-79","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-94","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-77","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-79","CWE-89","CWE-78","CWE-94","CWE-77"],"owasp":"A05:2025"}},{"id":"D30","name":"Dependency Vulnerabilities","shortDescription":{"text":"Dependency Vulnerabilities"},"helpUri":"https://codehealth.canine.dev/dimensions/D30","relationships":[{"target":{"id":"CWE-1395","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-937","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1395","CWE-937"],"owasp":"A03:2025"}},{"id":"D31","name":"IaC \u0026 Container Security","shortDescription":{"text":"IaC \u0026 Container Security"},"helpUri":"https://codehealth.canine.dev/dimensions/D31","relationships":[{"target":{"id":"CWE-1032","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-732","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-16","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1032","CWE-732","CWE-16"],"owasp":"A02:2025"}},{"id":"D34","name":"Knowledge Freshness","shortDescription":{"text":"Knowledge Freshness"},"helpUri":"https://codehealth.canine.dev/dimensions/D34"},{"id":"D35","name":"Change Coupling","shortDescription":{"text":"Change Coupling"},"helpUri":"https://codehealth.canine.dev/dimensions/D35"},{"id":"D36","name":"Supply-chain Provenance \u0026 Signing","shortDescription":{"text":"Supply-chain Provenance \u0026 Signing"},"helpUri":"https://codehealth.canine.dev/dimensions/D36","relationships":[{"target":{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1357","CWE-494"],"owasp":"A03:2025"}},{"id":"D37","name":"Vulnerability-disclosure Policy","shortDescription":{"text":"Vulnerability-disclosure Policy"},"helpUri":"https://codehealth.canine.dev/dimensions/D37","relationships":[{"target":{"id":"CWE-1059","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1059"],"owasp":"A02:2025"}},{"id":"D43","name":"Malicious Dependencies","shortDescription":{"text":"Malicious Dependencies"},"helpUri":"https://codehealth.canine.dev/dimensions/D43","relationships":[{"target":{"id":"CWE-506","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-506"],"owasp":"A08:2025"}},{"id":"D44","name":"Platform End-of-Life","shortDescription":{"text":"Platform End-of-Life"},"helpUri":"https://codehealth.canine.dev/dimensions/D44"},{"id":"AC2","name":"Forms \u0026 labels","shortDescription":{"text":"Forms \u0026 labels"},"helpUri":"https://codehealth.canine.dev/dimensions/AC2"},{"id":"AC3","name":"Page structure","shortDescription":{"text":"Page structure"},"helpUri":"https://codehealth.canine.dev/dimensions/AC3"},{"id":"AC4","name":"Keyboard semantics","shortDescription":{"text":"Keyboard semantics"},"helpUri":"https://codehealth.canine.dev/dimensions/AC4"},{"id":"AC5","name":"ARIA correctness","shortDescription":{"text":"ARIA correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/AC5"},{"id":"AC6","name":"Visual \u0026 motion safety","shortDescription":{"text":"Visual \u0026 motion safety"},"helpUri":"https://codehealth.canine.dev/dimensions/AC6"},{"id":"AX10","name":"Code composition","shortDescription":{"text":"Code composition"},"helpUri":"https://codehealth.canine.dev/dimensions/AX10"},{"id":"AX3","name":"Project dependency cycles","shortDescription":{"text":"Project dependency cycles"},"helpUri":"https://codehealth.canine.dev/dimensions/AX3"},{"id":"AX4","name":"Dependency direction","shortDescription":{"text":"Dependency direction"},"helpUri":"https://codehealth.canine.dev/dimensions/AX4"},{"id":"AX6","name":"Interface segregation","shortDescription":{"text":"Interface segregation"},"helpUri":"https://codehealth.canine.dev/dimensions/AX6"},{"id":"AXB2","name":"Runtime readiness","shortDescription":{"text":"Runtime readiness"},"helpUri":"https://codehealth.canine.dev/dimensions/AXB2"},{"id":"ED5","name":"Idempotency","shortDescription":{"text":"Idempotency"},"helpUri":"https://codehealth.canine.dev/dimensions/ED5"},{"id":"GD1","name":"Unfinished \u0026 placeholder code","shortDescription":{"text":"Unfinished \u0026 placeholder code"},"helpUri":"https://codehealth.canine.dev/dimensions/GD1"},{"id":"IC1","name":"Incompleteness \u0026 stubs","shortDescription":{"text":"Incompleteness \u0026 stubs"},"helpUri":"https://codehealth.canine.dev/dimensions/IC1"},{"id":"M1","name":"Documentation (README)","shortDescription":{"text":"Documentation (README)"},"helpUri":"https://codehealth.canine.dev/dimensions/M1"},{"id":"M2","name":"Architecture documentation","shortDescription":{"text":"Architecture documentation"},"helpUri":"https://codehealth.canine.dev/dimensions/M2"},{"id":"M3","name":"Folder \u0026 project structure","shortDescription":{"text":"Folder \u0026 project structure"},"helpUri":"https://codehealth.canine.dev/dimensions/M3"},{"id":"P1","name":"CI/CD gates","shortDescription":{"text":"CI/CD gates"},"helpUri":"https://codehealth.canine.dev/dimensions/P1"},{"id":"P10","name":"Library API \u0026 versioning","shortDescription":{"text":"Library API \u0026 versioning"},"helpUri":"https://codehealth.canine.dev/dimensions/P10"},{"id":"P12","name":"CI test-gate honesty","shortDescription":{"text":"CI test-gate honesty"},"helpUri":"https://codehealth.canine.dev/dimensions/P12"},{"id":"P2","name":"Observability","shortDescription":{"text":"Observability"},"helpUri":"https://codehealth.canine.dev/dimensions/P2"},{"id":"P3","name":"Security \u0026 performance tooling","shortDescription":{"text":"Security \u0026 performance tooling"},"helpUri":"https://codehealth.canine.dev/dimensions/P3"},{"id":"P4","name":"Deployment \u0026 Rollback","shortDescription":{"text":"Deployment \u0026 Rollback"},"helpUri":"https://codehealth.canine.dev/dimensions/P4"},{"id":"P6","name":"Release Hygiene","shortDescription":{"text":"Release Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/P6"},{"id":"P7","name":"Outbound HTTP resilience","shortDescription":{"text":"Outbound HTTP resilience"},"helpUri":"https://codehealth.canine.dev/dimensions/P7"},{"id":"PF1","name":"Benchmark discipline","shortDescription":{"text":"Benchmark discipline"},"helpUri":"https://codehealth.canine.dev/dimensions/PF1"},{"id":"PF3","name":"Async \u0026 latency hygiene","shortDescription":{"text":"Async \u0026 latency hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/PF3"},{"id":"R1","name":"Type Safety","shortDescription":{"text":"Type Safety"},"helpUri":"https://codehealth.canine.dev/dimensions/R1"},{"id":"R10","name":"Code Duplication","shortDescription":{"text":"Code Duplication"},"helpUri":"https://codehealth.canine.dev/dimensions/R10"},{"id":"R2","name":"Cyclomatic Complexity","shortDescription":{"text":"Cyclomatic Complexity"},"helpUri":"https://codehealth.canine.dev/dimensions/R2"},{"id":"R3","name":"Large Files","shortDescription":{"text":"Large Files"},"helpUri":"https://codehealth.canine.dev/dimensions/R3"},{"id":"R4","name":"Test Coverage","shortDescription":{"text":"Test Coverage"},"helpUri":"https://codehealth.canine.dev/dimensions/R4"},{"id":"R5","name":"Dependency Freshness","shortDescription":{"text":"Dependency Freshness"},"helpUri":"https://codehealth.canine.dev/dimensions/R5"},{"id":"R6","name":"Tooling","shortDescription":{"text":"Tooling"},"helpUri":"https://codehealth.canine.dev/dimensions/R6"},{"id":"R7","name":"Dead Code","shortDescription":{"text":"Dead Code"},"helpUri":"https://codehealth.canine.dev/dimensions/R7"},{"id":"R8","name":"Dependency Hygiene","shortDescription":{"text":"Dependency Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/R8"},{"id":"R9","name":"Circular Imports","shortDescription":{"text":"Circular Imports"},"helpUri":"https://codehealth.canine.dev/dimensions/R9"},{"id":"SC1","name":"Supply-chain hygiene","shortDescription":{"text":"Supply-chain hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/SC1"},{"id":"X1","name":"Async correctness","shortDescription":{"text":"Async correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X1"},{"id":"X10","name":"Duplicated predicate","shortDescription":{"text":"Duplicated predicate"},"helpUri":"https://codehealth.canine.dev/dimensions/X10"},{"id":"X12","name":"Unreachable branch","shortDescription":{"text":"Unreachable branch"},"helpUri":"https://codehealth.canine.dev/dimensions/X12"},{"id":"X13","name":"Undrained process stream","shortDescription":{"text":"Undrained process stream"},"helpUri":"https://codehealth.canine.dev/dimensions/X13"},{"id":"X14","name":"Bypassable address classification","shortDescription":{"text":"Bypassable address classification"},"helpUri":"https://codehealth.canine.dev/dimensions/X14"},{"id":"X15","name":"Unvalidated length from an untrusted reader","shortDescription":{"text":"Unvalidated length from an untrusted reader"},"helpUri":"https://codehealth.canine.dev/dimensions/X15"},{"id":"X16","name":"Unfloored truncation loop","shortDescription":{"text":"Unfloored truncation loop"},"helpUri":"https://codehealth.canine.dev/dimensions/X16"},{"id":"X17","name":"Uncapped recursion over a caller-supplied document","shortDescription":{"text":"Uncapped recursion over a caller-supplied document"},"helpUri":"https://codehealth.canine.dev/dimensions/X17"},{"id":"X18","name":"Disposal-pattern correctness","shortDescription":{"text":"Disposal-pattern correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X18"},{"id":"X19","name":"Unrestored process-global state","shortDescription":{"text":"Unrestored process-global state"},"helpUri":"https://codehealth.canine.dev/dimensions/X19"},{"id":"X20","name":"Mistyped argument guard","shortDescription":{"text":"Mistyped argument guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X20"},{"id":"X21","name":"Side-effecting pattern guard","shortDescription":{"text":"Side-effecting pattern guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X21"},{"id":"X22","name":"Contradicted release guard","shortDescription":{"text":"Contradicted release guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X22"},{"id":"X23","name":"Unguarded diagnostic materialisation","shortDescription":{"text":"Unguarded diagnostic materialisation"},"helpUri":"https://codehealth.canine.dev/dimensions/X23"},{"id":"X24","name":"Document value interpolated into markup unescaped","shortDescription":{"text":"Document value interpolated into markup unescaped"},"helpUri":"https://codehealth.canine.dev/dimensions/X24"},{"id":"X25","name":"Inert configuration knob","shortDescription":{"text":"Inert configuration knob"},"helpUri":"https://codehealth.canine.dev/dimensions/X25"},{"id":"X26","name":"Unsynchronised callback handoff","shortDescription":{"text":"Unsynchronised callback handoff"},"helpUri":"https://codehealth.canine.dev/dimensions/X26"},{"id":"X27","name":"Collection changed while being enumerated","shortDescription":{"text":"Collection changed while being enumerated"},"helpUri":"https://codehealth.canine.dev/dimensions/X27"},{"id":"X28","name":"Index access outside its own emptiness guard","shortDescription":{"text":"Index access outside its own emptiness guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X28"},{"id":"X29","name":"Per-element action decided by a fixed element","shortDescription":{"text":"Per-element action decided by a fixed element"},"helpUri":"https://codehealth.canine.dev/dimensions/X29"},{"id":"X3","name":"Exception handling","shortDescription":{"text":"Exception handling"},"helpUri":"https://codehealth.canine.dev/dimensions/X3"},{"id":"X30","name":"Support guard that admits what it rejects","shortDescription":{"text":"Support guard that admits what it rejects"},"helpUri":"https://codehealth.canine.dev/dimensions/X30"},{"id":"X32","name":"Type resolved by simple name across every loaded assembly","shortDescription":{"text":"Type resolved by simple name across every loaded assembly"},"helpUri":"https://codehealth.canine.dev/dimensions/X32"},{"id":"X4","name":"Structured logging","shortDescription":{"text":"Structured logging"},"helpUri":"https://codehealth.canine.dev/dimensions/X4"},{"id":"X5","name":"Nullable reference types","shortDescription":{"text":"Nullable reference types"},"helpUri":"https://codehealth.canine.dev/dimensions/X5"},{"id":"X6","name":"Hand-rolled structured-format parsing","shortDescription":{"text":"Hand-rolled structured-format parsing"},"helpUri":"https://codehealth.canine.dev/dimensions/X6"},{"id":"X7","name":"Silent fallback defaults","shortDescription":{"text":"Silent fallback defaults"},"helpUri":"https://codehealth.canine.dev/dimensions/X7"},{"id":"X9","name":"Subsumed condition operand","shortDescription":{"text":"Subsumed condition operand"},"helpUri":"https://codehealth.canine.dev/dimensions/X9"}]}},"results":[{"ruleId":"D1","level":"warning","message":{"text":"CheckAnalysis.checkAnalysis0 (cyclomatic 157): CheckAnalysis.checkAnalysis0 has cyclomatic complexity 157 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"d45ce0f6ce9a2b3125bbb2faabe029a1992107d00fcee3691a71509363754333"}},{"ruleId":"D1","level":"warning","message":{"text":"V2ExpressionBuilder.generateExpression (cyclomatic 135): V2ExpressionBuilder.generateExpression has cyclomatic complexity 135 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cb9975f895646c78f67c968e021edafb20b92a512724f4bb06623d01cb79634"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSubmit.prepareSubmitEnvironment (cyclomatic 132): SparkSubmit.prepareSubmitEnvironment has cyclomatic complexity 132 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4fdd8598f8e90f85963e4dd00c82c783a44b4f5186c41413d55f402d7e970ab"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 132): (anonymous) has cyclomatic complexity 132 (threshold 15). Most of this is not in the body itself: 1 of the 132 points is its own statement and the rest belongs to 55 function items inside it that branch (a function literal at line 678, a function literal at line 404, (anonymous)::(anonymous)::(anonymous)::data, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"13414b83140407066060280ab5985f03b9bf2996f202509a7ef1e8223166be91"}},{"ruleId":"D1","level":"warning","message":{"text":"DataSourceV2Strategy.apply (cyclomatic 129): DataSourceV2Strategy.apply has cyclomatic complexity 129 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"00f819e2237fbd3b366efbe05946b92cfe86d0f5e5a8bfc1542b9e2ad36ff158"}},{"ruleId":"D1","level":"warning","message":{"text":"UnsupportedOperationChecker.checkForStreaming (cyclomatic 110): UnsupportedOperationChecker.checkForStreaming has cyclomatic complexity 110 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"844d7755c9e4c979a743501c5e99b4983771e3467f916bbfbdfc0eb36203fc80"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveSessionCatalog.apply (cyclomatic 104): ResolveSessionCatalog.apply has cyclomatic complexity 104 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"80a94277a295b70b01c3eb0d14f15f32457a94ae374f6d07550dbbaefcf4f81d"}},{"ruleId":"D1","level":"warning","message":{"text":"V2ExpressionSQLBuilder.build (cyclomatic 98): V2ExpressionSQLBuilder.build has cyclomatic complexity 98 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"12480026a34b5e92135d9780231091694398ac1b0058bdc690fcb0237c70462c"}},{"ruleId":"D1","level":"warning","message":{"text":"DAGScheduler.handleTaskCompletion (cyclomatic 79): DAGScheduler.handleTaskCompletion has cyclomatic complexity 79 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3904}}}],"partialFingerprints":{"codehealthFindingId/v1":"71d521d81ef5cebd1ddff34cf1a8b0d8c6eeb5298709aee09e1177b4282d18a2"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveInspectors.unwrapperFor (cyclomatic 76): HiveInspectors.unwrapperFor has cyclomatic complexity 76 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5c25f2074c827619bbe6773f2b963da24b9e7e645be3a54f6d9341c7f643b2e"}},{"ruleId":"D1","level":"warning","message":{"text":"Cast.canCast (cyclomatic 75): Cast.canCast has cyclomatic complexity 75 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"daf0db16f836145877c5150e69baade2bd47cb0d6db67549c2d4021db40889ca"}},{"ruleId":"D1","level":"warning","message":{"text":"BasicOperators.apply (cyclomatic 74): BasicOperators.apply has cyclomatic complexity 74 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":1033}}}],"partialFingerprints":{"codehealthFindingId/v1":"35e574c0d179bbd631ad17f1ae3adba9d81ba6415f544b3c9593e36a1f00466f"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetVectorUpdaterFactory.getUpdater (cyclomatic 74): ParquetVectorUpdaterFactory.getUpdater has cyclomatic complexity 74 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f5cf9e227bb821848e5afe03b3c3d7ee66258591126f2a06d03a36655312935"}},{"ruleId":"D1","level":"warning","message":{"text":"AvroDeserializer.newWriter (cyclomatic 70): AvroDeserializer.newWriter has cyclomatic complexity 70 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"e21ea9c1b314d5ad2179d48b44de7c7d92802ddea3f168da7ce86b17a20d4b69"}},{"ruleId":"D1","level":"warning","message":{"text":"JacksonParser.makeConverter (cyclomatic 68): JacksonParser.makeConverter has cyclomatic complexity 68 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd5439f75d1193c13218e934b971827c2c6c4f28fae624260b19a55cc40c77e8"}},{"ruleId":"D1","level":"warning","message":{"text":"Cast.canAnsiCast (cyclomatic 67): Cast.canAnsiCast has cyclomatic complexity 67 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b1efd940296855cee39af7741e7e338a82beac03a09d37b6846a160c93ca9cd"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveInspectors.wrapperFor (cyclomatic 63): HiveInspectors.wrapperFor has cyclomatic complexity 63 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"771caad7c3a00c6d6cf7d3bf2b8b8349ee068577b4920e5be2a7854c309efb97"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveReferences.doApply (cyclomatic 62): ResolveReferences.doApply has cyclomatic complexity 62 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1653}}}],"partialFingerprints":{"codehealthFindingId/v1":"2919c06a05e227b38db124b40967f46ccdf8dcf9be69a1dfe936418ff0d0ea02"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowSerializer.serializerForDefault (cyclomatic 62): ArrowSerializer.serializerForDefault has cyclomatic complexity 62 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowSerializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0e44618b475c7c417ff2b1accbd9a2f54ed4c7d3aa7faf322fa9252c9ffc6e0"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSession.createDataFrame (cyclomatic 61): SparkSession.createDataFrame has cyclomatic complexity 61 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"104ecb23edc8888ccf436cbe9ae5d5f328b049d5d79e8b3d48ac48d95251eb87"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints.as_spark_type (cyclomatic 60): typehints.as_spark_type has cyclomatic complexity 60 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"17dfcf9b29e79313c97136ae39d6cdd9c1715d6f76bdbe8d3a38fc8d585b6efc"}},{"ruleId":"D1","level":"warning","message":{"text":"CatalystTranspiler._convert_chunk (cyclomatic 60): CatalystTranspiler._convert_chunk has cyclomatic complexity 60 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9908030c53c6d232a05ebe83b917c4b60e663978a25bc69c70689c51f626991"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetToSparkSchemaConverter.convertPrimitiveField (cyclomatic 58): ParquetToSparkSchemaConverter.convertPrimitiveField has cyclomatic complexity 58 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2ab1181130ff3d579269af3803e8b6e42664131623c914022ebaa39b1a99535"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.structFieldFor (cyclomatic 57): SchemaConverters.structFieldFor has cyclomatic complexity 57 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c90dc43b842aa376b2de559b1876ca50d843753539d8876a5f87d2f727ca0c1"}},{"ruleId":"D1","level":"warning","message":{"text":"EvaluatePython.makeFromJavaDefault (cyclomatic 57): EvaluatePython.makeFromJavaDefault has cyclomatic complexity 57 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvaluatePython.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"23b0173c579f1e1becefa3625eea406f5cdd505b58447940a46864c04ac50abd"}},{"ruleId":"D1","level":"warning","message":{"text":"LocIndexerLike.__setitem__ (cyclomatic 56): LocIndexerLike.__setitem__ has cyclomatic complexity 56 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f4e59450ef8a3df37eafe03bb5c32d5d8469a487ceb3d33991e7c799348850e"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkIntervalUtils.stringToInterval (cyclomatic 55): SparkIntervalUtils.stringToInterval has cyclomatic complexity 55 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkIntervalUtils.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d68c79cfdb37c6426711453bd2d513fd1bed4fac9edfef99c553274808b8eae"}},{"ruleId":"D1","level":"warning","message":{"text":"PlanMerger.tryMergePlans (cyclomatic 55): PlanMerger.tryMergePlans has cyclomatic complexity 55 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"453481ba2c26df0a55713a774fc3828949524cc5359ffb9747893f455a9f9bc1"}},{"ruleId":"D1","level":"warning","message":{"text":"BinaryArithmeticWithDatetimeResolver.resolve (cyclomatic 53): BinaryArithmeticWithDatetimeResolver.resolve has cyclomatic complexity 53 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BinaryArithmeticWithDatetimeResolver.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe6de05616497bcff5a4b47d515ae7194155e299dc2c49a9d3d3226e13be0320"}},{"ruleId":"D1","level":"warning","message":{"text":"DataTypeAstBuilder.visitPrimitiveDataType (cyclomatic 52): DataTypeAstBuilder.visitPrimitiveDataType has cyclomatic complexity 52 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e0c46abfb3e2107b3c904bd740092655360cee109b36a3ed5f137874d110ed5"}},{"ruleId":"D1","level":"warning","message":{"text":"DecorrelateInnerQuery.apply (cyclomatic 51): DecorrelateInnerQuery.apply has cyclomatic complexity 51 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala"},"region":{"startLine":476}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb949cf3cdcede0fcc72fa1f7438391e0c663e44cef76cb44243c5fe344b3aed"}},{"ruleId":"D1","level":"warning","message":{"text":"Shim_v2_0.convertFilters (cyclomatic 51): Shim_v2_0.convertFilters has cyclomatic complexity 51 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"b60d98dbc5479e42c744c994698a106907a49a938e043fc80670eeaeb3f9f2f0"}},{"ruleId":"D1","level":"warning","message":{"text":"ScalaReflection.encoderFor (cyclomatic 50): ScalaReflection.encoderFor has cyclomatic complexity 50 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3bb02a43e0175b6527b9c7c8a52882da25d932dd9a387b69eb4dbb632c2be9c"}},{"ruleId":"D1","level":"warning","message":{"text":"PropagateEmptyRelationBase.commonApplyFunc (cyclomatic 50): PropagateEmptyRelationBase.commonApplyFunc has cyclomatic complexity 50 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PropagateEmptyRelation.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddec0ac2720e7a8a823c6f470fed4290f010f3e89363e1f75b34434666312b04"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowDeserializers.deserializerForDefault (cyclomatic 50): ArrowDeserializers.deserializerForDefault has cyclomatic complexity 50 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"a903ad882061c0bd02a5c004ed62154e400b78f62e21da8e47e9ba8d761bf6dc"}},{"ruleId":"D1","level":"warning","message":{"text":"StringRegexExpression.scanQuantifiers (cyclomatic 49): StringRegexExpression.scanQuantifiers has cyclomatic complexity 49 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"6469c662313f544b753c771261e523d90470c6d3ce884974914c09049cea5766"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetFilters.createFilterHelper (cyclomatic 49): ParquetFilters.createFilterHelper has cyclomatic complexity 49 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0d97f1ac1978607b179ac3f7eb0907c016afa1e4f19e93dcddc94516b17e517"}},{"ruleId":"D1","level":"warning","message":{"text":"namespace.concat (cyclomatic 49): namespace.concat has cyclomatic complexity 49 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2380}}}],"partialFingerprints":{"codehealthFindingId/v1":"54da2b0373e003c60e9ecf5bf50e83b47930af7fc525202bc565d473435f895c"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkDateTimeUtils.parseTimestampString (cyclomatic 48): SparkDateTimeUtils.parseTimestampString has cyclomatic complexity 48 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"00640d49962d7cd2f7c78fe4bb62c67d852639b96d9f23f30a8a3664bdf591ec"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantShreddingWriter.tryTypedShred (cyclomatic 48): VariantShreddingWriter.tryTypedShred has cyclomatic complexity 48 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantShreddingWriter.java"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c661e10ceac216e9cebf1b9bbc2cac1bb1af9601066b9bc936f99842c2c731e"}},{"ruleId":"D1","level":"warning","message":{"text":"types.proto_schema_to_pyspark_data_type (cyclomatic 48): types.proto_schema_to_pyspark_data_type has cyclomatic complexity 48 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"83466694ea7e51b4eacfa84172e86c82fbdb30e9f160ff976f7a9dbe8fe94403"}},{"ruleId":"D1","level":"warning","message":{"text":"SerializerBuildHelper.createSerializerDefault (cyclomatic 46): SerializerBuildHelper.createSerializerDefault has cyclomatic complexity 46 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"cde6b7a699ff25ffd8f4c262a0f0e81316f9ee81201f4f8905fa1638ab8a71e8"}},{"ruleId":"D1","level":"warning","message":{"text":"namespace.read_csv (cyclomatic 46): namespace.read_csv has cyclomatic complexity 46 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"215b0b5ddc57a933675e3afd11276c9472ef9314302ebd22d6172f917bf6bbdb"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 46): (anonymous) has cyclomatic complexity 46 (threshold 15). Most of this is not in the body itself: 1 of the 46 points is its own statement and the rest belongs to 33 function items inside it that branch (a function literal at line 436, a function literal at line 575, (anonymous)::(anonymous)::(anonymous)::data, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ed462bba996bba1ab04daf1b79e66301b0c99518a274af4fc493e22bd5d67aa"}},{"ruleId":"D1","level":"warning","message":{"text":"ProtobufSerializer.newConverter (cyclomatic 45): ProtobufSerializer.newConverter has cyclomatic complexity 45 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"912f78c20723f5932df4427b2847118963d2759166a13e36d1facf0303e63b37"}},{"ruleId":"D1","level":"warning","message":{"text":"AvroSerializer.newConverter (cyclomatic 45): AvroSerializer.newConverter has cyclomatic complexity 45 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a455a7ecef2617996b36747d851f06c9946429da44609addb4bb2eb3c44722a"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.toSqlTypeHelper (cyclomatic 45): SchemaConverters.toSqlTypeHelper has cyclomatic complexity 45 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"16cf1e44b54bdffe944a2b2ea3c380a56a751f0280ca69dd7b9038a64677aa27"}},{"ruleId":"D1","level":"warning","message":{"text":"ParseSqlResult.collectPlanReferences (cyclomatic 45): ParseSqlResult.collectPlanReferences has cyclomatic complexity 45 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"325a33e50f208337f6696c00406f4e1058a0d71e6117a0ec0d1b0dc9efe7211f"}},{"ruleId":"D1","level":"warning","message":{"text":"InProcessArrowEvalPythonEvaluatorFactory.evaluateBatches (cyclomatic 45): InProcessArrowEvalPythonEvaluatorFactory.evaluateBatches has cyclomatic complexity 45 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/InProcessArrowEvalPythonEvaluatorFactory.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"c28d98dc41769939a0ad5948bd32ea50e063b49d75cdc4e22723e545d0c87905"}},{"ruleId":"D1","level":"warning","message":{"text":"exports (cyclomatic 45): exports has cyclomatic complexity 45 (threshold 15). Of this number, 28 points are the body\u0027s own statements and 17 belong to 18 function items inside it that branch. To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":".github/workflows/update_build_status.js"},"region":{"startLine":20}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc66a0b6c04ff0ccc441847b7401623c4cdbfd8a4993f9eb89c047d181968ee8"}},{"ruleId":"D1","level":"warning","message":{"text":"Master.receive (cyclomatic 44): Master.receive has cyclomatic complexity 44 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"b680e79c67b5af071efe16c5dd061f471c92c20d5d95129e8886163c22f6cf3a"}},{"ruleId":"D1","level":"warning","message":{"text":"JdbcUtils.getCatalystType (cyclomatic 44): JdbcUtils.getCatalystType has cyclomatic complexity 44 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"115574564e69845a2b93fa2a96c88bf76e2e051029210eb093c526c65873da5e"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetRowConverter.newConverterDefault (cyclomatic 44): ParquetRowConverter.newConverterDefault has cyclomatic complexity 44 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"63b03160f5384a5bfd52a436a3685a172ed3dfe0711131a6fe71d834d9493bb7"}},{"ruleId":"D1","level":"warning","message":{"text":"FunctionArgumentTypeCoercion.apply (cyclomatic 43): FunctionArgumentTypeCoercion.apply has cyclomatic complexity 43 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"f23da3fa1da1bfa8ddc4608ed326876eeeac0720ef936cb223e97d3447959d9c"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnNodeToExpressionConverter.apply (cyclomatic 43): ColumnNodeToExpressionConverter.apply has cyclomatic complexity 43 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/columnNodeSupport.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"2394a0f06e58eb286632318c6d7e8c23e483a82c00ea38cce5c5fe534c4561ef"}},{"ruleId":"D1","level":"warning","message":{"text":"MLExpressionUtils.scaleShift (cyclomatic 43): MLExpressionUtils.scaleShift has cyclomatic complexity 43 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"2156885904e5fbab5414c956c7c0a3188bad72b68c3d0a2c8eea09a8995a389f"}},{"ruleId":"D1","level":"warning","message":{"text":"Resampler._bin_timestamp (cyclomatic 43): Resampler._bin_timestamp has cyclomatic complexity 43 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/resample.py"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c1f00e1d8c5c5663ee230dd88864ee21dfb830d3315a39c42b85ce475bc6960"}},{"ruleId":"D1","level":"warning","message":{"text":"StateSourceOptions.apply (cyclomatic 42): StateSourceOptions.apply has cyclomatic complexity 42 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffab381002f5ba906b79c75f85d65a0afe1be5c2d0596c8eac8c50b931b00357"}},{"ruleId":"D1","level":"warning","message":{"text":"types._parse_datatype_json_value (cyclomatic 42): types._parse_datatype_json_value has cyclomatic complexity 42 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2674}}}],"partialFingerprints":{"codehealthFindingId/v1":"a66c0c0fd70a0782675f9fefd6efc52cd82122fc67b4465422e50b404a4853db"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSubmitArguments.handle (cyclomatic 41): SparkSubmitArguments.handle has cyclomatic complexity 41 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aed85d175d9574b7092568aa97b6cb95ea4d91a63437cf78feef37c08fc4c66"}},{"ruleId":"D1","level":"warning","message":{"text":"UnwrapCastInBinaryComparison.simplifyNumericComparison (cyclomatic 40): UnwrapCastInBinaryComparison.simplifyNumericComparison has cyclomatic complexity 40 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"7709762da0d326445fef1d7d8e5c57965c7db39460dcde0e8dcc292126ad84d0"}},{"ruleId":"D1","level":"warning","message":{"text":"InternalFrame.__init__ (cyclomatic 40): InternalFrame.__init__ has cyclomatic complexity 40 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cf67e4dc03011fae7d02ceb8604a0fcd42815f38057e1bd49d4e7118f9779a2"}},{"ruleId":"D1","level":"warning","message":{"text":"namespace.merge_asof (cyclomatic 40): namespace.merge_asof has cyclomatic complexity 40 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":3110}}}],"partialFingerprints":{"codehealthFindingId/v1":"174051975422e4b0526b0584adc9b9391d6139fd5f37e460be920ef82b113124"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkParserUtils.unescapeSQLString (cyclomatic 39): SparkParserUtils.unescapeSQLString has cyclomatic complexity 39 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkParserUtils.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b0b4cd7b32b54d8eb9127d1581b464e13ee482b9164b7d0d1b44e9ccc61958b"}},{"ruleId":"D1","level":"warning","message":{"text":"LocIndexer._select_rows_by_slice (cyclomatic 39): LocIndexer._select_rows_by_slice has cyclomatic complexity 39 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1064}}}],"partialFingerprints":{"codehealthFindingId/v1":"e505802438c791e7424602fbb34ac9841d051bdf978e8c7ed978425208af4163"}},{"ruleId":"D1","level":"warning","message":{"text":"DAGScheduler.submitMissingTasks (cyclomatic 38): DAGScheduler.submitMissingTasks has cyclomatic complexity 38 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3215}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a72b470e0ec34b6c61a5f9e0acdd37a85700c54c12fa93fa31f55a701b37e15"}},{"ruleId":"D1","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.next (cyclomatic 38): ShuffleBlockFetcherIterator.next has cyclomatic complexity 38 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":808}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cbd9125830b8abde0add4a39b6df9631ecd7195d4affba85888e246c7f6e791"}},{"ruleId":"D1","level":"warning","message":{"text":"EnsureRequirements.checkKeyGroupCompatible (cyclomatic 38): EnsureRequirements.checkKeyGroupCompatible has cyclomatic complexity 38 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9f7a735cced774be32c63e3a201ab7dc36d084d0754a8738abaf7212cf30363"}},{"ruleId":"D1","level":"warning","message":{"text":"LiteralExpression._to_value (cyclomatic 38): LiteralExpression._to_value has cyclomatic complexity 38 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4aa92a4b725680a5a2e221ca53b9f1032844c5350b62585393fb8c5867ff329"}},{"ruleId":"D1","level":"warning","message":{"text":"WeightedLeastSquares.fit (cyclomatic 37): WeightedLeastSquares.fit has cyclomatic complexity 37 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"12eb555cdfad3098dc14d66e8de74741705f6f2ff60b15b5008319b8f91c7261"}},{"ruleId":"D1","level":"warning","message":{"text":"ValidateSubqueryExpression.checkCorrelationsInSubquery (cyclomatic 37): ValidateSubqueryExpression.checkCorrelationsInSubquery has cyclomatic complexity 37 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ValidateSubqueryExpression.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e18e3951d6d127e00ff614f7b84d14ced84ccecf0c4e0b2c5be2bebe200b31d"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.withPredicate (cyclomatic 37): AstBuilder.withPredicate has cyclomatic complexity 37 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":3861}}}],"partialFingerprints":{"codehealthFindingId/v1":"f06ecb12c018b15394086aac932c16eaaa60786ca6817d7117187db52ebddb1e"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkToParquetSchemaConverter.convertFieldDefault (cyclomatic 37): SparkToParquetSchemaConverter.convertFieldDefault has cyclomatic complexity 37 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":673}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3f5bd74dc7832f7c66a825b44446f3cfcfd297689da96e9229071af9f56a108"}},{"ruleId":"D1","level":"warning","message":{"text":"OnHeapColumnVector.reserveInternal (cyclomatic 37): OnHeapColumnVector.reserveInternal has cyclomatic complexity 37 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a639fe00c3cec433b856fae9adfd25bb60e36d0a6f2534b4d9691b0507977b9"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.merge (cyclomatic 37): DataFrame.merge has cyclomatic complexity 37 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8812}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d04e0ccc0a1ce1edec89d836e2683e06dd4b2515b3684241bd500b04bc7e7b0"}},{"ruleId":"D1","level":"warning","message":{"text":"types.pyspark_types_to_proto_types (cyclomatic 37): types.pyspark_types_to_proto_types has cyclomatic complexity 37 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"01f99c7d91a93e151892e24bd1389f7d58a1792de930bdf4d5cc110bec6e91b8"}},{"ruleId":"D1","level":"warning","message":{"text":"LogisticRegression.train (cyclomatic 36): LogisticRegression.train has cyclomatic complexity 36 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"4889f38e5a82b7f82ee8ac4c9e071ca445c10caa7d76c118b26618a47c3554a7"}},{"ruleId":"D1","level":"warning","message":{"text":"ValidateSubqueryExpression.apply (cyclomatic 36): ValidateSubqueryExpression.apply has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ValidateSubqueryExpression.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e4331d5bd2e6c52a49dd4df78d814a608390f6d016b1b52b126c422c51255ab"}},{"ruleId":"D1","level":"warning","message":{"text":"InterpretedHashFunction.hash (cyclomatic 36): InterpretedHashFunction.hash has cyclomatic complexity 36 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":717}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e10e5267cba0393ae5452e849114037f2e80768b1be3492860d6cc24a0eeed4"}},{"ruleId":"D1","level":"warning","message":{"text":"IntervalUtils.castStringToDTInterval (cyclomatic 36): IntervalUtils.castStringToDTInterval has cyclomatic complexity 36 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":275}}}],"partialFingerprints":{"codehealthFindingId/v1":"eef8668cc0539bba832545bda4875ebf04e279d7e97a159a5b2d144d04093122"}},{"ruleId":"D1","level":"warning","message":{"text":"DataTypeProtoConverter.toConnectProtoTypeDefault (cyclomatic 36): DataTypeProtoConverter.toConnectProtoTypeDefault has cyclomatic complexity 36 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/DataTypeProtoConverter.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"d350c393098626c992ec1a80575723bcf1490fb37e7cadfe248917ab64cb4b8f"}},{"ruleId":"D1","level":"warning","message":{"text":"MLHandler._handleMlCommand (cyclomatic 36): MLHandler._handleMlCommand has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/MLHandler.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"f122b2b226611a37d970040b015feb401de803a49805819951f8f49f21768cdf"}},{"ruleId":"D1","level":"warning","message":{"text":"MultiColumnInSubqueryEvaluator.eval (cyclomatic 36): MultiColumnInSubqueryEvaluator.eval has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb0f9e76998db4827ac03a56f775ebba68f86bff1b3c74d3477761c6d3da95c0"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.pivot_table (cyclomatic 36): DataFrame.pivot_table has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6942}}}],"partialFingerprints":{"codehealthFindingId/v1":"49dea39e1cc0e4b4ed6f7926fc647f9793bc923b41b44711f1bc525742764538"}},{"ruleId":"D1","level":"warning","message":{"text":"LocIndexerLike.__getitem__ (cyclomatic 36): LocIndexerLike.__getitem__ has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":439}}}],"partialFingerprints":{"codehealthFindingId/v1":"2058b0a34031c0bfe81ed579afeb63202835b2f9101829dcec67b20c2744cbbf"}},{"ruleId":"D1","level":"warning","message":{"text":"namespace.get_dummies (cyclomatic 36): namespace.get_dummies has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2153}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c786936f2c796aa958db19978f9003297e3a19afcfb322e869f977a429e8059"}},{"ruleId":"D1","level":"warning","message":{"text":"CatalystTranspiler._category_uncached (cyclomatic 36): CatalystTranspiler._category_uncached has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":598}}}],"partialFingerprints":{"codehealthFindingId/v1":"e438fd43116956bfcf33fc35977952a66aa7f2a8ae0063c1e364d2ad8e7d216f"}},{"ruleId":"D1","level":"warning","message":{"text":"ProtobufDeserializer.newWriter (cyclomatic 35): ProtobufDeserializer.newWriter has cyclomatic complexity 35 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"49c45c4fe014e3bf85c43a65c793b2c74bad8c0496ea2c70ca1ebfa86e4b6b2e"}},{"ruleId":"D1","level":"warning","message":{"text":"Decimal.changePrecision (cyclomatic 35): Decimal.changePrecision has cyclomatic complexity 35 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"53801f3a3bc88919eb8fe9e218756945d5bedb98a50bfa47901f9a12d436625b"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantGet.cast (cyclomatic 35): VariantGet.cast has cyclomatic complexity 35 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":763}}}],"partialFingerprints":{"codehealthFindingId/v1":"88fe1ec909f65144caa9abefc4dc5f7a02491d3cdc7abd3d5caee4a861921faf"}},{"ruleId":"D1","level":"warning","message":{"text":"SqlStatementSplitter.splitWithPositions (cyclomatic 35): SqlStatementSplitter.splitWithPositions has cyclomatic complexity 35 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e711b1e144a0027ecc378106c1acb272065d9010de07de01459e98f3be2649c"}},{"ruleId":"D1","level":"warning","message":{"text":"DataTypeUtils.canWrite (cyclomatic 35): DataTypeUtils.canWrite has cyclomatic complexity 35 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/DataTypeUtils.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"da1d3ffb74757df1da6a5923769e47ebeca811083a2e815cc25dcf4feb46d8f5"}},{"ruleId":"D1","level":"warning","message":{"text":"merge_spark_pr.main (cyclomatic 35): merge_spark_pr.main has cyclomatic complexity 35 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3353}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aca3794aa394daa088014a6d27f464feb8802fadf1c3dc8e88fb2ee5d8fdce3"}},{"ruleId":"D1","level":"warning","message":{"text":"Master.receiveAndReply (cyclomatic 34): Master.receiveAndReply has cyclomatic complexity 34 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1f57858574a2e0fb32b1af0e0dfc9da949e09846b345b66d6fd71b86274c079"}},{"ruleId":"D1","level":"warning","message":{"text":"Worker.receive (cyclomatic 34): Worker.receive has cyclomatic complexity 34 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":534}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dea2f75195be97236e83dc195af352ff3938a9e5ab72186cf33f82a89dabc3d"}},{"ruleId":"D1","level":"warning","message":{"text":"TypeCoercion.implicitCast (cyclomatic 34): TypeCoercion.implicitCast has cyclomatic complexity 34 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"971e4990f70b290987cc20bc887471cf7cd1710a380cdae58eb32aad1fe490ce"}},{"ruleId":"D1","level":"warning","message":{"text":"InterpretedUnsafeProjection.generateFieldWriter (cyclomatic 34): InterpretedUnsafeProjection.generateFieldWriter has cyclomatic complexity 34 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/InterpretedUnsafeProjection.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"4049b7cfea4cbaa59cd03b9c0bfeb525805ffdd8066f9ff986ded4f5b4caf560"}},{"ruleId":"D1","level":"warning","message":{"text":"FilterEstimation.evaluateBinaryForTwoColumns (cyclomatic 34): FilterEstimation.evaluateBinaryForTwoColumns has cyclomatic complexity 34 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae27a897e2226a668c6b0f2cee4dc05fa9220a286ee00616926c6c1942ac0089"}},{"ruleId":"D1","level":"warning","message":{"text":"PredicateUtils.toV1 (cyclomatic 34): PredicateUtils.toV1 has cyclomatic complexity 34 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/connector/PredicateUtils.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ff39de68eca798e7c5de7fc4c944f08b31d00bcb903cab61069030587d72f72"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnNodeToProtoConverter.apply (cyclomatic 34): ColumnNodeToProtoConverter.apply has cyclomatic complexity 34 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"29a77c4c0f4bbc09aab976b6f5c3e969800a95e3bb9efd3d50c92cbb6363fb93"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowColumnVector.initAccessor (cyclomatic 34): ArrowColumnVector.initAccessor has cyclomatic complexity 34 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6dea030e60e1d6103480a58dd48bbafd3dca008000a17361dec5a58ded49f7c"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.melt (cyclomatic 34): DataFrame.melt has cyclomatic complexity 34 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10853}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa1e503f77061d1aa3f45b78ac6c6b23a8566d44f2ffb9b115a45d059d6d4d2f"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveFunctions.apply (cyclomatic 33): ResolveFunctions.apply has cyclomatic complexity 33 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2420}}}],"partialFingerprints":{"codehealthFindingId/v1":"463706b898115990f9c825afe5a03351e694b4623b9b7a1b1b6fa723f4703082"}},{"ruleId":"D1","level":"warning","message":{"text":"ToStringBase.castToStringDefault (cyclomatic 33): ToStringBase.castToStringDefault has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ToStringBase.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0ee5e0d64be7813ea31ca3566e3a1500a0f7baba3b8bc7686e1b415d23d3065"}},{"ruleId":"D1","level":"warning","message":{"text":"OrcSerializer.newConverter (cyclomatic 33): OrcSerializer.newConverter has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcSerializer.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"828e9dbfcfbcd51b78bfd82dfa34d6c6ef274afeb75e7cb5fd1b0c522760c1eb"}},{"ruleId":"D1","level":"warning","message":{"text":"SortMergeJoinEvaluator.eval (cyclomatic 33): SortMergeJoinEvaluator.eval has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"74625476bce714280034317d833752943f6bd019845ba6b706d8989463ecc9d1"}},{"ruleId":"D1","level":"warning","message":{"text":"AbstractCommandBuilder.buildClassPath (cyclomatic 33): AbstractCommandBuilder.buildClassPath has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/AbstractCommandBuilder.java"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"4316394fe74d21fe096f5f07013f94051a489b7509cfbc33b18383c4f3300b3c"}},{"ruleId":"D1","level":"warning","message":{"text":"ShreddingUtils.rebuild (cyclomatic 33): ShreddingUtils.rebuild has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/ShreddingUtils.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"2eaa6949deeeb984fa762b9bec8fa6f4de3efaf076e441175ee437eff4198545"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.xs (cyclomatic 33): DataFrame.xs has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3589}}}],"partialFingerprints":{"codehealthFindingId/v1":"f91bf22bcb8fe7ce3dfd3cc6d095c51ada876ee800f81e83d71f762211c75eaa"}},{"ruleId":"D1","level":"warning","message":{"text":"types.from_arrow_type (cyclomatic 33): types.from_arrow_type has cyclomatic complexity 33 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"21102c4de4d641353c6e0d503b084352171a268fdfb05b76289d947f8bd22dc2"}},{"ruleId":"D1","level":"warning","message":{"text":"pandasutils._assert_pandas_almost_equal (cyclomatic 33): pandasutils._assert_pandas_almost_equal has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5a53676695420c2905411611d81a8cc8fd7ad0436aff24d0812b385fd108be3"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskSchedulerImpl.resourceOffers (cyclomatic 32): TaskSchedulerImpl.resourceOffers has cyclomatic complexity 32 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":573}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb63cc3cd5de84c207a16812baea0dc536e96977832cb4945db859cdd2e47f78"}},{"ruleId":"D1","level":"warning","message":{"text":"UnivocityParser.makeConverter (cyclomatic 32): UnivocityParser.makeConverter has cyclomatic complexity 32 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"64729d0113597b058aaca57622544e65e229de9b0ca34b94c00fcd2ecfc1bcf3"}},{"ruleId":"D1","level":"warning","message":{"text":"Literal.sql (cyclomatic 32): Literal.sql has cyclomatic complexity 32 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: Literal.componentTypeToDataType (cyclomatic 34) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":654}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcca4ca73613bf59941eb67a8f03d441c6daad47b756e0c1e887b7ea4f6da601"}},{"ruleId":"D1","level":"warning","message":{"text":"SimpleMetricsCachedBatchSerializer.buildFilter (cyclomatic 32): SimpleMetricsCachedBatchSerializer.buildFilter has cyclomatic complexity 32 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/columnar/CachedBatchSerializer.scala"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"507b428e284edb76edef79f196ff56986d032b70c14c21a08943a8eed2e428a7"}},{"ruleId":"D1","level":"warning","message":{"text":"Series.replace (cyclomatic 32): Series.replace has cyclomatic complexity 32 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5089}}}],"partialFingerprints":{"codehealthFindingId/v1":"29434818d0f8c2942f0bdec7d8c0f37308628fc6ea55c915d79112e8cde237d3"}},{"ruleId":"D1","level":"warning","message":{"text":"UserDefinedFunction._check_return_type (cyclomatic 32): UserDefinedFunction._check_return_type has cyclomatic complexity 32 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":334}}}],"partialFingerprints":{"codehealthFindingId/v1":"f39d5dcd4edfd2099dc15dff80b3b92b260e826cc4c5cb1de4fa9f28f0d49d7d"}},{"ruleId":"D1","level":"warning","message":{"text":"SerDe.writeObject (cyclomatic 31): SerDe.writeObject has cyclomatic complexity 31 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/SerDe.scala"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"0339ec0e93e23fc307ea0e8663e6ad136fde176df63cdc81c3b51c262c2384e8"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkIntervalUtils.toDayTimeIntervalString (cyclomatic 31): SparkIntervalUtils.toDayTimeIntervalString has cyclomatic complexity 31 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkIntervalUtils.scala"},"region":{"startLine":435}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a299c8ea6107f85921bd8d38bea909d9d3790605b03b385601f31a217ce3f8b"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnPruning.apply (cyclomatic 31): ColumnPruning.apply has cyclomatic complexity 31 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1517}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a68d0d576f5f14d3c26537cb2ff65599a1f64a7f3b9a3ee803bb7ff234418f4"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkContext._do_init (cyclomatic 31): SparkContext._do_init has cyclomatic complexity 31 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/context.py"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbe87bcabf24609be7d10d3c5a46027b49491044b72e3bf7e1f34f835db35408"}},{"ruleId":"D1","level":"warning","message":{"text":"GroupBy.apply (cyclomatic 31): GroupBy.apply has cyclomatic complexity 31 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1818}}}],"partialFingerprints":{"codehealthFindingId/v1":"f319398a1b951a1291b3bd518684d2ca2f4f2093c48b9df7c915667020519604"}},{"ruleId":"D1","level":"warning","message":{"text":"types._infer_type (cyclomatic 31): types._infer_type has cyclomatic complexity 31 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2994}}}],"partialFingerprints":{"codehealthFindingId/v1":"0096371616301777ab4058c97e53bcce930545874068670b3da08ad065e7aa24"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskRunner.run (cyclomatic 30): TaskRunner.run has cyclomatic complexity 30 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"b442c3be514ee895fdd4ad8f034a04d76171b93e4c78ab7b8f3863fc3cb1c040"}},{"ruleId":"D1","level":"warning","message":{"text":"DataType.nameToType (cyclomatic 30): DataType.nameToType has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"8acb6ce5b2d560fa9e9a1468c5ac63911558494077c4fe1f695d787a994e5dbe"}},{"ruleId":"D1","level":"warning","message":{"text":"V2ExpressionUtils.convertMathFunc (cyclomatic 30): V2ExpressionUtils.convertMathFunc has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/V2ExpressionUtils.scala"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"99c07623a97915d711a133f1ec05812be930af750f1167bcf4f42fcdaec3b184"}},{"ruleId":"D1","level":"warning","message":{"text":"UDFRegistration.registerJava (cyclomatic 30): UDFRegistration.registerJava has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/UDFRegistration.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4ed40567a0b52b78639c0abafabba4d3dbeb78525bd5be1a962657c5af4c8f4"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkShreddingUtils.buildVariantSchema (cyclomatic 30): SparkShreddingUtils.buildVariantSchema has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":559}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7e41a8c9fb1b38a827766a2bc9438098275c9c8f96295f14dd492bcde77a93b"}},{"ruleId":"D1","level":"warning","message":{"text":"StateStoreCoordinator.receiveAndReply (cyclomatic 30): StateStoreCoordinator.receiveAndReply has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreCoordinator.scala"},"region":{"startLine":317}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9b41614f769056979b82449e584a166bb6698b4e9f6f12ffa1bc9c25ebbe019"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveInspectors.toInspector (cyclomatic 30): HiveInspectors.toInspector has cyclomatic complexity 30 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: HiveInspectors.javaTypeToDataType (cyclomatic 41) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1085}}}],"partialFingerprints":{"codehealthFindingId/v1":"54d01d2d3caacbd1db9368e6050d1aee84e6befe7fb2a0dab8a4c5c733e5f52e"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSubmitCommandBuilder.buildSparkSubmitArgs (cyclomatic 30): SparkSubmitCommandBuilder.buildSparkSubmitArgs has cyclomatic complexity 30 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkSubmitCommandBuilder.java"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cf5fe2257db059830701ea40df190df8256347c5c8b0adcf5ef631c348a0330"}},{"ruleId":"D1","level":"warning","message":{"text":"types.to_arrow_type (cyclomatic 30): types.to_arrow_type has cyclomatic complexity 30 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae31629ff5bf82dcc9c4d620755c7d20de743707acc1965a3dfcbf4975a09868"}},{"ruleId":"D1","level":"warning","message":{"text":"AppStatusListener.onTaskEnd (cyclomatic 29): AppStatusListener.onTaskEnd has cyclomatic complexity 29 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":669}}}],"partialFingerprints":{"codehealthFindingId/v1":"b93e458e250449f1cf68d3fe029f8cd108e1fc8bd0775e56e68a09227be152ae"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveReferences.expandStarExpression (cyclomatic 29): ResolveReferences.expandStarExpression has cyclomatic complexity 29 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2117}}}],"partialFingerprints":{"codehealthFindingId/v1":"40cb4959b7e67c4bb7fb0cf9712bc6f49d8e346bc7a1f3891d9ff557e3d6906a"}},{"ruleId":"D1","level":"warning","message":{"text":"CodegenContext.collectInputs (cyclomatic 29): CodegenContext.collectInputs has cyclomatic complexity 29 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala"},"region":{"startLine":1331}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a10c41a550c9d5e657ee5890bfbf7fa0320fae77a17db278afe10d651addfb2"}},{"ruleId":"D1","level":"warning","message":{"text":"Literal.validateLiteralValue (cyclomatic 29): Literal.validateLiteralValue has cyclomatic complexity 29 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: Literal.componentTypeToDataType (cyclomatic 34) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":253}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ac02421196988a12c1ff4bb236805c299c9ab14d8aa55eaa591b64a209296b8"}},{"ruleId":"D1","level":"warning","message":{"text":"JsonInferSchema.inferField (cyclomatic 29): JsonInferSchema.inferField has cyclomatic complexity 29 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9d72cd02f520b57461f654fa1200e54e3ba527561205298fcb877b2747cc2a6"}},{"ruleId":"D1","level":"warning","message":{"text":"SimplifyConditionals.apply (cyclomatic 29): SimplifyConditionals.apply has cyclomatic complexity 29 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":807}}}],"partialFingerprints":{"codehealthFindingId/v1":"d963ee2b0cc6ec1a4823447e94943f344f39adf8e5f0a0195b3c088f111db8c6"}},{"ruleId":"D1","level":"warning","message":{"text":"TreeNode.parseToJson (cyclomatic 29): TreeNode.parseToJson has cyclomatic complexity 29 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1319}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b153d6ff428862a1b9eef73318269880437e04efa050e024ba7a361bdb460ff"}},{"ruleId":"D1","level":"warning","message":{"text":"StringUtils.splitSemiColon (cyclomatic 29): StringUtils.splitSemiColon has cyclomatic complexity 29 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/StringUtils.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"d83ca763e70f5bce895b8fb25a6bff5e3be4562ebd3de579788d6d65575b166f"}},{"ruleId":"D1","level":"warning","message":{"text":"StreamingV2ScanPushDown.buildScan (cyclomatic 29): StreamingV2ScanPushDown.buildScan has cyclomatic complexity 29 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":558}}}],"partialFingerprints":{"codehealthFindingId/v1":"8eba28ff2c76f37dbf6712004395d589c965d7a6ca4dfd37267aedc6e3dec358"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSQLCLIDriver.main (cyclomatic 29): SparkSQLCLIDriver.main has cyclomatic complexity 29 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"78944e390b2748ef75e173fb7ed1f89306b10103ecd650b876762354d246376f"}},{"ruleId":"D1","level":"warning","message":{"text":"makeSortable (cyclomatic 29): makeSortable has cyclomatic complexity 29 (threshold 15). Most of this is not in the body itself: 14 of the 29 points are its own statements and the rest belongs to 2 function items inside it that branch (innerSortFunction, a function literal at line 133). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"11d9130b8ec5f7b8f6f320f5031da87459f944f1e45ed18e8feb0d219b6ca226"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveRelations.apply (cyclomatic 28): ResolveRelations.apply has cyclomatic complexity 28 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1341}}}],"partialFingerprints":{"codehealthFindingId/v1":"7056722cd3ff701a4dc5d9952a91ca0cea3ec601e7376cc1304ac44c5329af27"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveSQLFunctions.rewrite (cyclomatic 28): ResolveSQLFunctions.rewrite has cyclomatic complexity 28 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2972}}}],"partialFingerprints":{"codehealthFindingId/v1":"f34a3e9f86c04498d05dc6667003a464fcdf28b8b59e43b30dc32c0441893840"}},{"ruleId":"D1","level":"warning","message":{"text":"UnsafeRowUtils.validateStructuralIntegrityWithReasonImpl (cyclomatic 28): UnsafeRowUtils.validateStructuralIntegrityWithReasonImpl has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowUtils.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d73be004b6a99a62de8af6895862907fdf4a8f014c7cca64ea31d300df7b27c"}},{"ruleId":"D1","level":"warning","message":{"text":"BufferSetterGetterUtils.createGetters (cyclomatic 28): BufferSetterGetterUtils.createGetters has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3dbc0d2d05e2117d0d790806cf2f73151c7799499669e2d24c054d7ff51830f"}},{"ruleId":"D1","level":"warning","message":{"text":"ShuffleExchangeExec.prepareShuffleDependency (cyclomatic 28): ShuffleExchangeExec.prepareShuffleDependency has cyclomatic complexity 28 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d961619f413af9ae961eec533de0469daa3656041535f97145d4bfb4259cf14"}},{"ruleId":"D1","level":"warning","message":{"text":"WritableColumnVector.appendObjects (cyclomatic 28): WritableColumnVector.appendObjects has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe90c054600763f24a5f5447ad7cb81d74f9d680adc37fa1de2f8b230ec7478c"}},{"ruleId":"D1","level":"warning","message":{"text":"functions._validate_and_transform_prediction_result (cyclomatic 28): functions._validate_and_transform_prediction_result has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/functions.py"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba969bd8bab6fcc173e78ea57ecd73b50f30c36f8a95925da4a64fe280e253d2"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.dropna (cyclomatic 28): DataFrame.dropna has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6099}}}],"partialFingerprints":{"codehealthFindingId/v1":"76e9c7816567f1344f199b2a89bd9fbecee5066f1184b8576399175c723ea28e"}},{"ruleId":"D1","level":"warning","message":{"text":"PandasOnSparkTestUtils.assert_eq (cyclomatic 28): PandasOnSparkTestUtils.assert_eq has cyclomatic complexity 28 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb513aa225a2714a952c8de6af48193e4216ef70c2ef0fc099d909e3c5eea205"}},{"ruleId":"D1","level":"warning","message":{"text":"FunctionResolution.validateFunction (cyclomatic 27): FunctionResolution.validateFunction has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"65ee310a9b127c91d5e20f172409a690ee4b5f3e12403913bcdeb9e96c547125"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveLateralColumnAliasReference.apply0 (cyclomatic 27): ResolveLateralColumnAliasReference.apply0 has cyclomatic complexity 27 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveLateralColumnAliasReference.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"be4719cf37db3b2fea37b4a7f1ad5bc699a0beddbfe69ad5a1b30c871ea612a0"}},{"ruleId":"D1","level":"warning","message":{"text":"CatalogTable.toJsonLinkedHashMap (cyclomatic 27): CatalogTable.toJsonLinkedHashMap has cyclomatic complexity 27 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":642}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b69bdc2c98b6451453dcbada2e53db28fc7b79667e86cdf75e6c05c17ab7a90"}},{"ruleId":"D1","level":"warning","message":{"text":"UnivocityGenerator.makeConverter (cyclomatic 27): UnivocityGenerator.makeConverter has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityGenerator.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"723022301c439aa9ba9c2151c30d30a8fca4c8e738c97040ded405feb3bb8b9b"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantValueConverter.convertInput (cyclomatic 27): VariantValueConverter.convertInput has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":480}}}],"partialFingerprints":{"codehealthFindingId/v1":"edc6c9fc56fa52ec2d83404e7c2fb40bb3b2e1c7602cd897cc53c14d4ef7908a"}},{"ruleId":"D1","level":"warning","message":{"text":"BufferSetterGetterUtils.createSetters (cyclomatic 27): BufferSetterGetterUtils.createSetters has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"966563bb522af67e0abca940d880db5721f280cf9510eda2a1e684c731fe22f6"}},{"ruleId":"D1","level":"warning","message":{"text":"CreateSQLFunctionCommand.run (cyclomatic 27): CreateSQLFunctionCommand.run has cyclomatic complexity 27 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f4552dac9d7e4c561fcc15cf5b47d624097397a1de8ef74d674d30574f79862"}},{"ruleId":"D1","level":"warning","message":{"text":"XSDToSchema.getStructField (cyclomatic 27): XSDToSchema.getStructField has cyclomatic complexity 27 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b6298ca0c9f509f9a83353391907103da3f2aac0c5dbc0c39b4fe7f3f569cbe"}},{"ruleId":"D1","level":"warning","message":{"text":"MicroBatchExecution.runBatch (cyclomatic 27): MicroBatchExecution.runBatch has cyclomatic complexity 27 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":1198}}}],"partialFingerprints":{"codehealthFindingId/v1":"877e2dec11c44e192b5471b7a5d5319f065ac3d704040e72ecab77c25a56dccb"}},{"ruleId":"D1","level":"warning","message":{"text":"daemon.manager (cyclomatic 27): daemon.manager has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/daemon.py"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"52ddff4b59ddc222ddd4bb76e7cab74ab308f95330be7dca1f7ff8cd2cfe0063"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 27): (anonymous) has cyclomatic complexity 27 (threshold 15). Most of this is not in the body itself: 2 of the 27 points are its own statements and the rest belongs to 12 function items inside it that branch (init::renderSummary, init::render, init::renderSubExecutionsHtml, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":22}}}],"partialFingerprints":{"codehealthFindingId/v1":"b615a378dffaeb811bb4224e9d39fbfcb910d85e8d5e27a867013fad6a3bfa4d"}},{"ruleId":"D1","level":"warning","message":{"text":"KafkaSourceProvider.validateGeneralOptions (cyclomatic 26): KafkaSourceProvider.validateGeneralOptions has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4d642e48d0214bde66435160cd04aa5ffcdea8d533ba413977fcb7ebcd4c2a5"}},{"ruleId":"D1","level":"warning","message":{"text":"LinearRegression.train (cyclomatic 26): LinearRegression.train has cyclomatic complexity 26 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d6113805e5523adf4f1387aecf970e276dbfdc3488bb1feb8cddb3f90af2f15"}},{"ruleId":"D1","level":"warning","message":{"text":"BindParameters.apply (cyclomatic 26): BindParameters.apply has cyclomatic complexity 26 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/parameters.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"6624605d53e8311e9980407d85b39889588f938d8a96e4ade1f4d7fa3f24a95f"}},{"ruleId":"D1","level":"warning","message":{"text":"JsonTableEvaluator.anyMatch (cyclomatic 26): JsonTableEvaluator.anyMatch has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":880}}}],"partialFingerprints":{"codehealthFindingId/v1":"3eb706c975f2992297561b65e9a529632bf0f3ebcf1622d1c552ad5cd48d8825"}},{"ruleId":"D1","level":"warning","message":{"text":"GetJsonObjectEvaluator.evaluatePath (cyclomatic 26): GetJsonObjectEvaluator.evaluatePath has cyclomatic complexity 26 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1435}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbb3af46a1e4c4aa9c034e31f678e2941c7c0f5680f495fc14d76a84bf7cf184"}},{"ruleId":"D1","level":"warning","message":{"text":"LiteralValueProtoConverter.getProtoDataTypeDefault (cyclomatic 26): LiteralValueProtoConverter.getProtoDataTypeDefault has cyclomatic complexity 26 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: LiteralValueProtoConverter.toDataType (cyclomatic 34) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/LiteralValueProtoConverter.scala"},"region":{"startLine":544}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed072e0896985add98d29c2547ca802283f2f86fd4d41e575dd9dd5840cc1f75"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkConnectAnalyzeHandler.process (cyclomatic 26): SparkConnectAnalyzeHandler.process has cyclomatic complexity 26 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectAnalyzeHandler.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"622857bc8375af5fa60f60c598ff41c952ba0f2334becd9df9b31b9421a6dd4a"}},{"ruleId":"D1","level":"warning","message":{"text":"DataSource.lookupDataSource (cyclomatic 26): DataSource.lookupDataSource has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd2ad8ce6c6446ae17eeffb008896032a2b2f4ada02b83ed5f992b1b253bbbc2"}},{"ruleId":"D1","level":"warning","message":{"text":"FileScanRDD.compute (cyclomatic 26): FileScanRDD.compute has cyclomatic complexity 26 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"68fbe4f9064ab79cb8e01d7fd3980342068e3e17edfe35e47bad3fdcf52253b6"}},{"ruleId":"D1","level":"warning","message":{"text":"OrcDeserializer.newWriter (cyclomatic 26): OrcDeserializer.newWriter has cyclomatic complexity 26 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"59337c0e68bd96954b5f1bac93e2dafd67ca1477ca765c5b538d9cc593b20eed"}},{"ruleId":"D1","level":"warning","message":{"text":"DataTypeOps.__new__ (cyclomatic 26): DataTypeOps.__new__ has cyclomatic complexity 26 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"493c727ed6e4f4ccbfbcb3a67ef35077dce85f5e6a67546ac50a1129b6ceb0ec"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.drop (cyclomatic 26): DataFrame.drop has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7749}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fb3697909958f57f1e6a21f2d9d528d4b22e5e4e650b5762203503d3c400a10"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.describe (cyclomatic 26): DataFrame.describe has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10024}}}],"partialFingerprints":{"codehealthFindingId/v1":"941b09d3e66c99fd29d3436d218c86bbdd169bf1c6547dfc257e32606d94dea2"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkConnectClient._analyze (cyclomatic 26): SparkConnectClient._analyze has cyclomatic complexity 26 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1592}}}],"partialFingerprints":{"codehealthFindingId/v1":"01eb59e76da469cade838b0f2f40fa65132312e369e91654799316885b378172"}},{"ruleId":"D1","level":"warning","message":{"text":"NewHadoopRDD.compute (cyclomatic 25): NewHadoopRDD.compute has cyclomatic complexity 25 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d85129c75d0551bf9f9363fef9dcef17e3b429372439d3a199da42628928776"}},{"ruleId":"D1","level":"warning","message":{"text":"ExecutorPodsAllocator.onNewSnapshots (cyclomatic 25): ExecutorPodsAllocator.onNewSnapshots has cyclomatic complexity 25 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"c26d73d45d9902ca88596cc6d682db53af48c717d22c45cae67abb62d2757561"}},{"ruleId":"D1","level":"warning","message":{"text":"Client.prepareLocalResources (cyclomatic 25): Client.prepareLocalResources has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":527}}}],"partialFingerprints":{"codehealthFindingId/v1":"da15a51737c6a0f85aae3a324d560c5fc2244c61b04b0851ec2e1224f654e3da"}},{"ruleId":"D1","level":"warning","message":{"text":"MapObjects.doGenCode (cyclomatic 25): MapObjects.doGenCode has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":1089}}}],"partialFingerprints":{"codehealthFindingId/v1":"6169a84a00d9948bbc513d288f014620356b6ec24631fd80f5938675a519d700"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantExpressionEvalUtils.buildVariant (cyclomatic 25): VariantExpressionEvalUtils.buildVariant has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cb1a33b0f94f72c7af2160e777afa7e1f7614bea12ba5d206358e2fe36e6467"}},{"ruleId":"D1","level":"warning","message":{"text":"NullPropagation.apply (cyclomatic 25): NullPropagation.apply has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1163}}}],"partialFingerprints":{"codehealthFindingId/v1":"2586637ad229f8519e4e99bc3761b53f59aa94c654e573ca2d8f97aaee46db39"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.withJoinRelation (cyclomatic 25): AstBuilder.withJoinRelation has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2600}}}],"partialFingerprints":{"codehealthFindingId/v1":"527bee51ee0c1220c235ca8e0488c6931b3f3379f0c886cabca34f129bfe9eea"}},{"ruleId":"D1","level":"warning","message":{"text":"StringUtils.stripComment (cyclomatic 25): StringUtils.stripComment has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/StringUtils.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0c132af46ce873273cc07905d4d355b38d476471b4a8331afebdbfed6cf83aa"}},{"ruleId":"D1","level":"warning","message":{"text":"ToNumberParser.checkInputDataTypes (cyclomatic 25): ToNumberParser.checkInputDataTypes has cyclomatic complexity 25 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"818a628ad60c4277fb2c25c997432e993d594b29049b963443bb019509d82c3a"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.toAvroType (cyclomatic 25): SchemaConverters.toAvroType has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":402}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb16ef332697e24cc352e129f95fc5c189c6dec2410408aead2cd56fa2f76c69"}},{"ruleId":"D1","level":"warning","message":{"text":"JdbcUtils.makeSetter (cyclomatic 25): JdbcUtils.makeSetter has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: JdbcUtils.makeGetter (cyclomatic 28) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":507}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9205a94de4e40c38e03e89eae350fa2fdf23f41166cf8ce626a21360f504a14"}},{"ruleId":"D1","level":"warning","message":{"text":"V2ScanRelationPushDown.rewriteAggregate (cyclomatic 25): V2ScanRelationPushDown.rewriteAggregate has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":642}}}],"partialFingerprints":{"codehealthFindingId/v1":"f48abf98e22b662919f7ead7667e5f4d86f73439d2c24f851e7ece2dbedf7e44"}},{"ruleId":"D1","level":"warning","message":{"text":"NativePartitionReader.checkArrays (cyclomatic 25): NativePartitionReader.checkArrays has cyclomatic complexity 25 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"08238b2ac5cd827c9be2ae1b1fb346041ddd92245f24cb3ac7e06edd810f2bb5"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSQLCLIDriver.processCmd (cyclomatic 25): SparkSQLCLIDriver.processCmd has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala"},"region":{"startLine":442}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ecd06799dfbf4d23681eb7043b65d805cae5f223e72a78a60dbfd0c1f98e718"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskMemoryManager.allocatePageInternal (cyclomatic 25): TaskMemoryManager.allocatePageInternal has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":680}}}],"partialFingerprints":{"codehealthFindingId/v1":"dde00657a455f0b878984aea83f925d7bcb82fb8c91711cf526b2a7c7c9b72b7"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnarBatchRow.get (cyclomatic 25): ColumnarBatchRow.get has cyclomatic complexity 25 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bfa151bab1d3a7ce227217319448543484ab29ac898c005122c8b369a4c833d"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnVectorUtils.populate (cyclomatic 25): ColumnVectorUtils.populate has cyclomatic complexity 25 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"d38629ca30d42ce0416de79a22781235264f3da94630bf239c8ea2ee5f5670de"}},{"ruleId":"D1","level":"warning","message":{"text":"OperationState.validateTransition (cyclomatic 25): OperationState.validateTransition has cyclomatic complexity 25 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/OperationState.java"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"0bc3be1247902254eb9db172eede6f50308912de7aa536454e57ba245e0c58e8"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveFunctionRegistryUtils.getMethodInternal (cyclomatic 25): HiveFunctionRegistryUtils.getMethodInternal has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/HiveFunctionRegistryUtils.java"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b5a64f89bc02354343ef52cb0f0dbfdd3051c4373b5c6541218d702627d7346"}},{"ruleId":"D1","level":"warning","message":{"text":"merge_spark_pr.resolve_jira_issue (cyclomatic 25): merge_spark_pr.resolve_jira_issue has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":1880}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd54d5f1dbbad546a97b5e1c7769442d8b3c04ae9d144106dc96f026460927a2"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.reset_index (cyclomatic 25): DataFrame.reset_index has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4472}}}],"partialFingerprints":{"codehealthFindingId/v1":"72a81c27669798e77c6534679e911f5a0946b1079948fd9cafbec0017507e7a2"}},{"ruleId":"D1","level":"warning","message":{"text":"LocIndexer._select_cols_by_iterable (cyclomatic 25): LocIndexer._select_cols_by_iterable has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1346}}}],"partialFingerprints":{"codehealthFindingId/v1":"73c6de8d04ec61cfc670a2d85cdf4230f7ab591adfa60c73036080e999869d02"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSubmit.runMain (cyclomatic 24): SparkSubmit.runMain has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":971}}}],"partialFingerprints":{"codehealthFindingId/v1":"01003653de4aada22bc5a52310a6cafa5e9b4d1fbb764d940c5505be76d64efe"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSubmitArguments.validateSubmitArguments (cyclomatic 24): SparkSubmitArguments.validateSubmitArguments has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"a74a8977497f5c6b1b8241fb0a6c1018f364343d32cd704b1ef533f9d1bfdced"}},{"ruleId":"D1","level":"warning","message":{"text":"RowMatrix.computeSVD (cyclomatic 24): RowMatrix.computeSVD has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":341}}}],"partialFingerprints":{"codehealthFindingId/v1":"054dff814799ea73f8eee801df83741b2545cd485a56b384c9deeebad524cf24"}},{"ruleId":"D1","level":"warning","message":{"text":"ExtractGenerator.apply (cyclomatic 24): ExtractGenerator.apply has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":3445}}}],"partialFingerprints":{"codehealthFindingId/v1":"5785753da8b1bcee3f4a1391f42b27abecb52d6298c7648357fc3b76145224ea"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnResolutionHelper.resolveExpression (cyclomatic 24): ColumnResolutionHelper.resolveExpression has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ColumnResolutionHelper.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"9aab090762443fc7de5c58c9b3298b396374a09570cb203e867a7a6fb9000564"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveWithCTE.resolveWithCTE (cyclomatic 24): ResolveWithCTE.resolveWithCTE has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf3ebddc323015f8fa7369ca61fecebb644ec528c287896c58a46ab1592c4ab7"}},{"ruleId":"D1","level":"warning","message":{"text":"SelectedField.selectField (cyclomatic 24): SelectedField.selectField has cyclomatic complexity 24 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SelectedField.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"a29a6121b4e22443f05903c107273247a25149d0027970a7b0185ff79f1e1b70"}},{"ruleId":"D1","level":"warning","message":{"text":"JacksonParser.parseIterator (cyclomatic 24): JacksonParser.parseIterator has cyclomatic complexity 24 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":908}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c17cc66c52c36815cfaba15c06708ea6433a46ac28b425ebc6fe720d157f039"}},{"ruleId":"D1","level":"warning","message":{"text":"InjectRuntimeFilter.extractSelectiveFilterOverScan (cyclomatic 24): InjectRuntimeFilter.extractSelectiveFilterOverScan has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcef8eaf2aadbe2e39a93d18d05407b1f70fb6056733be2f03cb282851fa8c34"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveResult.toHiveStringDefault (cyclomatic 24): HiveResult.toHiveStringDefault has cyclomatic complexity 24 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cb7b8914588e230f089fc56944386a7aae763e1ccc15df7f1ca053efc99f2e8"}},{"ruleId":"D1","level":"warning","message":{"text":"JoinSelection.apply (cyclomatic 24): JoinSelection.apply has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"81637ec549641d9afb3172832d687ae03a860a7cafb5390bf040bf9a6971c808"}},{"ruleId":"D1","level":"warning","message":{"text":"InsertIntoHadoopFsRelationCommand.run (cyclomatic 24): InsertIntoHadoopFsRelationCommand.run has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f895dda4d59d2f46f5e55e1542d2c9ee69242bb8a651ceb4b06a760df3064c4"}},{"ruleId":"D1","level":"warning","message":{"text":"JdbcUtils.savePartition (cyclomatic 24): JdbcUtils.savePartition has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: JdbcUtils.makeGetter (cyclomatic 28) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":657}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceb30f0fc6db9fdf3883c0f163e8e67434474cd78737b4728eb0e8b3cdfa3930"}},{"ruleId":"D1","level":"warning","message":{"text":"OrcUtils.createAggInternalRowFromFooter (cyclomatic 24): OrcUtils.createAggInternalRowFromFooter has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"50d2e96591698c78bf338212a5c66657da3495bdae86cef79f9dfe14af93c686"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetFilters.valueMatchesParquetType (cyclomatic 24): ParquetFilters.valueMatchesParquetType has cyclomatic complexity 24 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":958}}}],"partialFingerprints":{"codehealthFindingId/v1":"de2abdcf8eb094225abd2236d7089e07b3c5dd6dae7e228d736bbd145b380c13"}},{"ruleId":"D1","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleStatefulProcessorCall (cyclomatic 24): TransformWithStateInPySparkStateServer.handleStatefulProcessorCall has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a45d75b69314987e4f13b30c5617cba3289c585697c39daa46a6a328f2be23b"}},{"ruleId":"D1","level":"warning","message":{"text":"StateStore.submitMaintenanceWorkForProvider (cyclomatic 24): StateStore.submitMaintenanceWorkForProvider has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala"},"region":{"startLine":2037}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee33341e9f8bb75b1d23c5112829e01d6b47ccef115d7b8bff44d2ab44a17120"}},{"ruleId":"D1","level":"warning","message":{"text":"SpecializedGettersReader.read (cyclomatic 24): SpecializedGettersReader.read has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/SpecializedGettersReader.java"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"6445e13addb22d7f521001d289b72fdcb5269cac342e36474f78280123e2ba81"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnarRow.get (cyclomatic 24): ColumnarRow.get has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"b639a3759d802e4df60fd406586dbbea00bd8fd9bb35173dd80559576020b1a2"}},{"ruleId":"D1","level":"warning","message":{"text":"MutableColumnarRow.copy (cyclomatic 24): MutableColumnarRow.copy has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"59942af47ec2150712daa155f79a211a4e91fd414a8007003fab7c6ffc90657c"}},{"ruleId":"D1","level":"warning","message":{"text":"api.create_auto_cdc_flow (cyclomatic 24): api.create_auto_cdc_flow has cyclomatic complexity 24 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"3178f937351d3c35ac78d31be0fa619cb066e1d0439f6712cff064d8a29627fe"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints.infer_pandas_eval_type (cyclomatic 24): typehints.infer_pandas_eval_type has cyclomatic complexity 24 (threshold 15). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a77a9c94600e04e26e8b8d4f4b9a4a3c896498c62148091127013d50b8b49e1"}},{"ruleId":"D1","level":"warning","message":{"text":"spark-sql-viz.document.addEventListener(\u0022DOMContentLoaded\u0022) (cyclomatic 24): spark-sql-viz.document.addEventListener(\u0022DOMContentLoaded\u0022) has cyclomatic complexity 24 (threshold 15). Most of this is not in the body itself: 7 of the 24 points are its own statements and the rest belongs to 4 function literals inside it that branch (lines 1118, 1139, 1142, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6623cc35b680d25f9c1f12d7647d96ca9ebfe18ebfdcd976f2a59d950f94fcb"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 24): (anonymous) has cyclomatic complexity 24 (threshold 15). Most of this is not in the body itself: 3 of the 24 points are its own statements and the rest belongs to 16 function items inside it that branch (a function literal at line 126, a function literal at line 291, (anonymous)::(anonymous)::render, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/historypage.js"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e4d5184454821c5400ffb8ee51b92647247e319d058c432ce8ac9a111e3f2c6"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 24): (anonymous) has cyclomatic complexity 24 (threshold 15). Most of this is not in the body itself: 7 of the 24 points are its own statements and the rest belongs to 7 function literals inside it that branch (lines 1118, 1139, 1142, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"67e0e8a8ed30a316039a4ce20bc1b2d7b16508f552fafd43cd029f6e319bb149"}},{"ruleId":"D1","level":"warning","message":{"text":"IndylambdaScalaClosures.findAccessedFields (cyclomatic 23): IndylambdaScalaClosures.findAccessedFields has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"53694ea3a1cf6f2d7ead0cf51769578e5a8595bb1f1c2f34f061127eebcccb2f"}},{"ruleId":"D1","level":"warning","message":{"text":"Writer.open (cyclomatic 23): Writer.open has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: PythonEvalType.toString (cyclomatic 39) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":966}}}],"partialFingerprints":{"codehealthFindingId/v1":"9574d2f61255a61bd5a0846fecc3630c49fd555d3d02f88b884c656a8f869806"}},{"ruleId":"D1","level":"warning","message":{"text":"JobPage.render (cyclomatic 23): JobPage.render has cyclomatic complexity 23 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbf7b8184b60b1abcbb8440225d6ea095bd2ca322a86b2dc955a5c56f9da99a4"}},{"ruleId":"D1","level":"warning","message":{"text":"SummarizerBuffer.merge (cyclomatic 23): SummarizerBuffer.merge has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":590}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1bceb8170729611245e1c5d60437708c170510f2df35c94a39ee0ae76b5772f"}},{"ruleId":"D1","level":"warning","message":{"text":"DeduplicateRelations.dedupRight (cyclomatic 23): DeduplicateRelations.dedupRight has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"83282c349e11983e9c213e28cfe149376b25dd3980396fdba29db6ec3a39b814"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveCatalogs.apply (cyclomatic 23): ResolveCatalogs.apply has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"7446d3d2a75b6a4b8e474915d47c9501d1bf2a6c40ad2eae23081597d1f710dc"}},{"ruleId":"D1","level":"warning","message":{"text":"UnwrapCastInBinaryComparison.unwrapCast (cyclomatic 23): UnwrapCastInBinaryComparison.unwrapCast has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7570eb5c018202bf4ac4ea44e1d98a128c020bd7a89ed10368267a8414d794d"}},{"ruleId":"D1","level":"warning","message":{"text":"RewritePredicateSubquery.apply (cyclomatic 23): RewritePredicateSubquery.apply has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c1f4e7b8f3b825ec920b3f12200e1297cabf2d5a28a881307dff74a89f2e5cb"}},{"ruleId":"D1","level":"warning","message":{"text":"ToNumberParser.parse (cyclomatic 23): ToNumberParser.parse has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9c0820c3a5aa8b30a8c6af7dd98c7fa1bb7956c2b9564b49cbdd14809d350d1"}},{"ruleId":"D1","level":"warning","message":{"text":"StaxXmlParser.convertTo (cyclomatic 23): StaxXmlParser.convertTo has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":791}}}],"partialFingerprints":{"codehealthFindingId/v1":"02814069cc186c9f8f1bd6542d705c1893d73250685672f2a365f603ff0d387d"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkConnectPlanner.transformReadRel (cyclomatic 23): SparkConnectPlanner.transformReadRel has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: SparkConnectPlanner.transformRelation (cyclomatic 66) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":1790}}}],"partialFingerprints":{"codehealthFindingId/v1":"531d148db0fdcdfcc281518b68f3ee34a24dc04936ab19932eda8d570a7c2be7"}},{"ruleId":"D1","level":"warning","message":{"text":"HashAggregateExec.doProduceWithKeys (cyclomatic 23): HashAggregateExec.doProduceWithKeys has cyclomatic complexity 23 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":574}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f00d91312bce36421b5a4ba6ea8f1b4cdb041773b598ba8c444ddd388717c0b"}},{"ruleId":"D1","level":"warning","message":{"text":"TableCapabilityCheck.apply (cyclomatic 23): TableCapabilityCheck.apply has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/TableCapabilityCheck.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"70562039819f24a6c71cf151dff12a7c434949edf9a482565e3f9c89e455c64c"}},{"ruleId":"D1","level":"warning","message":{"text":"SortMergeJoinExec.doProduce (cyclomatic 23): SortMergeJoinExec.doProduce has cyclomatic complexity 23 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":448}}}],"partialFingerprints":{"codehealthFindingId/v1":"cff61b0edc37267ce9075aa9aa1cbd02536e32dc243e1f430239f86ca0817724"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnVectorUtils.appendValue (cyclomatic 23): ColumnVectorUtils.appendValue has cyclomatic complexity 23 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e88330ebb2fb0241cf4f17aea2ea31ee4717182188dad7bdef9407eb649c132"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.filter (cyclomatic 23): DataFrame.filter has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11965}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c79edb9ecd92d952f3e642e80427a7e7dfd7dd8e216e963b72611bc220bce42"}},{"ruleId":"D1","level":"warning","message":{"text":"GroupBy.aggregate (cyclomatic 23): GroupBy.aggregate has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fdd47a53cd77452a756a2c1d0680cc2c4e7eee00f4ef96aed717435f593759f"}},{"ruleId":"D1","level":"warning","message":{"text":"iLocIndexer._select_rows_by_slice (cyclomatic 23): iLocIndexer._select_rows_by_slice has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1645}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8646cfc1d2a6cf7f5538c4d3c62d2352f581b8122cb6ecefc841ec2912b14c8"}},{"ruleId":"D1","level":"warning","message":{"text":"LocalDataToArrowConversion._create_converter (cyclomatic 23): LocalDataToArrowConversion._create_converter has cyclomatic complexity 23 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This shape REPEATS in the file: one other method here (LocalDataToArrowConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":664}}}],"partialFingerprints":{"codehealthFindingId/v1":"b500fed84e87d185b28b0b463272fe5383ee0f81cd7e441b3fdb5a14983cc97b"}},{"ruleId":"D1","level":"warning","message":{"text":"LocalDataToArrowConversion._create_converter (cyclomatic 23): LocalDataToArrowConversion._create_converter has cyclomatic complexity 23 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This shape REPEATS in the file: one other method here (LocalDataToArrowConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":674}}}],"partialFingerprints":{"codehealthFindingId/v1":"03c43726541825dae8b089a435f45de7f8b685ce8713b2cdf56004d3e72b8e1a"}},{"ruleId":"D1","level":"warning","message":{"text":"Builder.getOrCreate (cyclomatic 23): Builder.getOrCreate has cyclomatic complexity 23 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e549d8ebe77fea363df08cf4f343831c24acc83ca1c48bb4941ce464f184559"}},{"ruleId":"D1","level":"warning","message":{"text":"spark-sql-viz.updateDetailsPanel (cyclomatic 23): spark-sql-viz.updateDetailsPanel has cyclomatic complexity 23 (threshold 15). Of this number, 19 points are the body\u0027s own statements and 4 belong to 2 function literals inside it that branch. To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbf1fcb53516038383795083c1a40475e78db120cd43d533687192cc09e240e9"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkContext.addJar (cyclomatic 22): SparkContext.addJar has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2479}}}],"partialFingerprints":{"codehealthFindingId/v1":"15ac88e220d2c53e1d99f1ac762ee3721a69a18824cf6ef86e812c187a36926c"}},{"ruleId":"D1","level":"warning","message":{"text":"HadoopRDD.compute (cyclomatic 22): HadoopRDD.compute has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cb2289134f56c23a415ba6dc530a86a010616653ce4f4d0481a0ba073c354b7"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskSetManager.handleFailedTask (cyclomatic 22): TaskSetManager.handleFailedTask has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1001}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6c10d3abd4084ae76babc4349144538ce972851f08623c8271447f418ff0577"}},{"ruleId":"D1","level":"warning","message":{"text":"SummarizerBuffer.add (cyclomatic 22): SummarizerBuffer.add has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":499}}}],"partialFingerprints":{"codehealthFindingId/v1":"66e3a69471d407c4fb35e8a7bea3d9ec946e9880cb4c63964d9cff7f5a3ed642"}},{"ruleId":"D1","level":"warning","message":{"text":"Client.monitorApplication (cyclomatic 22): Client.monitorApplication has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1210}}}],"partialFingerprints":{"codehealthFindingId/v1":"917ad95ac127608e290247b09cd16747a572953ae48caae19feadd5bdb44f4b0"}},{"ruleId":"D1","level":"warning","message":{"text":"AlterTableValidation.validate (cyclomatic 22): AlterTableValidation.validate has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlterTableValidation.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"965437e3f13dd5149e720e7fd3e4542b60f91e7262de08e255fec2cc849440d6"}},{"ruleId":"D1","level":"warning","message":{"text":"RelationResolution.tryResolvePersistent (cyclomatic 22): RelationResolution.tryResolvePersistent has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa2111f2aab12ddfb9febf196b4c72e9f2a2a3c82ebd289e61fabb1af5b7d3a3"}},{"ruleId":"D1","level":"warning","message":{"text":"TypeCoercion.findCommonTypeForBinaryComparison (cyclomatic 22): TypeCoercion.findCommonTypeForBinaryComparison has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"7121e34399ba3ba21180796d90f40504b011aadb1ad3e60c6007afedd87849b8"}},{"ruleId":"D1","level":"warning","message":{"text":"Cast.castToByte (cyclomatic 22): Cast.castToByte has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: Cast.castInternal (cyclomatic 32) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1314}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d8d2b1abedef8a03e6d8560624c28dd5b0b04dd7715b2b87d3cacc6a6479bcf"}},{"ruleId":"D1","level":"warning","message":{"text":"ProjectionOverSchema.getProjection (cyclomatic 22): ProjectionOverSchema.getProjection has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ProjectionOverSchema.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7a3c9eed37111ace4ec2be429b7bd1482a42431652abd8f69750b2a8cc38e4d"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaOfVariant.schemaOf (cyclomatic 22): SchemaOfVariant.schemaOf has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":2249}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf6feac57addcba0ce451a780ec68ebee29f5dde56ada6104e49aeda33a0fd84"}},{"ruleId":"D1","level":"warning","message":{"text":"StaxXmlParser.convertObject (cyclomatic 22): StaxXmlParser.convertObject has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fac9bcfd2bbd2be625d132ade5af5e32b6e90f09bb609f4aa23cc7d7056c9ad"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkResult.processResponses (cyclomatic 22): SparkResult.processResponses has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkResult.scala"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"4194ca595301ae373b6bfe282323390e0a81957107e32d9029aa699b49c66916"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.toAvroTypeWithDefaults (cyclomatic 22): SchemaConverters.toAvroTypeWithDefaults has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":509}}}],"partialFingerprints":{"codehealthFindingId/v1":"36bac87039055c48a4b0a01d0fab965bc07e30083a651f3c7e522d2f989ea881"}},{"ruleId":"D1","level":"warning","message":{"text":"PushDownShuffleExchangeThroughUnion.apply (cyclomatic 22): PushDownShuffleExchangeThroughUnion.apply has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PushDownShuffleExchangeThroughUnion.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"b128e2843987ecce24291453a9b9d871323b87ddba81de7d70e92e18ef59e32d"}},{"ruleId":"D1","level":"warning","message":{"text":"BinaryFileFormat.createFilterFunction (cyclomatic 22): BinaryFileFormat.createFilterFunction has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/binaryfile/BinaryFileFormat.scala"},"region":{"startLine":207}}}],"partialFingerprints":{"codehealthFindingId/v1":"b452518d3665ef3650e035f7f4a40771c2928bbef518967437d152235ac01642"}},{"ruleId":"D1","level":"warning","message":{"text":"StreamingV2ScanPushDown.impliedBy (cyclomatic 22): StreamingV2ScanPushDown.impliedBy has cyclomatic complexity 22 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc3e865dba0c8782d10081feb13b9ba672433c15a20f5b0c36aa00471da25c25"}},{"ruleId":"D1","level":"warning","message":{"text":"DataflowGraphTransformer.transformDownNodes (cyclomatic 22): DataflowGraphTransformer.transformDownNodes has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/DataflowGraphTransformer.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb52a17c42ad2c11ab6f286bdbcaff346152fb56886ab996a08bf5e204e3d4d1"}},{"ruleId":"D1","level":"warning","message":{"text":"SortState.mergeHi (cyclomatic 22): SortState.mergeHi has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (SortState.mergeLo) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1a8a6c38eb1e6ddd06fcc468670f757f2858f94f737ac0a8f57bb1697104e80"}},{"ruleId":"D1","level":"warning","message":{"text":"SortState.mergeLo (cyclomatic 22): SortState.mergeLo has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (SortState.mergeHi) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":686}}}],"partialFingerprints":{"codehealthFindingId/v1":"c78235f86dce280935335abb0dd9e64cf614edec338d3171f3cd59a945ab02ee"}},{"ruleId":"D1","level":"warning","message":{"text":"functions._validate_vectorized_udf (cyclomatic 22): functions._validate_vectorized_udf has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/functions.py"},"region":{"startLine":882}}}],"partialFingerprints":{"codehealthFindingId/v1":"718528d2dfbd5c820e9fda87e23ccdff36443849949cbe0ce180064534fb3733"}},{"ruleId":"D1","level":"warning","message":{"text":"transpile._transpile_func (cyclomatic 22): transpile._transpile_func has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":1399}}}],"partialFingerprints":{"codehealthFindingId/v1":"e04bd057b66685293b89e3f878d55243a0028b953788cc40af0142ab6eda4f8f"}},{"ruleId":"D1","level":"warning","message":{"text":"types._merge_type (cyclomatic 22): types._merge_type has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":3297}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c778ebd72ef44af31d75329702f0b049c8bbd9bb01a6638c43a1aa761d7f4e5"}},{"ruleId":"D1","level":"warning","message":{"text":"analyze_udtf._main (cyclomatic 22): analyze_udtf._main has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/analyze_udtf.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"3606788fe9b5969ea62e4ce8c667e68151267d5967f1971e40c3a7c5929a80a1"}},{"ruleId":"D1","level":"warning","message":{"text":"sql-table-utils.getSqlTableColumns (cyclomatic 22): sql-table-utils.getSqlTableColumns has cyclomatic complexity 22 (threshold 15). Most of this is not in the body itself: 2 of the 22 points are its own statements and the rest belongs to 9 function literals inside it that branch (lines 263, 202, 254, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/sql-table-utils.js"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ce4e06ac8dbcb405f77b486fe719a7d5e6cb24fd975f7be51583066d17343e8"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkContext.addFile (cyclomatic 21): SparkContext.addFile has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1867}}}],"partialFingerprints":{"codehealthFindingId/v1":"80854d8db4ab0734735009c78c80bb547b959ec0f416a86e099784b391355075"}},{"ruleId":"D1","level":"warning","message":{"text":"GeneralizedLinearAlgorithm.run (cyclomatic 21): GeneralizedLinearAlgorithm.run has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c153b65e8c425af1d23081673ae6e68022c73f23353010b1a27f2e132488c30"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkDateTimeUtils.stringToDate (cyclomatic 21): SparkDateTimeUtils.stringToDate has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":577}}}],"partialFingerprints":{"codehealthFindingId/v1":"7be942cd5ab352dcd52343fac34c607395f68cf5513ad8660ac62353a0f5604c"}},{"ruleId":"D1","level":"warning","message":{"text":"Cast.castToShort (cyclomatic 21): Cast.castToShort has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: Cast.castInternal (cyclomatic 32) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1250}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1ae8f65f19c7cb0353b979ac111cd3614ec64e2f8a920231993b0c68e13d9d1"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.withSample (cyclomatic 21): AstBuilder.withSample has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2828}}}],"partialFingerprints":{"codehealthFindingId/v1":"97ab1706fd09adcb3e213410c74149deb4e5f35551d4ee58e2563bff308cfb2b"}},{"ruleId":"D1","level":"warning","message":{"text":"FilterEstimation.evaluateBinaryForNumeric (cyclomatic 21): FilterEstimation.evaluateBinaryForNumeric has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: FilterEstimation.calculateSingleCondition (cyclomatic 22) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":510}}}],"partialFingerprints":{"codehealthFindingId/v1":"3df0258795c247a7aef341fb5694ad04303d44ac6b02b44db40cf25c80072afa"}},{"ruleId":"D1","level":"warning","message":{"text":"DetectAmbiguousSelfJoin.apply (cyclomatic 21): DetectAmbiguousSelfJoin.apply has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/analysis/DetectAmbiguousSelfJoin.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d6db5610c7f636491cabc50da6958ec16437ed4fc043844a37c72246dea1cc2"}},{"ruleId":"D1","level":"warning","message":{"text":"ParquetReadSupport.findCheapestGroupField (cyclomatic 21): ParquetReadSupport.findCheapestGroupField has cyclomatic complexity 21 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadSupport.scala"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5ec1c3ede8c2957431e4e2ab02b1e1a6785b60cb22eaa55c1b42e3063642631"}},{"ruleId":"D1","level":"warning","message":{"text":"StreamExecution.runStream (cyclomatic 21): StreamExecution.runStream has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"73b3bf317d84a8eafd347c4a238c3a6bab250cb1701d5d6aa732879dac8db096"}},{"ruleId":"D1","level":"warning","message":{"text":"UTF8String.indexOf (cyclomatic 21): UTF8String.indexOf has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1320}}}],"partialFingerprints":{"codehealthFindingId/v1":"5476827becb42fe3d6566bfad934f590723cabb02125619cb8d9c82b892cb495"}},{"ruleId":"D1","level":"warning","message":{"text":"UTF8String.toInt (cyclomatic 21): UTF8String.toInt has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (UTF8String.toLong) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1922}}}],"partialFingerprints":{"codehealthFindingId/v1":"bad8b97e5cbd942c8bfd16259bab6e621cdbe63ffd0bb11d0d5980d491d70a0a"}},{"ruleId":"D1","level":"warning","message":{"text":"UTF8String.toLong (cyclomatic 21): UTF8String.toLong has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (UTF8String.toInt) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1825}}}],"partialFingerprints":{"codehealthFindingId/v1":"e18498be2ad9608bce330ba514108f12d4b2bdac71bcea0010d1711b1fe0f6e2"}},{"ruleId":"D1","level":"warning","message":{"text":"Variant.toJsonImpl (cyclomatic 21): Variant.toJsonImpl has cyclomatic complexity 21 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/Variant.java"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"61a4d8223d0b84cb9cb228202314e0f6dc89f0df392315097c415907db4f2e54"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantUtil.validateImpl (cyclomatic 21): VariantUtil.validateImpl has cyclomatic complexity 21 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: VariantUtil.getType (cyclomatic 22) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":633}}}],"partialFingerprints":{"codehealthFindingId/v1":"10a8f13bdd2f136751c46b122075a0afa898cade87589b73e2df3af92be5c5ed"}},{"ruleId":"D1","level":"warning","message":{"text":"AwsStsCredentialProvider.resolve (cyclomatic 21): AwsStsCredentialProvider.resolve has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/credential-aws/src/main/java/org/apache/spark/security/aws/AwsStsCredentialProvider.java"},"region":{"startLine":310}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc9f8a77aa3a836c71597ad0fc2320e2adfffff1f3a17c782f8785a32b960b1a"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.align (cyclomatic 21): DataFrame.align has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13800}}}],"partialFingerprints":{"codehealthFindingId/v1":"c677a698dc0602269e8f7530e66d73ece83e80f0ab48608bec1905bab3290a93"}},{"ruleId":"D1","level":"warning","message":{"text":"PandasOnSparkBoxPlot.boxplot (cyclomatic 21): PandasOnSparkBoxPlot.boxplot has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"81960307d4266ebdbcdbff77713ff6f6750bf45fa8913e3ee0a8bf3862f264f6"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints.spark_type_to_pandas_dtype (cyclomatic 21): typehints.spark_type_to_pandas_dtype has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"51a5ad3d29eeed61bd87011fdead4aafacf0e0429c7c1c9f1ad8a3616daf42e0"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.replace (cyclomatic 21): DataFrame.replace has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1550}}}],"partialFingerprints":{"codehealthFindingId/v1":"30665d89ec398f9092a93c46e4db7e539177331a089a92fed33fdeaaa1ac9d6c"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.replace (cyclomatic 21): DataFrame.replace has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1516}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3a3f236a3ecdd6fde44222e0b31baff9eb84dc8973a8ecc17ed9b30a395e557"}},{"ruleId":"D1","level":"warning","message":{"text":"ServerPool._reap_retired (cyclomatic 21): ServerPool._reap_retired has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/local_server_pool.py"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ac13bea7a354cab7d026b0b38ac81885da0ccd52572eeb80450ac373e837d57"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints.infer_arrow_eval_type (cyclomatic 21): typehints.infer_arrow_eval_type has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b617ed4f7829ced0c4a3243a8361a803070df94e0e675e43f55d81d6691fabb"}},{"ruleId":"D1","level":"warning","message":{"text":"types._check_arrow_array_timestamps_localize (cyclomatic 21): types._check_arrow_array_timestamps_localize has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aa9ad09223e1d7a4474432c298848b933fecfc89e8accdacfaba790a6cac02c"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSession.createDataFrame (cyclomatic 21): SparkSession.createDataFrame has cyclomatic complexity 21 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1428}}}],"partialFingerprints":{"codehealthFindingId/v1":"93388fb14bf089e6264dfc49e4e2f3f78851178d620375d53f32ac229faa1308"}},{"ruleId":"D1","level":"warning","message":{"text":"spark-sql-viz.setupPlanVizSearch (cyclomatic 21): spark-sql-viz.setupPlanVizSearch has cyclomatic complexity 21 (threshold 15). Most of this is not in the body itself: 7 of the 21 points are its own statements and the rest belongs to 3 function literals inside it that branch (lines 888, 875, 868). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":850}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4e7b2f173be28317d3922e55239dbfff85213812536d611d06685c6a9382d17"}},{"ruleId":"D1","level":"warning","message":{"text":"spark-sql-viz.runPlanVizSearch (cyclomatic 21): spark-sql-viz.runPlanVizSearch has cyclomatic complexity 21 (threshold 15). Most of this is not in the body itself: 6 of the 21 points are its own statements and the rest belongs to 2 function literals inside it that branch (lines 951, 980). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ef7e398225620589eb09c9e9ff4e4ee79e3ecf6c233afd1949439817cdab04e"}},{"ruleId":"D1","level":"warning","message":{"text":"ShuffleMigrationRunnable.run (cyclomatic 20): ShuffleMigrationRunnable.run has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerDecommissioner.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8a2b83a807713dd97481d4bcd0abf02f776886a9ff34f05c968ff6f1388b288"}},{"ruleId":"D1","level":"warning","message":{"text":"Client.createContainerLaunchContext (cyclomatic 20): Client.createContainerLaunchContext has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1033}}}],"partialFingerprints":{"codehealthFindingId/v1":"c712a7d1582aa9e80eb1e3968e38ad3f3410185bf1a5662ec051e86f7cafd1c7"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowUtils.fromArrowField (cyclomatic 20): ArrowUtils.fromArrowField has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: ArrowUtils.fromArrowTypeDefault (cyclomatic 27) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9ce23fbbd01a3a8e6d78e29791fe0dc578616d34df6cf5775798b053a6e2fb9"}},{"ruleId":"D1","level":"warning","message":{"text":"InternalRow.getAccessor (cyclomatic 20): InternalRow.getAccessor has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/InternalRow.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"07121699c9b29aba57083b7928e900db9ac5cbd45fd524c8acca6059f6680dca"}},{"ruleId":"D1","level":"warning","message":{"text":"StreamingJoinHelper.collectTerms (cyclomatic 20): StreamingJoinHelper.collectTerms has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/StreamingJoinHelper.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"bea4d7084295bfe0f5376039ab3627bb7841eb2e9dfe6524bcaabcaa8ca26f98"}},{"ruleId":"D1","level":"warning","message":{"text":"InjectRuntimeFilter.tryInjectRuntimeFilter (cyclomatic 20): InjectRuntimeFilter.tryInjectRuntimeFilter has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"676bcd9f85740100c50eda5242371314f858ab570b96857867a569b23d869e84"}},{"ruleId":"D1","level":"warning","message":{"text":"PushdownPredicatesAndPruneColumnsForCTEDef.removePushedDownFilter (cyclomatic 20): PushdownPredicatesAndPruneColumnsForCTEDef.removePushedDownFilter has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushdownPredicatesAndPruneColumnsForCTEDef.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"63874273894e86e4f7bdbca6765a2d512d879d70cf6e4d56c033d38c81cb61a4"}},{"ruleId":"D1","level":"warning","message":{"text":"RewriteDistinctAggregates.rewrite (cyclomatic 20): RewriteDistinctAggregates.rewrite has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddd111ee59922f39b802b57ef7df1aeb048cd55824182c04c2f31904055b8aa4"}},{"ruleId":"D1","level":"warning","message":{"text":"JoinSelectionHelper.getNonEquiJoinBuildSide (cyclomatic 20): JoinSelectionHelper.getNonEquiJoinBuildSide has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"d80a2312c1bd38a5ca6b46cf0241b6691c2c34ccc2425ada20fb6e41740a81bd"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.withQueryResultClauses (cyclomatic 20): AstBuilder.withQueryResultClauses has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1636}}}],"partialFingerprints":{"codehealthFindingId/v1":"c05b5fd1c26a1a5287c5b99edbc8b74f162916c3963bb7a3b136f3b8d92694a1"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.visitTypeConstructor (cyclomatic 20): AstBuilder.visitTypeConstructor has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":4851}}}],"partialFingerprints":{"codehealthFindingId/v1":"f48bdd21834d9e2485e253c95d3e64303dadd9d6aadae519a1477a64c2b31974"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.visitOperatorPipeAggregate (cyclomatic 20): AstBuilder.visitOperatorPipeAggregate has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":8495}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1b73de50a12da50ea5ad1840206040240602676fb5f795ca3aa70cac32a8e55"}},{"ruleId":"D1","level":"warning","message":{"text":"StaxXmlGenerator.writeVariantPrimitive (cyclomatic 20): StaxXmlGenerator.writeVariantPrimitive has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: StaxXmlGenerator.writeElement (cyclomatic 28) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlGenerator.scala"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c4a9c9745019b9bfdb05cda8e65cca65ecea8e481de2f3e44772bf61a03d5f1"}},{"ruleId":"D1","level":"warning","message":{"text":"PipelinesHandler.buildAutoCdcFlow (cyclomatic 20): PipelinesHandler.buildAutoCdcFlow has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala"},"region":{"startLine":440}}}],"partialFingerprints":{"codehealthFindingId/v1":"b566e82ddac2793b9824c5c94cf660c71326f2632b0e73a7c97ddd913af2db5b"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkConnectPlanner.handleWriteStreamOperationStart (cyclomatic 20): SparkConnectPlanner.handleWriteStreamOperationStart has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: SparkConnectPlanner.transformRelation (cyclomatic 66) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":3704}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f4cb1137882913358991b72e390b6fea1f04c6dbc93971e1f6654e87f5cdce9"}},{"ruleId":"D1","level":"warning","message":{"text":"AdaptiveSparkPlanExec.withFinalPlanUpdate (cyclomatic 20): AdaptiveSparkPlanExec.withFinalPlanUpdate has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe85eecaa3db907b3f3f4c0e706bc04473273f14e0c8df977965114bbd6df586"}},{"ruleId":"D1","level":"warning","message":{"text":"PreprocessTableInsertion.preprocess (cyclomatic 20): PreprocessTableInsertion.preprocess has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca0b93afd53c87587b9fa8e4af87ed1cf39d352d00880846456b0a335afedece"}},{"ruleId":"D1","level":"warning","message":{"text":"V2ScanRelationPushDown.pushVariantExtractions (cyclomatic 20): V2ScanRelationPushDown.pushVariantExtractions has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":451}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c7ff3d91fe685c06ee93d2feef4ae53d6ce510d4dfc88395b5efbd56f1782b1"}},{"ruleId":"D1","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleMapStateRequest (cyclomatic 20): TransformWithStateInPySparkStateServer.handleMapStateRequest has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":595}}}],"partialFingerprints":{"codehealthFindingId/v1":"d987edd553f134c4105a127b3ed95701d91cbf8b26761e6495efce90577064f4"}},{"ruleId":"D1","level":"warning","message":{"text":"StreamingSymmetricHashJoinExec.processPartitions (cyclomatic 20): StreamingSymmetricHashJoinExec.processPartitions has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"7696d6580955c8ed8a4e416b326ff8357eba7ae420ade012f80b41daede4fd2e"}},{"ruleId":"D1","level":"warning","message":{"text":"HadoopTableReader.fillObject (cyclomatic 20): HadoopTableReader.fillObject has cyclomatic complexity 20 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala"},"region":{"startLine":444}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ee945b1d823db05b573e75cb1c089a95804a07ec5c744faf71bb42b87cc5ad4"}},{"ruleId":"D1","level":"warning","message":{"text":"TransportResponseHandler.handle (cyclomatic 20): TransportResponseHandler.handle has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportResponseHandler.java"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1398f22455fbb25cfedf255903004e7344be50a11560e1a6f0d2b98babfe2cd"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantBuilder.appendWithInsertionImpl (cyclomatic 20): VariantBuilder.appendWithInsertionImpl has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":627}}}],"partialFingerprints":{"codehealthFindingId/v1":"721622226382c97cc0524613116d918b46c7797af029796a70743178ecca06bb"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantBuilder.appendWithSetImpl (cyclomatic 20): VariantBuilder.appendWithSetImpl has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":730}}}],"partialFingerprints":{"codehealthFindingId/v1":"bddca8bf2c40b20c5edf92b6891b705c1175b497bdb76f42a4a48a8d4cbb7b29"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnarBatchRow.copy (cyclomatic 20): ColumnarBatchRow.copy has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8a84b1214c8ad4d94cb5fa74cbb6d614631b9e1ade456c71ec0ab326ef8b892"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnarRow.copy (cyclomatic 20): ColumnarRow.copy has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"2269b964f07ac4a9759bfa88644aa50e1a1105670f180f69d998b5e151e8e04c"}},{"ruleId":"D1","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.evaluateStorageFilter (cyclomatic 20): LateMaterializationParquetRecordReader.evaluateStorageFilter has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":708}}}],"partialFingerprints":{"codehealthFindingId/v1":"b60f802e98aaac321e6f21c16368491637d57a7c9248678edd26c918ad1fd418"}},{"ruleId":"D1","level":"warning","message":{"text":"VectorizedRleValuesReader.readBatchRepeatedInternal (cyclomatic 20): VectorizedRleValuesReader.readBatchRepeatedInternal has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"c16e8db8cb912af85d729e46a912c613789156b36656e5728c630d1eb2cafa21"}},{"ruleId":"D1","level":"warning","message":{"text":"MutableColumnarRow.get (cyclomatic 20): MutableColumnarRow.get has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"19b27466b618fceb58117c34d5d3a0634e4b34891682444808f6c2f17c040620"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.select_dtypes (cyclomatic 20): DataFrame.select_dtypes has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7453}}}],"partialFingerprints":{"codehealthFindingId/v1":"df3937449bf705bc8e6c392dffbdb669d6fea5588f79e447d94a617c301bd6df"}},{"ruleId":"D1","level":"warning","message":{"text":"Frame.groupby (cyclomatic 20): Frame.groupby has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2395}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5feff07ea09f0737b7643016f437c198a959699b318e19dae404e1289a1bf97"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints.infer_return_type (cyclomatic 20): typehints.infer_return_type has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d0eee2b6cb13a4ee3f31f644d6c6d9d753a42b1bc537d02e255d6af36663e14"}},{"ruleId":"D1","level":"warning","message":{"text":"LiteralExpression._infer_type (cyclomatic 20): LiteralExpression._infer_type has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":321}}}],"partialFingerprints":{"codehealthFindingId/v1":"254475cb33f86d73d7c3d23f5acdd106483f6e045e1c22c8141a5704d195b2b9"}},{"ruleId":"D1","level":"warning","message":{"text":"BasePythonRunner.compute (cyclomatic 19): BasePythonRunner.compute has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This is NOT this file\u0027s highest cyclomatic complexity: PythonEvalType.toString (cyclomatic 39) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":690}}}],"partialFingerprints":{"codehealthFindingId/v1":"79e9d232b65c47c13a753a5c252a94dd1933b1249425f3b86d7041b069313cca"}},{"ruleId":"D1","level":"warning","message":{"text":"RBackendHandler.findMatchedSignature (cyclomatic 19): RBackendHandler.findMatchedSignature has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef3f480c36b35ac410c01b8c81d74ff71457a2e363721844aaa401b1447710ff"}},{"ruleId":"D1","level":"warning","message":{"text":"FsHistoryProvider.doMergeApplicationListingInternal (cyclomatic 19): FsHistoryProvider.doMergeApplicationListingInternal has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":1056}}}],"partialFingerprints":{"codehealthFindingId/v1":"283725eb1be4d685dee431d90ea21bd87dd1c2f9d483e9d310857c0b56ddf0e3"}},{"ruleId":"D1","level":"warning","message":{"text":"PipedRDD.compute (cyclomatic 19): PipedRDD.compute has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PipedRDD.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"5632cc4b02de2ba04c5e565b616fd49c4734cd376431a6d7d44b9941e7baed20"}},{"ruleId":"D1","level":"warning","message":{"text":"DAGScheduler.handleJobSubmitted (cyclomatic 19): DAGScheduler.handleJobSubmitted has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This is NOT this file\u0027s highest cyclomatic complexity: DAGSchedulerEventProcessLoop.doOnReceive (cyclomatic 27) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2619}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeff5a511a37ae629b3be75e9e771a27e165db3649472d32e1f46b1e4a74285d"}},{"ruleId":"D1","level":"warning","message":{"text":"BlockStoreUpdater.save (cyclomatic 19): BlockStoreUpdater.save has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":536}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9c31403caaaac9b02cc200237f0b3f873aff87428b96de604be185999dfa3d7"}},{"ruleId":"D1","level":"warning","message":{"text":"AllJobsPage.render (cyclomatic 19): AllJobsPage.render has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a420377366f935ab2ea3f75e0fe5a91e1d49bd603897b719b2e0d082c8d3645"}},{"ruleId":"D1","level":"warning","message":{"text":"KMeans.trainWithBlock (cyclomatic 19): KMeans.trainWithBlock has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala"},"region":{"startLine":526}}}],"partialFingerprints":{"codehealthFindingId/v1":"720fee9ed825ecaeecba5252dc8ca885b14b140861c146bf85316914ba061aac"}},{"ruleId":"D1","level":"warning","message":{"text":"MultinomialLogisticBlockAggregator.add (cyclomatic 19): MultinomialLogisticBlockAggregator.add has cyclomatic complexity 19 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/MultinomialLogisticBlockAggregator.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8831c2b1193f2fb1719aed220afba3c765bd778ef9d6593351b2fb31ef87bea"}},{"ruleId":"D1","level":"warning","message":{"text":"DecisionTreeMetadata.buildMetadata (cyclomatic 19): DecisionTreeMetadata.buildMetadata has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"afcc0d37dd933924582b1be31e6b2673ff47d338bcae577dc081faeca4bd741c"}},{"ruleId":"D1","level":"warning","message":{"text":"Row.equals (cyclomatic 19): Row.equals has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: Row.jsonValue (cyclomatic 28) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"8912615118b137d320f410aa158c12cbbfbadd0df1918b72a7479f9b514f8c79"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkDateTimeUtils.stringToTime (cyclomatic 19): SparkDateTimeUtils.stringToTime has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1098}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d3fa9c10d3ce5d2debe510a6df9f9ecae2502e69fa5a1a844c9705651389cfc"}},{"ruleId":"D1","level":"warning","message":{"text":"BinByResolution.validateAndComputeParameters (cyclomatic 19): BinByResolution.validateAndComputeParameters has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BinByResolution.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"38b6a1d16fdf95ca8d886781f7cd5c566834e6cfff5b0000a1f77b8ea0961072"}},{"ruleId":"D1","level":"warning","message":{"text":"DeduplicateRelations.apply (cyclomatic 19): DeduplicateRelations.apply has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e06cab01783f38b83ced87c23827476afee8db4c2450210aec9baeb3ec97f00"}},{"ruleId":"D1","level":"warning","message":{"text":"TableOutputResolver.resolveColumnsByPosition (cyclomatic 19): TableOutputResolver.resolveColumnsByPosition has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb7bf33e6ad55627ffed0beb2856a852ac2a4e19a0ec350b8fe159f5d692d63d"}},{"ruleId":"D1","level":"warning","message":{"text":"Cast.castToTimestamp (cyclomatic 19): Cast.castToTimestamp has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: Cast.castInternal (cyclomatic 32) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"a46560b672514c9775c5aeecaa41d49d999e840535ea20a471134b32bd95bb36"}},{"ruleId":"D1","level":"warning","message":{"text":"Literal.valueSizeInBytes (cyclomatic 19): Literal.valueSizeInBytes has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: Literal.componentTypeToDataType (cyclomatic 34) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"da69b3b4db27c90d0d81ac4d9e98df794f15ba6444befe7bd81d559fcec02d28"}},{"ruleId":"D1","level":"warning","message":{"text":"PullupCorrelatedPredicates.rewriteSubQueries (cyclomatic 19): PullupCorrelatedPredicates.rewriteSubQueries has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":570}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1aaded56e9db80f537181d3df5fe7cc7c832f47755329ff66ebbd448459fd3b"}},{"ruleId":"D1","level":"warning","message":{"text":"AstBuilder.visitMergeIntoTable (cyclomatic 19): AstBuilder.visitMergeIntoTable has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1274}}}],"partialFingerprints":{"codehealthFindingId/v1":"54010475c0f2eb3e890865c3568e1dc9e6cee6c8d009ea4fa29e818a815c4806"}},{"ruleId":"D1","level":"warning","message":{"text":"ExtractEquiJoinKeys.unapply (cyclomatic 19): ExtractEquiJoinKeys.unapply has cyclomatic complexity 19 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc2d81968d51b86d01cba8431a6f7482a630910d4630aeafc4741540016b263a"}},{"ruleId":"D1","level":"warning","message":{"text":"NormalizePlan.normalizeRecursive (cyclomatic 19): NormalizePlan.normalizeRecursive has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/NormalizePlan.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc7bba05962912c724bad5402b4b1e176111202c26c600703d199fb1e6f2c8f8"}},{"ruleId":"D1","level":"warning","message":{"text":"ToNumberParser.format (cyclomatic 19): ToNumberParser.format has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":649}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f68c168fe4f6b28f32f6a99872d20c88780c9b2c3ed4ee71493c4c90ae31ae6"}},{"ruleId":"D1","level":"warning","message":{"text":"XmlInferSchema.compatibleType (cyclomatic 19): XmlInferSchema.compatibleType has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":867}}}],"partialFingerprints":{"codehealthFindingId/v1":"405f5587ad4d169863cbf0265f28bcb8825c92422fd79550bf88ac2e8ecf0e07"}},{"ruleId":"D1","level":"warning","message":{"text":"LiteralValueProtoConverter.toLiteralProtoWithTypeDefault (cyclomatic 19): LiteralValueProtoConverter.toLiteralProtoWithTypeDefault has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: LiteralValueProtoConverter.toDataType (cyclomatic 34) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/LiteralValueProtoConverter.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c225782094ffa931f7de2ef91841b6ac21d595b1045a76e784a5e3fc7a9262d"}},{"ruleId":"D1","level":"warning","message":{"text":"ExecuteGrpcResponseSender.execute (cyclomatic 19): ExecuteGrpcResponseSender.execute has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/execution/ExecuteGrpcResponseSender.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"94a4316bb0cca9b77322c56722f6c9d21dbea98958a872ba6579fa5ed0a07625"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrameWriter.saveCommand (cyclomatic 19): DataFrameWriter.saveCommand has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"f73a9805db9514669c1eced236faf1af287a79101d4ef1165fd6f9ff9138d0d7"}},{"ruleId":"D1","level":"warning","message":{"text":"OrcUtils.requestedColumnIds (cyclomatic 19): OrcUtils.requestedColumnIds has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ae606fce8c22a6a4e66ff3dd608042452e3a00a38db553751ad0d83c6d9a8ea"}},{"ruleId":"D1","level":"warning","message":{"text":"UserDefinedPythonFunction.builder (cyclomatic 19): UserDefinedPythonFunction.builder has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0891e4ddf7fec9a759879beb1ba0031df8f6f3d42ea2273ed4bfd1d91b14cde"}},{"ruleId":"D1","level":"warning","message":{"text":"OneSideHashJoiner.storeAndJoinWithOtherSide (cyclomatic 19): OneSideHashJoiner.storeAndJoinWithOtherSide has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":783}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f6b2ffcdb820da2e9858e9d6a7a1bd3695bafe50939624c5c6816dcca74b029"}},{"ruleId":"D1","level":"warning","message":{"text":"FileStreamSource.fetchMaxOffset (cyclomatic 19): FileStreamSource.fetchMaxOffset has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/FileStreamSource.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"035ca36d8b4ac7b6616e1e0a014c46398ccbd018a7e1a5f1010aecbac92c69e1"}},{"ruleId":"D1","level":"warning","message":{"text":"SqlGraphRegistrationContext.buildChangeArgs (cyclomatic 19): SqlGraphRegistrationContext.buildChangeArgs has cyclomatic complexity 19 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea363073fc3ba823986bc9219d09172238c73d2a52a3fa6d8c1cfa87f72c635f"}},{"ruleId":"D1","level":"warning","message":{"text":"RDD.histogram (cyclomatic 19): RDD.histogram has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":2210}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b5684d84ae0281f8610109c80f813502e4da5b00a470a932b8779e2e2fa7d57"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.rename (cyclomatic 19): DataFrame.rename has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12140}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3bd84a6deb033df3de19631002cbff4f8189b1e2e0322cb12ec620102e9937e"}},{"ruleId":"D1","level":"warning","message":{"text":"Index.difference (cyclomatic 19): Index.difference has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2031}}}],"partialFingerprints":{"codehealthFindingId/v1":"d03fca45f3780b58e0d463a4ea72b22012832ef558a28174451e66ec2ffa955a"}},{"ruleId":"D1","level":"warning","message":{"text":"LocIndexer._get_from_multiindex_column (cyclomatic 19): LocIndexer._get_from_multiindex_column has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1246}}}],"partialFingerprints":{"codehealthFindingId/v1":"169c539a9384c496dd972ba6adf071ac909082bea1e3efae435ba4afbeaa9886"}},{"ruleId":"D1","level":"warning","message":{"text":"Series._interpolate (cyclomatic 19): Series._interpolate has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2327}}}],"partialFingerprints":{"codehealthFindingId/v1":"77d831e926aab9a3ef58c119bfc5b851138ca764073da11a4d08017d1a076e3a"}},{"ruleId":"D1","level":"warning","message":{"text":"ArtifactManager._parse_artifacts (cyclomatic 19): ArtifactManager._parse_artifacts has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0a3096965f1b5a355f72a68b7a7656ee7be51deee5440d69fd05c7bb40a695d"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowTableToRowsConversion._to_pylist (cyclomatic 19): ArrowTableToRowsConversion._to_pylist has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1141}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c44e98d70eed7b7106c55fe772c90580b73d399e48eebc4a36422a2894933e0"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowTableToRowsConversion._create_converter (cyclomatic 19): ArrowTableToRowsConversion._create_converter has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This shape REPEATS in the file: one other method here (ArrowTableToRowsConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1290}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8a59fc41d77838337738c420eb2654531b6fc14af1ae67b7b8b8d5f62abaa2d"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowTableToRowsConversion._create_converter (cyclomatic 19): ArrowTableToRowsConversion._create_converter has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages. This shape REPEATS in the file: one other method here (ArrowTableToRowsConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1296}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddf24304048e0642deaf46c9fc963b0616673fc73707dfa9bb6e8c4c181c0230"}},{"ruleId":"D1","level":"warning","message":{"text":"(anonymous) (cyclomatic 19): (anonymous) has cyclomatic complexity 19 (threshold 15). Most of this is not in the body itself: 3 of the 19 points are its own statements and the rest belongs to 10 function items inside it that branch (a function literal at line 164, (anonymous)::(anonymous)::createdRow, a function literal at line 186, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/environmentpage.js"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"df7b61dfefed00c9eda8cb23f43cb00e703ff3818855d9425658390b7f83ce8f"}},{"ruleId":"D1","level":"warning","message":{"text":"KinesisUtilsPythonHelper.createStream (cyclomatic 18): KinesisUtilsPythonHelper.createStream has cyclomatic complexity 18 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtilsPythonHelper.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fe9eba78c672d3786dd08150f5cc13e2b6efb11cbae00d9c86980faebba2ab9"}},{"ruleId":"D1","level":"warning","message":{"text":"ExecutorAllocationManager.validateSettings (cyclomatic 18): ExecutorAllocationManager.validateSettings has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"08b1e2a1742eeda3ad19d69a4f948f57c1d51312bcb176e65b5e93921dcc1726"}},{"ruleId":"D1","level":"warning","message":{"text":"FsHistoryProvider.checkForLogsInDir (cyclomatic 18): FsHistoryProvider.checkForLogsInDir has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":635}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c0bb59188c4d46e45f502aa65a93db49749b3b805ae66fbf24f909836a2bf72"}},{"ruleId":"D1","level":"warning","message":{"text":"Inbox.process (cyclomatic 18): Inbox.process has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/netty/Inbox.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"82db82df7d3e0e2459a53de888aaa0b26951544fa16f3b61a01f2a6bb850dfb1"}},{"ruleId":"D1","level":"warning","message":{"text":"DriverEndpoint.receive (cyclomatic 18): DriverEndpoint.receive has cyclomatic complexity 18 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"0feccda003df7aa54acd7a75e5ad684c336f5bad33f3e13c3ee1a8a031f4f6e9"}},{"ruleId":"D1","level":"warning","message":{"text":"DriverEndpoint.receiveAndReply (cyclomatic 18): DriverEndpoint.receiveAndReply has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"acaeb1b3edecd736d6364b34c964207497b4af010054720a4b366b6f0bdcea66"}},{"ruleId":"D1","level":"warning","message":{"text":"EdgePartition.aggregateMessagesIndexScan (cyclomatic 18): EdgePartition.aggregateMessagesIndexScan has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"3632a2795bba36fda39de6dee8abf845a6a138e12d96d936694e38bcb78fc93a"}},{"ruleId":"D1","level":"warning","message":{"text":"VectorIndexerModel.getTransformFunc (cyclomatic 18): VectorIndexerModel.getTransformFunc has cyclomatic complexity 18 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"917808fb7d95ce307ec99a3d3cf33e9dcfad1cf2c2998b20f83adad7405edada"}},{"ruleId":"D1","level":"warning","message":{"text":"BasicExecutorFeatureStep.configurePod (cyclomatic 18): BasicExecutorFeatureStep.configurePod has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3fac11dc5dff5aebb5d35a1d8fe8a03ee2da45bdbb863ddf8ffe6bcb62e2431"}},{"ruleId":"D1","level":"warning","message":{"text":"YarnAllocator.processCompletedContainers (cyclomatic 18): YarnAllocator.processCompletedContainers has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"d454841ea35025550aebdbe962e62e4d27f1283eda1e13c65188d057d33ac84f"}},{"ruleId":"D1","level":"warning","message":{"text":"DeduplicateRelations.deduplicate (cyclomatic 18): DeduplicateRelations.deduplicate has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: DeduplicateRelations.renewDuplicatedRelations (cyclomatic 19) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e211c0a37266cd579f22dd5c24f731aedd0504f7594473efa11d75b2633f65c"}},{"ruleId":"D1","level":"warning","message":{"text":"JdkCodeCompiler.narrowingVerdict (cyclomatic 18): JdkCodeCompiler.narrowingVerdict has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1225}}}],"partialFingerprints":{"codehealthFindingId/v1":"71af102a876ddd973a1a2ba329ac15821e6e9cd9330a36760a29916a682af2ab"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveHashFunction.hash (cyclomatic 18): HiveHashFunction.hash has cyclomatic complexity 18 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: HashExpression.computeHashWithTailRec (cyclomatic 19) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":1308}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a2f9bf95b24a594bdcf694a6c9fd8c9856f84ced1f8683d55c9abb97d6ab1a3"}},{"ruleId":"D1","level":"warning","message":{"text":"StarSchemaDetection.findStarJoins (cyclomatic 18): StarSchemaDetection.findStarJoins has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/StarSchemaDetection.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4ea969d53842487335c3505300c8439cd71bff5791e2ed13818a68972de04b3"}},{"ruleId":"D1","level":"warning","message":{"text":"SimplifyBinaryComparison.apply (cyclomatic 18): SimplifyBinaryComparison.apply has cyclomatic complexity 18 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":760}}}],"partialFingerprints":{"codehealthFindingId/v1":"9230c16cb483f8b9c4279c3d0e3389092826e84172cb1d5ed0b393a03f8568dc"}},{"ruleId":"D1","level":"warning","message":{"text":"JoinEstimation.estimateInnerOuterJoin (cyclomatic 18): JoinEstimation.estimateInnerOuterJoin has cyclomatic complexity 18 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"959a0a54eae695dfbb149128dff9e59cf41e7ebc8270861763a8ed6d120670b8"}},{"ruleId":"D1","level":"warning","message":{"text":"GenericArrayData.equals (cyclomatic 18): GenericArrayData.equals has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"db76f21f802af9a43c26ba4352889dc201c86d6379e547a25bf6096003340f12"}},{"ruleId":"D1","level":"warning","message":{"text":"XmlTokenizer.readUntilEndElement (cyclomatic 18): XmlTokenizer.readUntilEndElement has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: StaxXmlParser.castTo (cyclomatic 19) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1067}}}],"partialFingerprints":{"codehealthFindingId/v1":"9016e615ec0eda03a3fefdf9b6aed2ab00ab2838f9cd98fe3cfdeb29dc025ad7"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaUtils.validateTypeCompatibility (cyclomatic 18): SchemaUtils.validateTypeCompatibility has cyclomatic complexity 18 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8fb19cca792914a1bd771c2e011aed42ded18e196e7240005ea14a085050784"}},{"ruleId":"D1","level":"warning","message":{"text":"UnionLoopExec.doExecute (cyclomatic 18): UnionLoopExec.doExecute has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/UnionLoopExec.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6738b116b6a216ebe4be2f5e56e69266f0c429421b7c2ef55c0266407706cfb"}},{"ruleId":"D1","level":"warning","message":{"text":"HashAggregateExec.doConsumeWithKeys (cyclomatic 18): HashAggregateExec.doConsumeWithKeys has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":966}}}],"partialFingerprints":{"codehealthFindingId/v1":"f57468a65ec43f9fd2594990a70f47171568a66805d038b76ac74e836a6a8d09"}},{"ruleId":"D1","level":"warning","message":{"text":"OrcUtils.orcTypeDescription (cyclomatic 18): OrcUtils.orcTypeDescription has cyclomatic complexity 18 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":456}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4dbd6ad2d0b5843fc8a6212645ad21a9da446bd25a61789474012ccb93d2179"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkShreddingUtils.extractField (cyclomatic 18): SparkShreddingUtils.extractField has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":788}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed9c99dea4bdf17740f36f5681b6b8b41287626d979c7afbaf7b37d557cbb5b0"}},{"ruleId":"D1","level":"warning","message":{"text":"XSDToSchema.getStructFieldsFromParticle (cyclomatic 18): XSDToSchema.getStructFieldsFromParticle has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"5dcc409fe436a245394e88604fecd1bf39e11a855e28bdf54f622e64e1b94aef"}},{"ruleId":"D1","level":"warning","message":{"text":"RocksDBFileManager.deleteOldVersions (cyclomatic 18): RocksDBFileManager.deleteOldVersions has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala"},"region":{"startLine":659}}}],"partialFingerprints":{"codehealthFindingId/v1":"8823d5d2036b89655e71e20607083a6933c242b134defc7eeaacdb1cb76dc9c5"}},{"ruleId":"D1","level":"warning","message":{"text":"AvroStateEncoder.encodePrefixKeyForRangeScan (cyclomatic 18): AvroStateEncoder.encodePrefixKeyForRangeScan has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1063}}}],"partialFingerprints":{"codehealthFindingId/v1":"90ecab28f69aacfa34966190e26e083e9cf953e6016d14d0e3540cb09b157ad1"}},{"ruleId":"D1","level":"warning","message":{"text":"RowSetUtils.toTColumnValue (cyclomatic 18): RowSetUtils.toTColumnValue has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/RowSetUtils.scala"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"f235b2139bf57d3b3b864ab1c7e0c769485074b4d887f9856d51387247d5e87e"}},{"ruleId":"D1","level":"warning","message":{"text":"HiveInspectors.unwrapperFor (cyclomatic 18): HiveInspectors.unwrapperFor has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: HiveInspectors.javaTypeToDataType (cyclomatic 41) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":852}}}],"partialFingerprints":{"codehealthFindingId/v1":"6da1658dc081ee15ab73876357ef33426433e8c8ea4b367d6fb4a9072ff5695d"}},{"ruleId":"D1","level":"warning","message":{"text":"CommandBuilderUtils.parseOptionString (cyclomatic 18): CommandBuilderUtils.parseOptionString has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/CommandBuilderUtils.java"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"396542a55e89549acfa6a037ce25189aa85801806d3aafa48a07e06db0d69b91"}},{"ruleId":"D1","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseTrimRight (cyclomatic 18): CollationAwareUTF8String.lowercaseTrimRight has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1490}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9d216691f727b27d67ad85520910c1ba5c516fbe3569e31038b13e173423c3d"}},{"ruleId":"D1","level":"warning","message":{"text":"CollationAwareUTF8String.trimRight (cyclomatic 18): CollationAwareUTF8String.trimRight has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1588}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8c284565dba81e450eb0b93303ebab812732d8991a1a81e25d31a3928341e18"}},{"ruleId":"D1","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.loadNextRowGroup (cyclomatic 18): LateMaterializationParquetRecordReader.loadNextRowGroup has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"260cc9990bc37f5f106742d343eb81c646d1fae6ba611d6e67bc98d7e1c18314"}},{"ruleId":"D1","level":"warning","message":{"text":"VectorizedColumnReader.readBatch (cyclomatic 18): VectorizedColumnReader.readBatch has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2ecfd981e9b4414e7c29116949c206ee1388b0c63afac0355a84d5f5effe6cf"}},{"ruleId":"D1","level":"warning","message":{"text":"connect._convert_exception (cyclomatic 18): connect._convert_exception has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/connect.py"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e789a5a88d90ba3fd895a66621e662a576a9be9cd67c4b297ab69f7040fbf82"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.__init__ (cyclomatic 18): DataFrame.__init__ has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":553}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed707e33df264ec5eaa028eb93b5a6a63190cc1607dd5bb464283f5da52c8d07"}},{"ruleId":"D1","level":"warning","message":{"text":"Frame.to_csv (cyclomatic 18): Frame.to_csv has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"49aab68d978780c92b63df5de1ba4694c2026ab1634d87309b61d218bda80967"}},{"ruleId":"D1","level":"warning","message":{"text":"utils.align_diff_frames (cyclomatic 18): utils.align_diff_frames has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/utils.py"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"de801d7741126468b371c92cbee82eea02e544e3375f022ff4c58fe893da6a80"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.explain (cyclomatic 18): DataFrame.explain has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"2332ddee6ae1fe9ccdf87abd2ca0c259a15a6b889aca263a6705d60085221fb0"}},{"ruleId":"D1","level":"warning","message":{"text":"plan_data_source_read.records_to_arrow_batches (cyclomatic 18): plan_data_source_read.records_to_arrow_batches has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/plan_data_source_read.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd7132cdd5549ea7913754e723b93c32ffacef4ab70778359bda76870f45328d"}},{"ruleId":"D1","level":"warning","message":{"text":"StringSubstitutor.substitute (cyclomatic 17): StringSubstitutor.substitute has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/StringSubstitutor.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"e28fe6bb56095388e29ebdb07d5624353080d02c1248c8d79abd27a3822da32b"}},{"ruleId":"D1","level":"warning","message":{"text":"NettyBlockRpcServer.receive (cyclomatic 17): NettyBlockRpcServer.receive has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/network/netty/NettyBlockRpcServer.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1afbf6c8fac438295c12b3cc124ceea7254ac164b3d0d95900325490a5241fd"}},{"ruleId":"D1","level":"warning","message":{"text":"ResourceProfileManager.isSupported (cyclomatic 17): ResourceProfileManager.isSupported has cyclomatic complexity 17 (threshold 15). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ResourceProfileManager.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"987c2334facb0d5feef9b12eba0cecea8335d0da5363cb196c8909664dcc7009"}},{"ruleId":"D1","level":"warning","message":{"text":"BLAS.gemmImpl (cyclomatic 17): BLAS.gemmImpl has cyclomatic complexity 17 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":523}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ac0189be29de66c0c79a4bd51713f90925db3ad1c6678c2b455b5fe740ae523"}},{"ruleId":"D1","level":"warning","message":{"text":"ParsedRFormula.resolve (cyclomatic 17): ParsedRFormula.resolve has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb4157ee35d1281e089fada5b76b9f59610abac312a01c2592e6a917979ec7d3"}},{"ruleId":"D1","level":"warning","message":{"text":"Word2Vec.doFit (cyclomatic 17): Word2Vec.doFit has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c78b5ed96e56a9069bc208ca6f5d277dbfc67b1afbb82ca1d47c937aea39a1d"}},{"ruleId":"D1","level":"warning","message":{"text":"BLAS.gemm (cyclomatic 17): BLAS.gemm has cyclomatic complexity 17 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"571fe56a9270bd9e4872fb5824b37d50b58fb1514c620b319aa979ab4861141f"}},{"ruleId":"D1","level":"warning","message":{"text":"LogisticGradient.compute (cyclomatic 17): LogisticGradient.compute has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbd13693cd5e83fabf8e19b9841eaf19c968aed549d49581a7b58bd0c4624fff"}},{"ruleId":"D1","level":"warning","message":{"text":"ExecutorPodsLifecycleManager.onNewSnapshots (cyclomatic 17): ExecutorPodsLifecycleManager.onNewSnapshots has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsLifecycleManager.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9c35d146c408a70385a7d89812e37d5338306cac40e836ab406a63e46943547"}},{"ruleId":"D1","level":"warning","message":{"text":"ApplyCharTypePaddingHelper.singleNodePaddingForStringComparison (cyclomatic 17): ApplyCharTypePaddingHelper.singleNodePaddingForStringComparison has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ApplyCharTypePaddingHelper.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"49a6c3abc7a2768450820886b9c07b60b8db955ecdc64f8fdc1be6474354d563"}},{"ruleId":"D1","level":"warning","message":{"text":"CTESubstitution.apply (cyclomatic 17): CTESubstitution.apply has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CTESubstitution.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"c91162e65ede1402cfa8cc84190593faeabdbd29953e3c8d3ea2bd95428847ab"}},{"ruleId":"D1","level":"warning","message":{"text":"CollationTypeCoercion.findCollationContext (cyclomatic 17): CollationTypeCoercion.findCollationContext has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CollationTypeCoercion.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"07940f4ef03899cb1ae4db26218eb7ff24a0dc011576153e11e59a7a4b826cfb"}},{"ruleId":"D1","level":"warning","message":{"text":"ExternalLookupJoinEligibility.apply (cyclomatic 17): ExternalLookupJoinEligibility.apply has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a39280d3348a75a70cfee064d7733ec226536245cf28293aaeaa5668c5ccdb5"}},{"ruleId":"D1","level":"warning","message":{"text":"ImplicitTypeCoercion.apply (cyclomatic 17): ImplicitTypeCoercion.apply has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"0af8b29f93065d0dc224ce4fc4fd227ae08ef5cde92507362a0ce50f9865ef81"}},{"ruleId":"D1","level":"warning","message":{"text":"RoundBase.nullSafeEval (cyclomatic 17): RoundBase.nullSafeEval has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala"},"region":{"startLine":1780}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d35ce92a09c36d66a6e34c97979cae78ecf95759349365bac03cbefe67db002"}},{"ruleId":"D1","level":"warning","message":{"text":"BaseGenericInternalRow.equals (cyclomatic 17): BaseGenericInternalRow.equals has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef8056ba6d3a2c2fa8ccfea730a59deb419877514cc7d61de5e6e6d1b5e81664"}},{"ruleId":"D1","level":"warning","message":{"text":"JsonInferSchema.compatibleType (cyclomatic 17): JsonInferSchema.compatibleType has cyclomatic complexity 17 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea5d95872005811364dc083c919c2d8e64ee9cc8034c448ff0a37da0b41f7f4d"}},{"ruleId":"D1","level":"warning","message":{"text":"GeneratorNestedColumnAliasing.unapply (cyclomatic 17): GeneratorNestedColumnAliasing.unapply has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"a001e3b21feae03cad6d82197bb59c00a93f1144e17693cea137df3217a4256d"}},{"ruleId":"D1","level":"warning","message":{"text":"ConvertToCatalyst.applyExpr (cyclomatic 17): ConvertToCatalyst.applyExpr has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1322}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce6bd2d4e22ef5e912acab25cd5f72792973abb0741c998ed269c3592181ed45"}},{"ruleId":"D1","level":"warning","message":{"text":"RuleExecutor.execute (cyclomatic 17): RuleExecutor.execute has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/rules/RuleExecutor.scala"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbd20f04623716688073268b9edd9c8519db4125b33660aedbeb24e7188a5226"}},{"ruleId":"D1","level":"warning","message":{"text":"util.usePrettyExpression (cyclomatic 17): util.usePrettyExpression has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"c58370d0cd80a5d2086ce12f050eb9f7156a67bfc1feab5a9c8457ee99cac70c"}},{"ruleId":"D1","level":"warning","message":{"text":"DataSourceV2Relation.transformV2Stats (cyclomatic 17): DataSourceV2Relation.transformV2Stats has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala"},"region":{"startLine":761}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fd255115990471c258b28a297f39a323e1b9e0dcc189b6bb69f946bec04e12e"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkPlan.executeTake (cyclomatic 17): SparkPlan.executeTake has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":525}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ded954f087c880a102d5a4a24044bb02c1d3669fa65c032e6dd62bebdb92e6b"}},{"ruleId":"D1","level":"warning","message":{"text":"WholeStageCodegenExec.decideFromTrials (cyclomatic 17): WholeStageCodegenExec.decideFromTrials has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"922177cc3c5a3d8fd5dbb5e9ec637733b08eb63357930f3bae72b1d7ec64ba00"}},{"ruleId":"D1","level":"warning","message":{"text":"DemoteBroadcastHashJoin.selectJoinStrategy (cyclomatic 17): DemoteBroadcastHashJoin.selectJoinStrategy has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/DemoteBroadcastHashJoin.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"e43a5ff487b2c4d54b7d2b03c712369607683f11a334434d8a4ff9b64b73ae8e"}},{"ruleId":"D1","level":"warning","message":{"text":"AggregatePushDownUtils.getSchemaForPushedAggregation (cyclomatic 17): AggregatePushDownUtils.getSchemaForPushedAggregation has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/AggregatePushDownUtils.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"41dc1515d50b2829d1b66957febfa5597ef9888e2fc62a64211b3e68f8b41118"}},{"ruleId":"D1","level":"warning","message":{"text":"JDBCRDD.compute (cyclomatic 17): JDBCRDD.compute has cyclomatic complexity 17 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f7294f7056a5c550fb1c60f6858a234e3d0d924ca8f8c0187c7ac57072b33a1"}},{"ruleId":"D1","level":"warning","message":{"text":"InferVariantShreddingSchema.mergeSchema (cyclomatic 17): InferVariantShreddingSchema.mergeSchema has cyclomatic complexity 17 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/InferVariantShreddingSchema.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1f696f050754a595dcf45d26f62c80fe7e6d9c0fa6440693c4f727253946044"}},{"ruleId":"D1","level":"warning","message":{"text":"InferVariantShreddingSchema.collectFieldStats (cyclomatic 17): InferVariantShreddingSchema.collectFieldStats has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/InferVariantShreddingSchema.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7022ecb3862cbf8604c8a0e2293f2c4ee214803a12540fb25b55363b327e604"}},{"ruleId":"D1","level":"warning","message":{"text":"PrepareExternalLookupJoin.prepare (cyclomatic 17): PrepareExternalLookupJoin.prepare has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4765e79fca47eeb0aff055e2dcc8d6f94f1fe4e46ad3f488826cad15b7870e4"}},{"ruleId":"D1","level":"warning","message":{"text":"BroadcastRangeJoinExec.makeCandidateFn (cyclomatic 17): BroadcastRangeJoinExec.makeCandidateFn has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"0bb926e496e89e81133b61d28046a05994e3a32ea183f9ac1e80af346eb45203"}},{"ruleId":"D1","level":"warning","message":{"text":"SQLLastAttemptAccumulator.extractStageRDDScopes (cyclomatic 17): SQLLastAttemptAccumulator.extractStageRDDScopes has cyclomatic complexity 17 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"f70dad65ee810c8474ecba165ace8bdb527070d4cb9edabb0752246d184a7c07"}},{"ruleId":"D1","level":"warning","message":{"text":"StatFunctions.summary (cyclomatic 17): StatFunctions.summary has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbdf0fb12ff24b5f89a326f667cfd60220f113a9b7b4f3abfb062dd2bc21264f"}},{"ruleId":"D1","level":"warning","message":{"text":"TriggeredGraphExecution.topologicalExecution (cyclomatic 17): TriggeredGraphExecution.topologicalExecution has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/TriggeredGraphExecution.scala"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f325087c00dee26d1139651254188c9b62337d08769ff278e8e1855951c05bd"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkLauncher.startApplication (cyclomatic 17): SparkLauncher.startApplication has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkLauncher.java"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7c4d5635908629fb26214b72d9ef8689ac1138771d7f07a7d21c64d16d35e7b"}},{"ruleId":"D1","level":"warning","message":{"text":"UTF8String.levenshteinDistance (cyclomatic 17): UTF8String.levenshteinDistance has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":2228}}}],"partialFingerprints":{"codehealthFindingId/v1":"530a8ff039a8beef565c445efb21c455a42c225d1859d45f1e9b96050224c53a"}},{"ruleId":"D1","level":"warning","message":{"text":"AwsStsCredentialProvider.init (cyclomatic 17): AwsStsCredentialProvider.init has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/credential-aws/src/main/java/org/apache/spark/security/aws/AwsStsCredentialProvider.java"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"9246d97402fd003954c2c6f051dce8b30fb33d759d4e02f7a32bbd91f26f72c9"}},{"ruleId":"D1","level":"warning","message":{"text":"RecordBinaryComparator.compare (cyclomatic 17): RecordBinaryComparator.compare has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a44cc4828872d0ec69322acd6bda565f21bf71a3de3755406662b47382c25a0"}},{"ruleId":"D1","level":"warning","message":{"text":"VectorizedColumnReader.isLazyDecodingSupported (cyclomatic 17): VectorizedColumnReader.isLazyDecodingSupported has cyclomatic complexity 17 (threshold 15). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f9deeb54e873cdf04f2dffebf3fc852565b808cd7350645fd389428e2e899fa"}},{"ruleId":"D1","level":"warning","message":{"text":"RemoteMLReader.loadInstance (cyclomatic 17): RemoteMLReader.loadInstance has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/readwrite.py"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"e449f360cf84f041b3f4b058bb12734f72c4f4cd292821914623273248584bd8"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.corrwith (cyclomatic 17): DataFrame.corrwith has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1765}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ea4072668d15d8de836c7728f29f7afaa53dd1f911f65220e01663cb07497ad"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame._assign (cyclomatic 17): DataFrame._assign has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5852}}}],"partialFingerprints":{"codehealthFindingId/v1":"bef9ce2b3a9df49ab6032cd71a79971d0cfd8f12e780ecdc1487929a1fccd911"}},{"ruleId":"D1","level":"warning","message":{"text":"Series._rank (cyclomatic 17): Series._rank has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":4350}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc2c62474ab50899cbe474a2082f4cac217a3f427106e00cf41f03bbd49c4069"}},{"ruleId":"D1","level":"warning","message":{"text":"LiteralExpression.__repr__ (cyclomatic 17): LiteralExpression.__repr__ has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: LiteralExpression.__init__ (cyclomatic 19) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"af5ea4b2ce36f98848b87d2ac1053c6cbe0600e7941167829152f78a4b3567b9"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowToPandasConversion._convert_array_numpy (cyclomatic 17): ArrowToPandasConversion._convert_array_numpy has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":2075}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b3e4d1060cee8842495c97558424f5278f14f996094786a71447e588205c2cb"}},{"ruleId":"D1","level":"warning","message":{"text":"types._to_corrected_pandas_type (cyclomatic 17): types._to_corrected_pandas_type has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"6431ca5d122cd9a539cae1cf10c75f9ef180c74d0cfb13c42df9ff426eaf6ee7"}},{"ruleId":"D1","level":"warning","message":{"text":"UserDefinedFunction.__init__ (cyclomatic 17): UserDefinedFunction.__init__ has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"40b379b9f2b3365054b0b3f3380a8656569115439415b317791272c7dade8d58"}},{"ruleId":"D1","level":"warning","message":{"text":"getInnerText (cyclomatic 17): getInnerText has cyclomatic complexity 17 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"c125f8c1eda74bead01756eeab484f67366fbf74ea21065120d0c43311fcb7f0"}},{"ruleId":"D1","level":"warning","message":{"text":"KafkaSourceProvider.validateBatchOptions (cyclomatic 16): KafkaSourceProvider.validateBatchOptions has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":370}}}],"partialFingerprints":{"codehealthFindingId/v1":"68c16954e0ac24f95331f67608db8d3899d5a3541c6afa32b4feb12005e1e45e"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskContextImpl.markTaskCompleted (cyclomatic 16): TaskContextImpl.markTaskCompleted has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"04e3f91cbf83887b19fe89c2033a387883827abd2b477ee1b6dabd85cd563e78"}},{"ruleId":"D1","level":"warning","message":{"text":"TaskContextImpl.invokeListeners (cyclomatic 16): TaskContextImpl.invokeListeners has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":596}}}],"partialFingerprints":{"codehealthFindingId/v1":"8af3fee39c57a60cf0b4252a3e6ed2dc3cf4867c0efa567dea43adceea7db990"}},{"ruleId":"D1","level":"warning","message":{"text":"PythonWorkerFactory.startDaemon (cyclomatic 16): PythonWorkerFactory.startDaemon has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"af16590523594c8f285703d57dee36328c488b4626f299c382dcd3cc2452077b"}},{"ruleId":"D1","level":"warning","message":{"text":"CoarseGrainedExecutorBackend.decommissionSelf (cyclomatic 16): CoarseGrainedExecutorBackend.decommissionSelf has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"937caba71af1805220d993eb39551d0eee0a45f0f69a374bfcbad99335ca826a"}},{"ruleId":"D1","level":"warning","message":{"text":"IndexShuffleBlockResolver.writeMetadataFileAndCommit (cyclomatic 16): IndexShuffleBlockResolver.writeMetadataFileAndCommit has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5d9e556563647b599429bb9e8f2744d4d7c169ecc72793026f7032bcbb27ff8"}},{"ruleId":"D1","level":"warning","message":{"text":"BlockManagerMasterEndpoint.updateBlockInfo (cyclomatic 16): BlockManagerMasterEndpoint.updateBlockInfo has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: BlockManagerMasterEndpoint.receiveAndReply (cyclomatic 31) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":828}}}],"partialFingerprints":{"codehealthFindingId/v1":"086bfc251869d4cd9d43915d13658abae638fb65e5e948c8dca2676009176e74"}},{"ruleId":"D1","level":"warning","message":{"text":"LogisticRegression.createInitialSolution (cyclomatic 16): LogisticRegression.createInitialSolution has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":820}}}],"partialFingerprints":{"codehealthFindingId/v1":"63c98ca7f8781cfb1ce0643fd884ef1c9b5d47b1a7093cef1ab35d6a6ad47673"}},{"ruleId":"D1","level":"warning","message":{"text":"GradientBoostedTrees.boost (cyclomatic 16): GradientBoostedTrees.boost has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa9e4d5435525ffd4b01e59c192f3540f7477b2758cb0712d990fa6a75bb7cc2"}},{"ruleId":"D1","level":"warning","message":{"text":"RandomForest.runBagged (cyclomatic 16): RandomForest.runBagged has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc6d85f4af914f08ea1230f588379233628da80a12bb61f6fac13f32e6ef08c3"}},{"ruleId":"D1","level":"warning","message":{"text":"RandomForest.findBestSplits (cyclomatic 16): RandomForest.findBestSplits has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c2465dc810e11c4ad7e1bb21176a6082ae4ba7c59a629236185e5b0ecdf1a57"}},{"ruleId":"D1","level":"warning","message":{"text":"RowMatrix.columnSimilaritiesDIMSUM (cyclomatic 16): RowMatrix.columnSimilaritiesDIMSUM has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":722}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cf4a99f989e19e2ed363c25c54177f1d268040a3a318af4b9f1cbf074cdab1d"}},{"ruleId":"D1","level":"warning","message":{"text":"Metadata.fromJObject (cyclomatic 16): Metadata.fromJObject has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Metadata.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"ace4292e3538893d6d5ed75746841e47fc360e18aa40fa1acd02aee3b0db996a"}},{"ruleId":"D1","level":"warning","message":{"text":"CollapseGroupedSumOfCount.collapse (cyclomatic 16): CollapseGroupedSumOfCount.collapse has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CollapseGroupedSumOfCount.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a5695f3a8cb2d1589914ca5b3849afa7b0269f3bf709c828a8535c8fa5bfae8"}},{"ruleId":"D1","level":"warning","message":{"text":"OptimizeJoinCondition.optimizeCondition (cyclomatic 16): OptimizeJoinCondition.optimizeCondition has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJoinCondition.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab6078b6e95a68d28962149cb45ec428f26f171b59d36652632ae7dacd9e2eb9"}},{"ruleId":"D1","level":"warning","message":{"text":"CombineUnions.flattenUnion (cyclomatic 16): CombineUnions.flattenUnion has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":2414}}}],"partialFingerprints":{"codehealthFindingId/v1":"b91e39b89f6b26a5cc8fb13a8f4c7a9d1331d83bb9f82f8310fa811f4af60280"}},{"ruleId":"D1","level":"warning","message":{"text":"ToNumberParser.formatDigitGroups (cyclomatic 16): ToNumberParser.formatDigitGroups has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":788}}}],"partialFingerprints":{"codehealthFindingId/v1":"80f6f02534e25f105ba56448b3a70f7fc85a892c1fc5e7bd637ab57853cee174"}},{"ruleId":"D1","level":"warning","message":{"text":"Abbreviator.abbreviateRecursive (cyclomatic 16): Abbreviator.abbreviateRecursive has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/Abbreviator.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae037a09f997294c8aa6c9624a8f6835b0f0e320322997d10ee386cf81e55766"}},{"ruleId":"D1","level":"warning","message":{"text":"Serializer.deserializeMethodArguments (cyclomatic 16): Serializer.deserializeMethodArguments has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/Serializer.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c692b8b346fdd5d42e73164ca67fab614dae13b06baf46c9fde56a5f74e5f6f"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkConnectPlanner.handleStreamingQueryCommand (cyclomatic 16): SparkConnectPlanner.handleStreamingQueryCommand has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: SparkConnectPlanner.transformRelation (cyclomatic 66) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":3880}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fb5ecd6b8affe2bce236b65568973381b3911f12d58ee44110fa677ec050c2e"}},{"ruleId":"D1","level":"warning","message":{"text":"ResolveDataSource.apply (cyclomatic 16): ResolveDataSource.apply has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"792d725d18df44704d51c628e6e29ca7f2d83da14c563baad76e6db562ffef18"}},{"ruleId":"D1","level":"warning","message":{"text":"ParseSqlResult.qualifyRoutine (cyclomatic 16): ParseSqlResult.qualifyRoutine has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing. This is NOT this file\u0027s highest cyclomatic complexity: ParseSqlResult.primaryQueryPlan (cyclomatic 29) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4cad93b840102f0c2bbd157667630db625b8eb67f76d8df75ced629f9122b5c"}},{"ruleId":"D1","level":"warning","message":{"text":"SQLExecution.withNewExecutionId0 (cyclomatic 16): SQLExecution.withNewExecutionId0 has cyclomatic complexity 16 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"53ae5da2bffcd4e1fb33d108019fbcfa61b4ab2c3a953578848533aa22ec954c"}},{"ruleId":"D1","level":"warning","message":{"text":"SparkSqlAstBuilder.visitCreateUserDefinedFunction (cyclomatic 16): SparkSqlAstBuilder.visitCreateUserDefinedFunction has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"abb586d1c3120c294457fe66037e49b2f75c8c095068edfbdb21ab5acd58e666"}},{"ruleId":"D1","level":"warning","message":{"text":"Aggregation.apply (cyclomatic 16): Aggregation.apply has cyclomatic complexity 16 (threshold 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Where every arm is uniform \u2014 the same kind of value, with no behaviour of its own \u2014 a table keyed by the case is the shorter form; wherever the arms carry different data or different behaviour, keep them as cases, because collapsing those trades an explicit, reviewable set of cases for nothing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":670}}}],"partialFingerprints":{"codehealthFindingId/v1":"72d116ea7a4d5ee0e5c56048cde71e507a94f04aa67fa9face2e1297057ae320"}},{"ruleId":"D1","level":"warning","message":{"text":"TungstenAggregationIterator.processInputs (cyclomatic 16): TungstenAggregationIterator.processInputs has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"c350b38ce4dffcbdf6708780a30e79272f9d258b4f5b12bccdce11caabcc9c84"}},{"ruleId":"D1","level":"warning","message":{"text":"TruncateTableCommand.run (cyclomatic 16): TruncateTableCommand.run has cyclomatic complexity 16 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":449}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ef177857ceeb3df6afdc29a2fc2ef4012e5240e8661b7e2e0d072186e2cc71a"}},{"ruleId":"D1","level":"warning","message":{"text":"DataSourceAnalysis.apply (cyclomatic 16): DataSourceAnalysis.apply has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: DataSourceStrategy.translateLeafNodeFilter (cyclomatic 23) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"9728895bc717a803f6566287ff2b3b4654d5185e1978735a2c712dbeb48a6701"}},{"ruleId":"D1","level":"warning","message":{"text":"EmbeddedArraySplitter.consumeValue (cyclomatic 16): EmbeddedArraySplitter.consumeValue has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/EmbeddedArrayJsonDataSource.scala"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9890a37545e973ff72994178a3e1f44009290e56fbb68f8c9255ba52717b251"}},{"ruleId":"D1","level":"warning","message":{"text":"PreprocessTableCreation.apply (cyclomatic 16): PreprocessTableCreation.apply has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"b01b0d50f890e5976e98049837df27ff37d8d1d86b5587f256173ef0e67d9e93"}},{"ruleId":"D1","level":"warning","message":{"text":"ColumnDomains.compare (cyclomatic 16): ColumnDomains.compare has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3789a4d785388818cd18731260b1de5b351b5c6e60da1bb28bd6506a5a8b1f1"}},{"ruleId":"D1","level":"warning","message":{"text":"StateDataSource.runStateVarChecks (cyclomatic 16): StateDataSource.runStateVarChecks has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"dac242ab0daa88eed27f9c05f0b381cd02a1db09d9f733adf4206cd9e4feb95a"}},{"ruleId":"D1","level":"warning","message":{"text":"XmlRecordReader.readUntilEndElement (cyclomatic 16): XmlRecordReader.readUntilEndElement has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala"},"region":{"startLine":231}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3bd012382e9daf9dc97d0dc0c55303c4424e74d8f6aab658d487ddc88db1ab5"}},{"ruleId":"D1","level":"warning","message":{"text":"StateStoreSaveExec.doExecute (cyclomatic 16): StateStoreSaveExec.doExecute has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":880}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5671354e073c79d275f8458a671a4f8ed9aee3ce62e4926eea2ec55703116e3"}},{"ruleId":"D1","level":"warning","message":{"text":"RocksDBStateStoreChangeDataReader.getNext (cyclomatic 16): RocksDBStateStoreChangeDataReader.getNext has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":1676}}}],"partialFingerprints":{"codehealthFindingId/v1":"c52031aec1027a574ee725113168330ffa950fbdced85771b567ccbea0dd15ce"}},{"ruleId":"D1","level":"warning","message":{"text":"MySQLDialect.getCatalystType (cyclomatic 16): MySQLDialect.getCatalystType has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"43defde5bdf3650ff9724aa58f334570bbd29e70398881a3e3334caa2d3b8eec"}},{"ruleId":"D1","level":"warning","message":{"text":"OracleDialect.getCatalystType (cyclomatic 16): OracleDialect.getCatalystType has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"c760213ea0074ca169d9fcd45226b890cc6b7070a60a7fd9cdbdd1788309c73c"}},{"ruleId":"D1","level":"warning","message":{"text":"ProcessIterator.advance (cyclomatic 16): ProcessIterator.advance has cyclomatic complexity 16 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/grpc/src/main/scala/org/apache/spark/udf/worker/grpc/GrpcWorkerSession.scala"},"region":{"startLine":923}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c9581918cbde4422a226dc7ed9a54649a099fe7dccad473ff508c36a943490d"}},{"ruleId":"D1","level":"warning","message":{"text":"Index.addOrRemove (cyclomatic 16): Index.addOrRemove has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"a90b5694dabb33cc6bf4ab9e76ccfd1c2a9bf8498a023634202cb614604a68e0"}},{"ruleId":"D1","level":"warning","message":{"text":"Index.addOrRemove (cyclomatic 16): Index.addOrRemove has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"aff38531291576cdc069fcee81f52aca84f56a1aee8fdf7e9ccd126581f6bf45"}},{"ruleId":"D1","level":"warning","message":{"text":"DecryptionHandler.channelRead (cyclomatic 16): DecryptionHandler.channelRead has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/GcmTransportCipher.java"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"98cc2770a580c8c47cd135ac4007596e97eb52fc4a4d1472e6348c7964a80a61"}},{"ruleId":"D1","level":"warning","message":{"text":"VariantShreddingWriter.castShredded (cyclomatic 16): VariantShreddingWriter.castShredded has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantShreddingWriter.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"34a66817bb3cef26e2fcb9d7a4b54bba388282c39db198fdb0fd18f8fe3f6b8d"}},{"ruleId":"D1","level":"warning","message":{"text":"ExpressionImplUtils.aesInternal (cyclomatic 16): ExpressionImplUtils.aesInternal has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java"},"region":{"startLine":277}}}],"partialFingerprints":{"codehealthFindingId/v1":"21ed677a43e7bc6ad6ed0c3c8ec2de2433593f96c669eebd14601223530457ef"}},{"ruleId":"D1","level":"warning","message":{"text":"ExpressionImplUtils.jaroWinklerSimilarity (cyclomatic 16): ExpressionImplUtils.jaroWinklerSimilarity has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec1257b764f4b07bd148fe619b45ffe15473d8a4b8d4b8bb8ab0b5e33f558a98"}},{"ruleId":"D1","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.initializeLateMaterialization (cyclomatic 16): LateMaterializationParquetRecordReader.initializeLateMaterialization has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"cac118178ceafa0644eb02a2ce240f3cce66bfdf1be9d177c698431f6b5b2008"}},{"ruleId":"D1","level":"warning","message":{"text":"merge_spark_pr.prepare_merge_title (cyclomatic 16): merge_spark_pr.prepare_merge_title has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3015}}}],"partialFingerprints":{"codehealthFindingId/v1":"2de904dbeb307bbcdce296bcfce282556fb2ec04762419f1e2faa6c98fe1739c"}},{"ruleId":"D1","level":"warning","message":{"text":"instrumentation_utils._attach (cyclomatic 16): instrumentation_utils._attach has cyclomatic complexity 16 (threshold 15). To reduce it, separate the branches: extract each independent case into its own named function so the top-level body reads as a short sequence of named decisions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/instrumentation_utils.py"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"328fd3a0af7f197dc4a90785a119f30a00287af7972649cfb89bd3f8bbf6149e"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.replace (cyclomatic 16): DataFrame.replace has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6520}}}],"partialFingerprints":{"codehealthFindingId/v1":"077893008307add6e3eec349a97ac33b16768ee61a00db055a7b3075544a7f8a"}},{"ruleId":"D1","level":"warning","message":{"text":"DataFrame.quantile (cyclomatic 16): DataFrame.quantile has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13034}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba8aa72e72c489b4c4ff2d776a1b27156d0a93bc59c80831a3dbe9246454ddfa"}},{"ruleId":"D1","level":"warning","message":{"text":"Frame.truncate (cyclomatic 16): Frame.truncate has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":3110}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc85b3118a36f300f017559baaae07554574552a37224e442c8e549358a8e608"}},{"ruleId":"D1","level":"warning","message":{"text":"typehints._new_type_holders (cyclomatic 16): typehints._new_type_holders has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"43875efc52ddb08b2789c23e48ea6adb5fd70709af1529fcee9de49e28c6628f"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowBatchTransformer.enforce_schema (cyclomatic 16): ArrowBatchTransformer.enforce_schema has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c8bc97d9084ef13e8c8508baa8d2fed22f8f2393340f97823ef726530e867c5"}},{"ruleId":"D1","level":"warning","message":{"text":"transpile._get_function_from_ast (cyclomatic 16): transpile._get_function_from_ast has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":1306}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ff26c42e0e0a6089cccef6cd6adbdc153e8f5513a87ec283fe12c6f014d2045"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmit.prepareSubmitEnvironment (cognitive 201): SparkSubmit.prepareSubmitEnvironment has cognitive complexity 201 (threshold 15). Drivers by points: if/else 92 (152 pts), boolean chains 32, match/switch 6 (8 pts), loops 3 (7 pts), error handling 1 (2 pts) (nesting depth added 67). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"f647c2b695abf30824c654559b6e0017d496101551cb29c41032d00773d69f75"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.handleTaskCompletion (cognitive 198): DAGScheduler.handleTaskCompletion has cognitive complexity 198 (threshold 15). Drivers by points: if/else 52 (143 pts), match/switch 10 (25 pts), boolean chains 16, error handling 3 (14 pts) (nesting depth added 117). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3904}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cf199a6ffb69863fffb36dc00db20035c5d0d9616a57f9ae0d978e53a6ca048"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 194): (anonymous) has cognitive complexity 194 (threshold 15). Drivers by points: if/else 107 (136 pts), ternaries 20 (32 pts), boolean chains 25, match/switch 1 (nesting depth added 41). None of this is in the body itself: all 194 points belong to 55 function items inside it that branch (a function literal at line 404, a function literal at line 678, a function literal at line 1082, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb5421435e198f6fb3cffebcc6bf37465356cc22a7f887697204b948d4b70ab0"}},{"ruleId":"D2","level":"warning","message":{"text":"UnsupportedOperationChecker.checkForStreaming (cognitive 145): UnsupportedOperationChecker.checkForStreaming has cognitive complexity 145 (threshold 15). Drivers by points: if/else 45 (81 pts), match/switch 21 (38 pts), boolean chains 26 (nesting depth added 53). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"70d666261cd0496c64d6929b381b0c4ddd9ac774d9969d871d9770e994e1420e"}},{"ruleId":"D2","level":"warning","message":{"text":"DecorrelateInnerQuery.apply (cognitive 140): DecorrelateInnerQuery.apply has cognitive complexity 140 (threshold 15). Drivers by points: if/else 51 (102 pts), match/switch 10 (34 pts), boolean chains 4 (nesting depth added 75). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala"},"region":{"startLine":476}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ee9fdb321c63e86bd100b99d0ca7ab2c0c7a0e0920ca893b28143d8bd9cd853"}},{"ruleId":"D2","level":"warning","message":{"text":"LocIndexerLike.__setitem__ (cognitive 129): LocIndexerLike.__setitem__ has cognitive complexity 129 (threshold 15). Drivers by points: if/else 45 (108 pts), boolean chains 14, loops 3 (7 pts) (nesting depth added 67). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"750b229e5b7fa57d11366baf13a32450ad4ec0067abfe2c20dd41a9a2761e06a"}},{"ruleId":"D2","level":"warning","message":{"text":"CheckAnalysis.checkAnalysis0 (cognitive 117): CheckAnalysis.checkAnalysis0 has cognitive complexity 117 (threshold 15). Drivers by points: match/switch 22 (54 pts), if/else 25 (43 pts), boolean chains 20 (nesting depth added 50). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5153ef8ca90a18d318b6a3b21564a4df18f3e9e667ec3d87401be0d36b29479"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession.createDataFrame (cognitive 116): SparkSession.createDataFrame has cognitive complexity 116 (threshold 15). Drivers by points: if/else 45 (85 pts), ternaries 6 (17 pts), boolean chains 10, loops 1 (4 pts) (nesting depth added 54). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"88ef4484184b6cd4adb52c980f416cc59198b57d5b31a477e7a372c6bbc24d71"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveInspectors.unwrapperFor (cognitive 113): HiveInspectors.unwrapperFor has cognitive complexity 113 (threshold 15). Drivers by points: if/else 57 (110 pts), match/switch 2 (3 pts) (nesting depth added 54). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"30198831e6893fe7c725eeb2e4645ec399fa046e801c17db449ce94d49d934d8"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkDateTimeUtils.parseTimestampString (cognitive 109): SparkDateTimeUtils.parseTimestampString has cognitive complexity 109 (threshold 15). Drivers by points: if/else 36 (90 pts), boolean chains 16, loops 3 (nesting depth added 54). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f893e8f5fe2d2874238d03b47fac79b074be70f2c3bd7747f3b3ee260f94bcf"}},{"ruleId":"D2","level":"warning","message":{"text":"PlanMerger.tryMergePlans (cognitive 109): PlanMerger.tryMergePlans has cognitive complexity 109 (threshold 15). Drivers by points: match/switch 17 (54 pts), if/else 22 (39 pts), boolean chains 16 (nesting depth added 54). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b7e363ff5600c61b55ca125c0ac47e9ecde9a089f595ef8f5365565cc5d2056"}},{"ruleId":"D2","level":"warning","message":{"text":"exports (cognitive 102): exports has cognitive complexity 102 (threshold 15). Drivers by points: if/else 19 (53 pts), ternaries 8 (19 pts), error handling 4 (12 pts), boolean chains 10, loops 4 (7 pts), other 1 (nesting depth added 56). Of this number, 83 points are the body\u0027s own statements and 19 belong to 18 function items inside it that branch. To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":".github/workflows/update_build_status.js"},"region":{"startLine":20}}}],"partialFingerprints":{"codehealthFindingId/v1":"49b11f7ba0d6cff279e2dfbdff74959bd80840aa4f51c78cbd8a13f718013709"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetVectorUpdaterFactory.getUpdater (cognitive 101): ParquetVectorUpdaterFactory.getUpdater has cognitive complexity 101 (threshold 15). Drivers by points: if/else 58 (83 pts), boolean chains 14, ternaries 1 (3 pts), match/switch 1 (nesting depth added 27). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2fc5c3df84f1fab370bed945c332f9a41876c0ba0d9de89db6a9b2b511fdf94"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSourceV2Strategy.apply (cognitive 100): DataSourceV2Strategy.apply has cognitive complexity 100 (threshold 15). Drivers by points: if/else 38 (56 pts), match/switch 19 (38 pts), boolean chains 6 (nesting depth added 37). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c3a2263bb89f0bc8c8dd5c7f37b3618d62f48738fc84526cd8c62190e94b8d1"}},{"ruleId":"D2","level":"warning","message":{"text":"namespace.read_csv (cognitive 100): namespace.read_csv has cognitive complexity 100 (threshold 15). Drivers by points: if/else 39 (83 pts), loops 3 (8 pts), boolean chains 5, ternaries 2 (4 pts) (nesting depth added 51). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"02cf6815a11f02e42e8417733b2624e51e632388d01159522b01c6c7ecd5401b"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.next (cognitive 99): ShuffleBlockFetcherIterator.next has cognitive complexity 99 (threshold 15). Drivers by points: if/else 27 (76 pts), error handling 3 (11 pts), match/switch 2 (7 pts), boolean chains 4, loops 1 (nesting depth added 62). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":808}}}],"partialFingerprints":{"codehealthFindingId/v1":"839b9b69bdc4df6fc9636073941134bf71854c9ad42d9a45d234885e971c9426"}},{"ruleId":"D2","level":"warning","message":{"text":"MLExpressionUtils.scaleShift (cognitive 94): MLExpressionUtils.scaleShift has cognitive complexity 94 (threshold 15). Drivers by points: loops 15 (49 pts), if/else 25 (33 pts), boolean chains 6, ternaries 4 (6 pts) (nesting depth added 44). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3ed6697b23b249136fb71cb1dca379fad8a7a462733d18911f807e533085333"}},{"ruleId":"D2","level":"warning","message":{"text":"SqlStatementSplitter.splitWithPositions (cognitive 92): SqlStatementSplitter.splitWithPositions has cognitive complexity 92 (threshold 15). Drivers by points: if/else 22 (59 pts), loops 8 (23 pts), boolean chains 6, match/switch 1 (4 pts) (nesting depth added 55). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"007c4c400f22860807aa6f93269be626bc45d5bd8bcc944a4e73d7ae3624563d"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSchedulerImpl.resourceOffers (cognitive 91): TaskSchedulerImpl.resourceOffers has cognitive complexity 91 (threshold 15). Drivers by points: if/else 25 (71 pts), loops 6 (11 pts), boolean chains 5, match/switch 1 (4 pts) (nesting depth added 54). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":573}}}],"partialFingerprints":{"codehealthFindingId/v1":"635eb8ca222960111a98d987c08e57aa4883c8209ac1598dcb261cb26338920f"}},{"ruleId":"D2","level":"warning","message":{"text":"Decimal.changePrecision (cognitive 89): Decimal.changePrecision has cognitive complexity 89 (threshold 15). Drivers by points: if/else 29 (75 pts), match/switch 2 (8 pts), boolean chains 6 (nesting depth added 52). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c1db47885f86fd1023e72c94ca857df6f73a00cf2119422567cba682ad962b8"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ExpressionBuilder.generateExpression (cognitive 89): V2ExpressionBuilder.generateExpression has cognitive complexity 89 (threshold 15). Drivers by points: if/else 40 (60 pts), match/switch 7 (15 pts), boolean chains 14 (nesting depth added 28). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ded0f2cd064946151d243406848273113a66d92e5b6a17f2b0a007847920f32"}},{"ruleId":"D2","level":"warning","message":{"text":"namespace.concat (cognitive 87): namespace.concat has cognitive complexity 87 (threshold 15). Drivers by points: if/else 39 (66 pts), loops 7 (13 pts), boolean chains 4, ternaries 2 (4 pts) (nesting depth added 35). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2380}}}],"partialFingerprints":{"codehealthFindingId/v1":"f137bd56190e1a2277b9d41907596361ea8f642c52752e83b1f356cf755ae84e"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.toSqlTypeHelper (cognitive 86): SchemaConverters.toSqlTypeHelper has cognitive complexity 86 (threshold 15). Drivers by points: if/else 39 (74 pts), match/switch 5 (10 pts), boolean chains 2 (nesting depth added 40). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"fecefe4cee1abd94fd61b41fbbb89129d13a1141d1b1a8ac79e8148a24d27230"}},{"ruleId":"D2","level":"warning","message":{"text":"AvroDeserializer.newWriter (cognitive 85): AvroDeserializer.newWriter has cognitive complexity 85 (threshold 15). Drivers by points: if/else 25 (41 pts), match/switch 12 (34 pts), boolean chains 6, loops 2 (4 pts) (nesting depth added 40). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbf34ecda9728358e1865fd8c5c89b1991b2f3152031f47e08be7198306dc883"}},{"ruleId":"D2","level":"warning","message":{"text":"daemon.manager (cognitive 82): daemon.manager has cognitive complexity 82 (threshold 15). Drivers by points: if/else 20 (45 pts), error handling 6 (22 pts), loops 4 (14 pts), boolean chains 1 (nesting depth added 51). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/daemon.py"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"182f35c7101a146bcd8a6d3848092511bb87acc9f1d2203291341a925e052e86"}},{"ruleId":"D2","level":"warning","message":{"text":"JacksonParser.makeConverter (cognitive 81): JacksonParser.makeConverter has cognitive complexity 81 (threshold 15). Drivers by points: match/switch 27 (57 pts), if/else 8 (14 pts), error handling 3 (10 pts) (nesting depth added 43). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1f7976c2818216a233345a4e619f46bc628f22864e31d66087ea9332e1f0af9"}},{"ruleId":"D2","level":"warning","message":{"text":"CatalystTranspiler._convert_chunk (cognitive 80): CatalystTranspiler._convert_chunk has cognitive complexity 80 (threshold 15). Drivers by points: if/else 22 (51 pts), boolean chains 11, ternaries 3 (7 pts), loops 2 (6 pts), match/switch 3 (5 pts) (nesting depth added 39). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ff47ec271e0ec797107d3db9cc10e8fc1c222c2b872789922b32c1c40ae1174"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 79): (anonymous) has cognitive complexity 79 (threshold 15). Drivers by points: if/else 53 (64 pts), ternaries 10 (12 pts), boolean chains 3 (nesting depth added 13). None of this is in the body itself: all 79 points belong to 33 function items inside it that branch ((anonymous)::(anonymous)::(anonymous)::data, (anonymous)::(anonymous)::(anonymous)::data, (anonymous)::(anonymous)::(anonymous)::data, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"b74503957cd1064c3f287fe3f920ce940e4ee36efc673135a29667d3b34fd953"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.filter (cognitive 78): DataFrame.filter has cognitive complexity 78 (threshold 15). Drivers by points: if/else 27 (63 pts), loops 4 (15 pts) (nesting depth added 47). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11965}}}],"partialFingerprints":{"codehealthFindingId/v1":"975d236c0072cb0a6115f6a763b5126605db45ec61c59e546f73b9413ea19154"}},{"ruleId":"D2","level":"warning","message":{"text":"Series.replace (cognitive 77): Series.replace has cognitive complexity 77 (threshold 15). Drivers by points: if/else 28 (55 pts), ternaries 5 (15 pts), boolean chains 4, loops 1 (3 pts) (nesting depth added 39). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5089}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7adf7ca13bc4d8abed9f687e7a9737edad9e2340760d16e898173981c8db727"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantShreddingWriter.tryTypedShred (cognitive 76): VariantShreddingWriter.tryTypedShred has cognitive complexity 76 (threshold 15). Drivers by points: if/else 24 (65 pts), match/switch 3 (7 pts), boolean chains 4 (nesting depth added 45). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantShreddingWriter.java"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"855e2d6461777e2cda28c3d6a38d149e7a72618a0b6b16ff05af034c5eda442c"}},{"ruleId":"D2","level":"warning","message":{"text":"WeightedLeastSquares.fit (cognitive 75): WeightedLeastSquares.fit has cognitive complexity 75 (threshold 15). Drivers by points: if/else 36 (58 pts), boolean chains 7, loops 6 (7 pts), error handling 1 (2 pts), match/switch 1 (nesting depth added 24). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"8440ebe8f12484296083f92dedaf28bee55fcb2aacf0b996c2346b4c80f79053"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.drop (cognitive 75): DataFrame.drop has cognitive complexity 75 (threshold 15). Drivers by points: if/else 24 (64 pts), ternaries 2 (8 pts), boolean chains 3 (nesting depth added 46). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7749}}}],"partialFingerprints":{"codehealthFindingId/v1":"4820d0319213fe5dedccb5ac56646ab3c56dbf843e717433238f18d6c588867e"}},{"ruleId":"D2","level":"warning","message":{"text":"LocIndexer._select_rows_by_slice (cognitive 75): LocIndexer._select_rows_by_slice has cognitive complexity 75 (threshold 15). Drivers by points: if/else 24 (55 pts), ternaries 4 (8 pts), boolean chains 6, loops 2 (6 pts) (nesting depth added 39). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1064}}}],"partialFingerprints":{"codehealthFindingId/v1":"96a02139e587b6bc1216f214f4e163ce8372e3b1d180ba3c39459c27d08bde41"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkIntervalUtils.stringToInterval (cognitive 72): SparkIntervalUtils.stringToInterval has cognitive complexity 72 (threshold 15). Drivers by points: if/else 26 (42 pts), match/switch 6 (15 pts), boolean chains 7, error handling 2 (7 pts), loops 1 (nesting depth added 30). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkIntervalUtils.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3b854bfecc8a32b2fe10b1620b0fc34cd72afd589cf48f601e385635a53b6fc"}},{"ruleId":"D2","level":"warning","message":{"text":"MultiColumnInSubqueryEvaluator.eval (cognitive 72): MultiColumnInSubqueryEvaluator.eval has cognitive complexity 72 (threshold 15). Drivers by points: if/else 23 (47 pts), loops 6 (15 pts), boolean chains 10 (nesting depth added 33). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"370261a062385d1a61527e3230ee9c53d7237c3dc295c4f0205743d3e5cf3e10"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSQLCLIDriver.processCmd (cognitive 72): SparkSQLCLIDriver.processCmd has cognitive complexity 72 (threshold 15). Drivers by points: if/else 15 (37 pts), match/switch 3 (16 pts), error handling 2 (8 pts), boolean chains 7, loops 1 (4 pts) (nesting depth added 44). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala"},"region":{"startLine":442}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ec1329163f78a1dbe251f24f48f565e41e97c46b28e56b06669f97a9fa13a03"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.melt (cognitive 72): DataFrame.melt has cognitive complexity 72 (threshold 15). Drivers by points: if/else 30 (49 pts), ternaries 8 (21 pts), boolean chains 2 (nesting depth added 32). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10853}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b52d27b21da8a9e2828d13f8d54fd94d37999e9f5258133e46209b590616206"}},{"ruleId":"D2","level":"warning","message":{"text":"ToStringBase.castToStringDefault (cognitive 71): ToStringBase.castToStringDefault has cognitive complexity 71 (threshold 15). Drivers by points: if/else 22 (61 pts), loops 3 (9 pts), match/switch 1 (nesting depth added 45). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ToStringBase.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ad3230160a9c0471705942e5810eb867f46a880f724cafeb55b11ab25f38c45"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeJoinEvaluator.eval (cognitive 71): SortMergeJoinEvaluator.eval has cognitive complexity 71 (threshold 15). Drivers by points: if/else 15 (46 pts), loops 7 (19 pts), boolean chains 5, match/switch 1 (nesting depth added 43). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"68366ab21454cdab2b3e615ad00295a55f146a0e6a7469194c2b5f84356df087"}},{"ruleId":"D2","level":"warning","message":{"text":"DataTypeAstBuilder.visitPrimitiveDataType (cognitive 70): DataTypeAstBuilder.visitPrimitiveDataType has cognitive complexity 70 (threshold 15). Drivers by points: if/else 29 (50 pts), match/switch 7 (20 pts) (nesting depth added 34). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"27d45020bd86f40a7112b26cddf7674e556de9535cbfb98f512a2768ce2021c1"}},{"ruleId":"D2","level":"warning","message":{"text":"StringRegexExpression.scanQuantifiers (cognitive 69): StringRegexExpression.scanQuantifiers has cognitive complexity 69 (threshold 15). Drivers by points: if/else 22 (49 pts), boolean chains 12, match/switch 3 (6 pts), loops 2 (nesting depth added 30). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"33d285ed5961550fae71557f615e080d2ac5a209eeaabe0a0d18157298f96c87"}},{"ruleId":"D2","level":"warning","message":{"text":"functions._validate_and_transform_prediction_result (cognitive 69): functions._validate_and_transform_prediction_result has cognitive complexity 69 (threshold 15). Drivers by points: if/else 22 (58 pts), loops 2 (6 pts), boolean chains 3, ternaries 1 (2 pts) (nesting depth added 41). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/functions.py"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9ed0876cf8f9c26db81d730c1452682ac7adf40eb56298624a24606579a8571"}},{"ruleId":"D2","level":"warning","message":{"text":"namespace.merge_asof (cognitive 69): namespace.merge_asof has cognitive complexity 69 (threshold 15). Drivers by points: if/else 34 (56 pts), boolean chains 11, loops 2 (nesting depth added 22). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":3110}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c4c5658e06b2c9817c4549fb2b48fb5d9e050a370a869cdb7c1eeccb2625552"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.merge (cognitive 68): DataFrame.merge has cognitive complexity 68 (threshold 15). Drivers by points: if/else 31 (54 pts), boolean chains 8, loops 3 (6 pts) (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8812}}}],"partialFingerprints":{"codehealthFindingId/v1":"624750063e1e0b671caaf0e5e6160f918626b28030f37d5eebfd1f775444391f"}},{"ruleId":"D2","level":"warning","message":{"text":"namespace.get_dummies (cognitive 67): namespace.get_dummies has cognitive complexity 67 (threshold 15). Drivers by points: if/else 24 (47 pts), ternaries 4 (13 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 33). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2153}}}],"partialFingerprints":{"codehealthFindingId/v1":"0915ecb223554ca6a1a55cba10973265fd1ad1d06a54a598b6e59afb312c9c6f"}},{"ruleId":"D2","level":"warning","message":{"text":"StateSourceOptions.apply (cognitive 66): StateSourceOptions.apply has cognitive complexity 66 (threshold 15). Drivers by points: if/else 38 (57 pts), boolean chains 5, error handling 4 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"91b027fe773d0c9ae140d3f44f5e7ed626ac1c8acfc6abe0710f96cedf1a9072"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkResult.processResponses (cognitive 65): SparkResult.processResponses has cognitive complexity 65 (threshold 15). Drivers by points: if/else 19 (53 pts), loops 2 (5 pts), match/switch 1 (5 pts), boolean chains 2 (nesting depth added 41). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkResult.scala"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"735a6583f1dd7cc7e33c6d590f292a5037724a2f007f9c266c4bfdf05046d3c5"}},{"ruleId":"D2","level":"warning","message":{"text":"AbstractCommandBuilder.buildClassPath (cognitive 65): AbstractCommandBuilder.buildClassPath has cognitive complexity 65 (threshold 15). Drivers by points: if/else 15 (40 pts), boolean chains 14, loops 4 (11 pts) (nesting depth added 32). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/AbstractCommandBuilder.java"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"209cd39e20098816834a0041bd919e24950f5d4cad17c4c8fc6550a9c0e7cc63"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupBy.apply (cognitive 65): GroupBy.apply has cognitive complexity 65 (threshold 15). Drivers by points: if/else 38 (60 pts), boolean chains 2, ternaries 1 (2 pts), error handling 1 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1818}}}],"partialFingerprints":{"codehealthFindingId/v1":"096e233e2b7b7f6bc3438273a4b1a09b1541228c55c6893ba3c68a5b28b281b8"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.withPredicate (cognitive 63): AstBuilder.withPredicate has cognitive complexity 63 (threshold 15). Drivers by points: if/else 23 (35 pts), match/switch 12 (24 pts), boolean chains 4 (nesting depth added 24). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":3861}}}],"partialFingerprints":{"codehealthFindingId/v1":"85d963fba894f083bdb4c6ea11d4ffb8e2e10fbc5a3aa4f82e651144bc564d50"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.xs (cognitive 63): DataFrame.xs has cognitive complexity 63 (threshold 15). Drivers by points: if/else 29 (50 pts), ternaries 3 (7 pts), error handling 2 (5 pts), boolean chains 1 (nesting depth added 28). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3589}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a2f1315d7d9685362e94558fe66ad1c707e66ffa2ed37822f08d6351acd5ae7"}},{"ruleId":"D2","level":"warning","message":{"text":"LocIndexerLike.__getitem__ (cognitive 63): LocIndexerLike.__getitem__ has cognitive complexity 63 (threshold 15). Drivers by points: if/else 31 (49 pts), boolean chains 9, loops 1 (2 pts), ternaries 1 (2 pts), error handling 1 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":439}}}],"partialFingerprints":{"codehealthFindingId/v1":"6942d19c17af70ca60d155be2ee173979e8017a4b593438ff8cc196b3d965c11"}},{"ruleId":"D2","level":"warning","message":{"text":"InternalFrame.__init__ (cognitive 63): InternalFrame.__init__ has cognitive complexity 63 (threshold 15). Drivers by points: if/else 28 (41 pts), ternaries 6 (12 pts), boolean chains 10 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"37ec290347760c663c7200051510f0920a050eb0ac44303521f1dccb9c3b1ab2"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveReferences.doApply (cognitive 62): ResolveReferences.doApply has cognitive complexity 62 (threshold 15). Drivers by points: if/else 20 (33 pts), match/switch 8 (18 pts), boolean chains 11 (nesting depth added 23). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1653}}}],"partialFingerprints":{"codehealthFindingId/v1":"94d3c0d763102e264074dc14c5b8c693b302924ef7cc1197c01d71ea1ed28762"}},{"ruleId":"D2","level":"warning","message":{"text":"StarSchemaDetection.findStarJoins (cognitive 61): StarSchemaDetection.findStarJoins has cognitive complexity 61 (threshold 15). Drivers by points: if/else 17 (38 pts), match/switch 6 (21 pts), boolean chains 2 (nesting depth added 36). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/StarSchemaDetection.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6a883efcf49e4f2fe64d93f3acec407219a77e4d912d023feba3d931eb1d6d"}},{"ruleId":"D2","level":"warning","message":{"text":"ShreddingUtils.rebuild (cognitive 60): ShreddingUtils.rebuild has cognitive complexity 60 (threshold 15). Drivers by points: if/else 22 (40 pts), loops 3 (10 pts), boolean chains 6, match/switch 1 (4 pts) (nesting depth added 28). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/ShreddingUtils.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e8845810b4d380a2ca2bc492e522272a963da4640891419d971b001970085c7"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorizedRleValuesReader.readBatchRepeatedInternal (cognitive 60): VectorizedRleValuesReader.readBatchRepeatedInternal has cognitive complexity 60 (threshold 15). Drivers by points: if/else 18 (52 pts), loops 2 (4 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 37). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca32c1266ba7b99d37e6d10e47cd49720b387cebb4dc97d04c26e94e3bcf7563"}},{"ruleId":"D2","level":"warning","message":{"text":"pandasutils._assert_pandas_almost_equal (cognitive 60): pandasutils._assert_pandas_almost_equal has cognitive complexity 60 (threshold 15). Drivers by points: if/else 14 (37 pts), loops 8 (18 pts), boolean chains 5 (nesting depth added 33). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cf5fb3b15960103ee7d422851ea95017b42c05283ca623f1dbdda334a5b3e6f"}},{"ruleId":"D2","level":"warning","message":{"text":"ValidateSubqueryExpression.apply (cognitive 59): ValidateSubqueryExpression.apply has cognitive complexity 59 (threshold 15). Drivers by points: if/else 21 (35 pts), match/switch 10 (21 pts), boolean chains 3 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ValidateSubqueryExpression.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"565a59df60d0ec19f03a454f0d66267c9c968c956d4df080e434dc91cdeb16c1"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetToSparkSchemaConverter.convertPrimitiveField (cognitive 59): ParquetToSparkSchemaConverter.convertPrimitiveField has cognitive complexity 59 (threshold 15). Drivers by points: if/else 20 (27 pts), match/switch 10 (22 pts), boolean chains 10 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"145d68e2374251a58bf703341112b8cd5fb86e228e3911c764ee37c80d947f56"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSQLCLIDriver.main (cognitive 59): SparkSQLCLIDriver.main has cognitive complexity 59 (threshold 15). Drivers by points: if/else 27 (49 pts), error handling 3 (4 pts), boolean chains 3, loops 2, match/switch 1 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"01f4dafb0a6d193b8962fd362f76283d034c407576d716dd6859455dd5c05ca2"}},{"ruleId":"D2","level":"warning","message":{"text":"OnHeapColumnVector.reserveInternal (cognitive 59): OnHeapColumnVector.reserveInternal has cognitive complexity 59 (threshold 15). Drivers by points: if/else 27 (49 pts), boolean chains 10 (nesting depth added 22). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9482a6dc8eb8e3e0f2c6571a3726bc2228d86b9f6db46acdd8c85079c8627a1"}},{"ruleId":"D2","level":"warning","message":{"text":"Resampler._bin_timestamp (cognitive 59): Resampler._bin_timestamp has cognitive complexity 59 (threshold 15). Drivers by points: if/else 23 (38 pts), boolean chains 15, ternaries 3 (6 pts) (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/resample.py"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"9714ed3f55a4da08771dfc338b6e5a0d4af5612cadb24e7bb94ae827e0aada63"}},{"ruleId":"D2","level":"warning","message":{"text":"Master.receive (cognitive 58): Master.receive has cognitive complexity 58 (threshold 15). Drivers by points: if/else 15 (31 pts), match/switch 7 (13 pts), loops 4 (12 pts), boolean chains 2 (nesting depth added 30). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b975f9ce4ef856897eb685e30ad2e9481a8c095c428b19579bbdc16d85ac79d"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemmImpl (cognitive 58): BLAS.gemmImpl has cognitive complexity 58 (threshold 15). Drivers by points: loops 12 (48 pts), if/else 7 (10 pts) (nesting depth added 39). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":523}}}],"partialFingerprints":{"codehealthFindingId/v1":"987e799c227af96d08f40861fe1ecc6510cba0fda197b2415b157b9204a587d8"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemm (cognitive 58): BLAS.gemm has cognitive complexity 58 (threshold 15). Drivers by points: loops 12 (48 pts), if/else 7 (10 pts) (nesting depth added 39). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8d53b265c599383bf4187c334c55a67f0e8355d36a9b48acc84b733200f24a3"}},{"ruleId":"D2","level":"warning","message":{"text":"MLHandler._handleMlCommand (cognitive 58): MLHandler._handleMlCommand has cognitive complexity 58 (threshold 15). Drivers by points: if/else 22 (31 pts), match/switch 8 (23 pts), error handling 1 (3 pts), boolean chains 1 (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/MLHandler.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"ded3e87c9afccd19adb860ec6cc38b92111a3e9a1732d7a12b517f70ed131562"}},{"ruleId":"D2","level":"warning","message":{"text":"DataflowGraphTransformer.transformDownNodes (cognitive 58): DataflowGraphTransformer.transformDownNodes has cognitive complexity 58 (threshold 15). Drivers by points: if/else 15 (31 pts), match/switch 2 (12 pts), error handling 4 (10 pts), loops 2 (3 pts), boolean chains 2 (nesting depth added 33). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/DataflowGraphTransformer.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"81c566c102d96437b65dfc9906f1ab5b1856f95e47f6c8b85288de49857e16ee"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantGet.cast (cognitive 57): VariantGet.cast has cognitive complexity 57 (threshold 15). Drivers by points: if/else 22 (33 pts), loops 3 (9 pts), match/switch 4 (9 pts), error handling 2 (6 pts) (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":763}}}],"partialFingerprints":{"codehealthFindingId/v1":"c810b570825d0e539b6ee020d1671a15f25d4986d281c36a9b0038c67876b28d"}},{"ruleId":"D2","level":"warning","message":{"text":"Master.receiveAndReply (cognitive 56): Master.receiveAndReply has cognitive complexity 56 (threshold 15). Drivers by points: if/else 21 (46 pts), match/switch 4 (9 pts), boolean chains 1 (nesting depth added 30). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"4073b0de51b6466a1cf7ce10726289c5f3e9b69269ddf87f0fc0f525393ed193"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonTableEvaluator.anyMatch (cognitive 56): JsonTableEvaluator.anyMatch has cognitive complexity 56 (threshold 15). Drivers by points: if/else 15 (34 pts), loops 3 (9 pts), match/switch 5 (9 pts), boolean chains 4 (nesting depth added 29). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":880}}}],"partialFingerprints":{"codehealthFindingId/v1":"77728f2b579279397845ba7a83db19587330e4b6c6b4bcf3fc9618516e8b7a0a"}},{"ruleId":"D2","level":"warning","message":{"text":"BufferSetterGetterUtils.createGetters (cognitive 56): BufferSetterGetterUtils.createGetters has cognitive complexity 56 (threshold 15). Drivers by points: if/else 27 (53 pts), match/switch 1 (2 pts), loops 1 (nesting depth added 27). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb2f3862caee0e09b615339f62fb8b28a92362b4afca4efe558c3877d28b1854"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ScanRelationPushDown.rewriteAggregate (cognitive 56): V2ScanRelationPushDown.rewriteAggregate has cognitive complexity 56 (threshold 15). Drivers by points: if/else 17 (29 pts), match/switch 8 (26 pts), boolean chains 1 (nesting depth added 30). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":642}}}],"partialFingerprints":{"codehealthFindingId/v1":"36c8d661245841d26beb4585e112158f52eb10a6e019cdcf240f34a4bc5a8b02"}},{"ruleId":"D2","level":"warning","message":{"text":"LocIndexer._select_cols_by_iterable (cognitive 56): LocIndexer._select_cols_by_iterable has cognitive complexity 56 (threshold 15). Drivers by points: if/else 18 (43 pts), loops 2 (5 pts), boolean chains 4, ternaries 1 (4 pts) (nesting depth added 31). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1346}}}],"partialFingerprints":{"codehealthFindingId/v1":"d58864d56bc4952897cb5cd8b0fc9222bef1014f2c6d1207a9dd8c4eb49539b8"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasOnSparkBoxPlot.boxplot (cognitive 56): PandasOnSparkBoxPlot.boxplot has cognitive complexity 56 (threshold 15). Drivers by points: if/else 22 (49 pts), loops 2 (6 pts), boolean chains 1 (nesting depth added 31). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8ab26765dd1845ccd97bf001f22d5baca1e44c9e9348d03e276bfc29fc79f87"}},{"ruleId":"D2","level":"warning","message":{"text":"CatalystTranspiler._category_uncached (cognitive 56): CatalystTranspiler._category_uncached has cognitive complexity 56 (threshold 15). Drivers by points: if/else 21 (46 pts), boolean chains 7, ternaries 1 (2 pts), match/switch 1 (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":598}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4223b078caf47dd5166b043a7ee1dbd398b326ad53ca6ad0592704d3893f390"}},{"ruleId":"D2","level":"warning","message":{"text":"SummarizerBuffer.merge (cognitive 55): SummarizerBuffer.merge has cognitive complexity 55 (threshold 15). Drivers by points: if/else 19 (51 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 33). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":590}}}],"partialFingerprints":{"codehealthFindingId/v1":"65d10f747fc9e2334003d1623fe6f03a69893f1b622d2a48b47b39570d64ab4b"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveWithCTE.resolveWithCTE (cognitive 55): ResolveWithCTE.resolveWithCTE has cognitive complexity 55 (threshold 15). Drivers by points: if/else 20 (46 pts), match/switch 4 (8 pts), boolean chains 1 (nesting depth added 30). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"eac9c847d7f694c9ff312819060da5ca8bb9bf210466681738e4c808140ec6da"}},{"ruleId":"D2","level":"warning","message":{"text":"WritableColumnVector.appendObjects (cognitive 55): WritableColumnVector.appendObjects has cognitive complexity 55 (threshold 15). Drivers by points: if/else 19 (32 pts), loops 9 (23 pts) (nesting depth added 27). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"37df9186fe2c0fa5c186518d4b6d4cf8544b1d946c2ff02b93a147bb76706fce"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveFunctionRegistryUtils.getMethodInternal (cognitive 55): HiveFunctionRegistryUtils.getMethodInternal has cognitive complexity 55 (threshold 15). Drivers by points: if/else 18 (38 pts), loops 4 (8 pts), ternaries 2 (7 pts), boolean chains 2 (nesting depth added 29). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/HiveFunctionRegistryUtils.java"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"e421a57ea6ebadb1cb69d4b13d75ead3e9b61c6db42254045845f71b5569f8fd"}},{"ruleId":"D2","level":"warning","message":{"text":"types._parse_datatype_json_value (cognitive 55): types._parse_datatype_json_value has cognitive complexity 55 (threshold 15). Drivers by points: if/else 21 (49 pts), boolean chains 5, ternaries 1 (nesting depth added 28). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2674}}}],"partialFingerprints":{"codehealthFindingId/v1":"39f1b4813cdd84e437eccfaa6e6e1f29108aea5fab553f9ba7e11480728f6390"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.structFieldFor (cognitive 54): SchemaConverters.structFieldFor has cognitive complexity 54 (threshold 15). Drivers by points: if/else 18 (27 pts), boolean chains 18, match/switch 5 (9 pts) (nesting depth added 13). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"748357fcdbfaaeaf72cc389f4c0173f0ff0527c3017426d62298829d7cca1955"}},{"ruleId":"D2","level":"warning","message":{"text":"DeduplicateRelations.deduplicate (cognitive 54): DeduplicateRelations.deduplicate has cognitive complexity 54 (threshold 15). Drivers by points: match/switch 6 (30 pts), if/else 11 (21 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 35). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"da1a983674d22c4eefb4f97d025c606043aa2b56622eccf2c730fa9a2b7dffca"}},{"ruleId":"D2","level":"warning","message":{"text":"PropagateEmptyRelationBase.commonApplyFunc (cognitive 54): PropagateEmptyRelationBase.commonApplyFunc has cognitive complexity 54 (threshold 15). Drivers by points: if/else 19 (34 pts), boolean chains 12, match/switch 4 (8 pts) (nesting depth added 19). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PropagateEmptyRelation.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f26dc17ddc9967cf9835f8b953cc39bf9d07323a2006b326750a6c0f9e4b26b"}},{"ruleId":"D2","level":"warning","message":{"text":"CreateSQLFunctionCommand.run (cognitive 54): CreateSQLFunctionCommand.run has cognitive complexity 54 (threshold 15). Drivers by points: if/else 28 (37 pts), match/switch 6 (14 pts), boolean chains 3 (nesting depth added 17). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"52909696f167bcb1e49ca9b923650da8152de1e4498b6013556cf4e7ebc0deeb"}},{"ruleId":"D2","level":"warning","message":{"text":"EnsureRequirements.checkKeyGroupCompatible (cognitive 54): EnsureRequirements.checkKeyGroupCompatible has cognitive complexity 54 (threshold 15). Drivers by points: if/else 24 (33 pts), boolean chains 16, loops 2 (3 pts), match/switch 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeb75cb2310077087a3721f330b482d868e5e24c2e7a354518c594c231420963"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.main (cognitive 54): merge_spark_pr.main has cognitive complexity 54 (threshold 15). Drivers by points: if/else 27 (43 pts), loops 4 (6 pts), boolean chains 4, ternaries 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3353}}}],"partialFingerprints":{"codehealthFindingId/v1":"622528e75dceda1a08cfd8bc5a582da6104f5bbead2b88c84b760642de5ba009"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.pivot_table (cognitive 54): DataFrame.pivot_table has cognitive complexity 54 (threshold 15). Drivers by points: if/else 27 (36 pts), boolean chains 8, ternaries 4 (8 pts), loops 1 (2 pts) (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6942}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cb7b6b067881b8350148d696a63fc9fbbf1141db843a28aef5cd923750b80dd"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkParserUtils.unescapeSQLString (cognitive 53): SparkParserUtils.unescapeSQLString has cognitive complexity 53 (threshold 15). Drivers by points: if/else 17 (33 pts), boolean chains 16, loops 2 (3 pts), match/switch 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkParserUtils.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a7455a06b7afbeab9319bec1bca4e525e72a6cf699014ee4a3c87d6162380cf"}},{"ruleId":"D2","level":"warning","message":{"text":"FilterEstimation.evaluateBinaryForTwoColumns (cognitive 53): FilterEstimation.evaluateBinaryForTwoColumns has cognitive complexity 53 (threshold 15). Drivers by points: if/else 17 (38 pts), boolean chains 10, match/switch 3 (5 pts) (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"49e7afe958213460b7e429ac1d2aac53d8e6740e923e3ece254de6717b9b3fb9"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveSessionCatalog.apply (cognitive 53): ResolveSessionCatalog.apply has cognitive complexity 53 (threshold 15). Drivers by points: if/else 23 (32 pts), match/switch 7 (13 pts), boolean chains 8 (nesting depth added 15). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2be790e98bc299c35d29163e3b48c080c30c3b5a97f71aa523df6211d37588a"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.reset_index (cognitive 53): DataFrame.reset_index has cognitive complexity 53 (threshold 15). Drivers by points: if/else 17 (30 pts), loops 4 (9 pts), ternaries 3 (8 pts), error handling 1 (4 pts), boolean chains 2 (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4472}}}],"partialFingerprints":{"codehealthFindingId/v1":"85372f4114ffbc000e03009e664933165799650975483da44de11ec0c4ed393b"}},{"ruleId":"D2","level":"warning","message":{"text":"types._infer_type (cognitive 53): types._infer_type has cognitive complexity 53 (threshold 15). Drivers by points: if/else 22 (39 pts), loops 3 (9 pts), boolean chains 3, error handling 1 (2 pts) (nesting depth added 24). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2994}}}],"partialFingerprints":{"codehealthFindingId/v1":"941802ca39cea48c07e78b063dd7d1d9891d2f1ec30eaca74db7afbff1f02ade"}},{"ruleId":"D2","level":"warning","message":{"text":"BufferSetterGetterUtils.createSetters (cognitive 52): BufferSetterGetterUtils.createSetters has cognitive complexity 52 (threshold 15). Drivers by points: if/else 25 (49 pts), match/switch 1 (2 pts), loops 1 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"530ea1bf593c5898970a16a05abdd494b15a512bcc3219a2cb32b67df8e2b175"}},{"ruleId":"D2","level":"warning","message":{"text":"StringSubstitutor.substitute (cognitive 51): StringSubstitutor.substitute has cognitive complexity 51 (threshold 15). Drivers by points: if/else 13 (39 pts), match/switch 2 (9 pts), boolean chains 2, loops 1 (nesting depth added 33). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/StringSubstitutor.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"a80ff70ed8336b0b567a410ed98a15c7a0649307b06f68a040c343ad457189cf"}},{"ruleId":"D2","level":"warning","message":{"text":"Writer.open (cognitive 51): Writer.open has cognitive complexity 51 (threshold 15). Drivers by points: if/else 21 (40 pts), error handling 2 (4 pts), match/switch 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 24). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":966}}}],"partialFingerprints":{"codehealthFindingId/v1":"6bb6d1e871a2a19fe842610b356d5ede0790acce1123340a0ddb52f1ae15db8e"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveReferences.expandStarExpression (cognitive 51): ResolveReferences.expandStarExpression has cognitive complexity 51 (threshold 15). Drivers by points: match/switch 12 (29 pts), if/else 14 (20 pts), boolean chains 2 (nesting depth added 23). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2117}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d8369cec081eeef60403c3e9afd2e31b20289f64afcc319ebda155ebcca6619"}},{"ruleId":"D2","level":"warning","message":{"text":"RelationResolution.tryResolvePersistent (cognitive 51): RelationResolution.tryResolvePersistent has cognitive complexity 51 (threshold 15). Drivers by points: if/else 14 (23 pts), match/switch 4 (9 pts), error handling 2 (8 pts), boolean chains 6, loops 2 (5 pts) (nesting depth added 23). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"305272ae067d24fe4fdbcc8be7a3af54421bf3a7827dd3df9e8fc722f9aa6745"}},{"ruleId":"D2","level":"warning","message":{"text":"StateStore.submitMaintenanceWorkForProvider (cognitive 51): StateStore.submitMaintenanceWorkForProvider has cognitive complexity 51 (threshold 15). Drivers by points: if/else 16 (35 pts), match/switch 6 (14 pts), boolean chains 1, error handling 1 (nesting depth added 27). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala"},"region":{"startLine":2037}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cc05519967efb00388b777a221f4945853301e01595de516f3c36edc1f9ec89"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskMemoryManager.allocatePageInternal (cognitive 51): TaskMemoryManager.allocatePageInternal has cognitive complexity 51 (threshold 15). Drivers by points: if/else 18 (36 pts), ternaries 2 (9 pts), boolean chains 3, error handling 1 (2 pts), loops 1 (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":680}}}],"partialFingerprints":{"codehealthFindingId/v1":"3db164ed6fa92916df86e0958eaf49be5ba13353edd47b49bd88ce8d02142bd7"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.describe (cognitive 51): DataFrame.describe has cognitive complexity 51 (threshold 15). Drivers by points: if/else 14 (24 pts), loops 6 (13 pts), ternaries 3 (10 pts), boolean chains 4 (nesting depth added 24). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10024}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fcee081440a5b8c16bea28942d0b7e97d603024d7f5e4aa0d14f2cdf4790599"}},{"ruleId":"D2","level":"warning","message":{"text":"Client.prepareLocalResources (cognitive 50): Client.prepareLocalResources has cognitive complexity 50 (threshold 15). Drivers by points: if/else 29 (43 pts), match/switch 3 (5 pts), boolean chains 2 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":527}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c4f271647f85fd13fb6082ccafb3157e960b5031ff7d47abac37b59d4b4b386"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveFunctions.apply (cognitive 50): ResolveFunctions.apply has cognitive complexity 50 (threshold 15). Drivers by points: match/switch 11 (27 pts), if/else 13 (21 pts), boolean chains 2 (nesting depth added 24). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2420}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc0e651ee73eb1f4ba65d1cc15d9d0fc8b7f3de490db9241a493d5947355ca5"}},{"ruleId":"D2","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.evaluateStorageFilter (cognitive 50): LateMaterializationParquetRecordReader.evaluateStorageFilter has cognitive complexity 50 (threshold 15). Drivers by points: if/else 11 (34 pts), error handling 3 (9 pts), loops 4 (6 pts), boolean chains 1 (nesting depth added 31). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":708}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4529a0a50d5e7fb04073571fa5649c91e9995e4436d365cc8e46ee8647b04b8"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.submitMissingTasks (cognitive 49): DAGScheduler.submitMissingTasks has cognitive complexity 49 (threshold 15). Drivers by points: if/else 15 (25 pts), match/switch 10 (14 pts), boolean chains 5, error handling 5 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3215}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e95be10ec431cd16a01cb2a93b912638aca7696ff7227af86ee71bb7676eea4"}},{"ruleId":"D2","level":"warning","message":{"text":"JdbcUtils.savePartition (cognitive 49): JdbcUtils.savePartition has cognitive complexity 49 (threshold 15). Drivers by points: if/else 20 (32 pts), error handling 6 (13 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":657}}}],"partialFingerprints":{"codehealthFindingId/v1":"291bcdf54e241ae6ff51b032d39ffa30953bf66d2e3c4976d08ba070926cd10f"}},{"ruleId":"D2","level":"warning","message":{"text":"XSDToSchema.getStructField (cognitive 49): XSDToSchema.getStructField has cognitive complexity 49 (threshold 15). Drivers by points: match/switch 13 (40 pts), if/else 9 (nesting depth added 27). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"e42c2052cfc29e687ece5a4b01ab159e23e7da2e335979c4462cc6c17f371920"}},{"ruleId":"D2","level":"warning","message":{"text":"InProcessArrowEvalPythonEvaluatorFactory.evaluateBatches (cognitive 49): InProcessArrowEvalPythonEvaluatorFactory.evaluateBatches has cognitive complexity 49 (threshold 15). Drivers by points: if/else 33, boolean chains 9, error handling 3, match/switch 2 (3 pts), loops 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/InProcessArrowEvalPythonEvaluatorFactory.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"33a2825f45eb748251febd95c0d994d71351bea1a78f03b080bcefc5ae51bf9b"}},{"ruleId":"D2","level":"warning","message":{"text":"TransportResponseHandler.handle (cognitive 49): TransportResponseHandler.handle has cognitive complexity 49 (threshold 15). Drivers by points: if/else 24 (33 pts), error handling 4 (16 pts) (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportResponseHandler.java"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"54035156978e3f51d9c4c59702f5a886b3ec2e28a4ba3c1534d80a9e564c5756"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.dropna (cognitive 49): DataFrame.dropna has cognitive complexity 49 (threshold 15). Drivers by points: if/else 23 (43 pts), boolean chains 3, ternaries 1 (3 pts) (nesting depth added 22). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6099}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1508842bf3acc496252ca93b45eb0a37608bddb9442d59c670700fdcb43516c"}},{"ruleId":"D2","level":"warning","message":{"text":"Word2Vec.doFit (cognitive 48): Word2Vec.doFit has cognitive complexity 48 (threshold 15). Drivers by points: if/else 12 (32 pts), loops 5 (14 pts), boolean chains 2 (nesting depth added 29). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf64d9f798a78a2e0aa2076fc54c39476b2954729f16d67e134d3194977bf9b3"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkIntervalUtils.toDayTimeIntervalString (cognitive 48): SparkIntervalUtils.toDayTimeIntervalString has cognitive complexity 48 (threshold 15). Drivers by points: if/else 14 (25 pts), match/switch 6 (20 pts), boolean chains 3 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkIntervalUtils.scala"},"region":{"startLine":435}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ce8ff9fdf4bcb8104241d1b1842f50fba2399ca29fcbb9c2d35007066abc7cd"}},{"ruleId":"D2","level":"warning","message":{"text":"RewriteWithExpression.rewriteWithExprAndInputPlans (cognitive 48): RewriteWithExpression.rewriteWithExprAndInputPlans has cognitive complexity 48 (threshold 15). Drivers by points: if/else 15 (43 pts), match/switch 3 (5 pts) (nesting depth added 30). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteWithExpression.scala"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"090c29f54a16768a2998df2dd6bf9c91e5b01f9170eed8d962c94b50a305ca85"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveInspectors.wrapperFor (cognitive 48): HiveInspectors.wrapperFor has cognitive complexity 48 (threshold 15). Drivers by points: match/switch 13 (42 pts), if/else 6 (nesting depth added 29). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"88fca6ff29f41cb0cead263ef1062ab0bf2fb384765c6ddcbc3870ae17602980"}},{"ruleId":"D2","level":"warning","message":{"text":"SortState.mergeHi (cognitive 48): SortState.mergeHi has cognitive complexity 48 (threshold 15). Drivers by points: if/else 16 (39 pts), loops 3 (5 pts), boolean chains 3, ternaries 1 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SortState.mergeLo) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"3906028968639b5329e51b6ef5afeb4db9eb45836937803b468467ce023319e0"}},{"ruleId":"D2","level":"warning","message":{"text":"SortState.mergeLo (cognitive 48): SortState.mergeLo has cognitive complexity 48 (threshold 15). Drivers by points: if/else 16 (39 pts), loops 3 (5 pts), boolean chains 3, ternaries 1 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SortState.mergeHi) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":686}}}],"partialFingerprints":{"codehealthFindingId/v1":"0779c2bd34180c604d9e47c7857b9247dfcd468cc78472ac037a9a2d6e78f8ee"}},{"ruleId":"D2","level":"warning","message":{"text":"UserDefinedFunction._check_return_type (cognitive 48): UserDefinedFunction._check_return_type has cognitive complexity 48 (threshold 15). Drivers by points: error handling 10 (25 pts), if/else 12 (18 pts), boolean chains 5 (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":334}}}],"partialFingerprints":{"codehealthFindingId/v1":"4233309db953bc67aa5c0d46afe180efa09df413a1aadabff93c4c6e68851169"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegression.train (cognitive 47): LogisticRegression.train has cognitive complexity 47 (threshold 15). Drivers by points: if/else 29 (34 pts), boolean chains 11, match/switch 2 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2b1c652374f4f9b0f45f921cf1494eebe0ed678142dd72b6353d995f2958a18"}},{"ruleId":"D2","level":"warning","message":{"text":"BindParameters.apply (cognitive 47): BindParameters.apply has cognitive complexity 47 (threshold 15). Drivers by points: if/else 11 (21 pts), match/switch 8 (19 pts), boolean chains 7 (nesting depth added 21). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/parameters.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"58378b6b1b5d8f0b14a1efbb6aea02e16bed8d127bfd6ec0bc8fe32d869d2897"}},{"ruleId":"D2","level":"warning","message":{"text":"FileScanRDD.compute (cognitive 47): FileScanRDD.compute has cognitive complexity 47 (threshold 15). Drivers by points: if/else 15 (21 pts), error handling 5 (13 pts), match/switch 5 (8 pts), boolean chains 5 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8b8e06dc2da1cb9912869c479ae65e0cab14ea65a09e5e3de9b310d0f18b69f"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext._do_init (cognitive 47): SparkContext._do_init has cognitive complexity 47 (threshold 15). Drivers by points: if/else 22 (30 pts), loops 6 (9 pts), boolean chains 5, error handling 1 (3 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/context.py"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c67a52eb5d0cc78d7d8283c284efb9cb64390bca56c67771ba04b38e87956b2"}},{"ruleId":"D2","level":"warning","message":{"text":"AdaptiveSparkPlanExec.withFinalPlanUpdate (cognitive 46): AdaptiveSparkPlanExec.withFinalPlanUpdate has cognitive complexity 46 (threshold 15). Drivers by points: if/else 11 (27 pts), match/switch 4 (13 pts), error handling 1 (3 pts), boolean chains 2, loops 1 (nesting depth added 27). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f2eac0a6d21e9d6b3a1f2e9a12faa3c6eae7a342bfa173c39d03a57d7b4af59"}},{"ruleId":"D2","level":"warning","message":{"text":"TungstenAggregationIterator.processInputs (cognitive 46): TungstenAggregationIterator.processInputs has cognitive complexity 46 (threshold 15). Drivers by points: if/else 14 (39 pts), loops 2 (4 pts), boolean chains 3 (nesting depth added 27). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"c33be7bbc28ea42c281950a5db45ca94af222fed883e723a641ab087f69756a7"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints.as_spark_type (cognitive 46): typehints.as_spark_type has cognitive complexity 46 (threshold 15). Drivers by points: boolean chains 26, if/else 10 (18 pts), ternaries 1 (2 pts) (nesting depth added 9). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"a48dcf25a5b03823240c27b9a23746845e47e74a2ff84380d469d8b64216b387"}},{"ruleId":"D2","level":"warning","message":{"text":"RBackendHandler.findMatchedSignature (cognitive 45): RBackendHandler.findMatchedSignature has cognitive complexity 45 (threshold 15). Drivers by points: if/else 8 (26 pts), loops 3 (8 pts), match/switch 1 (6 pts), boolean chains 5 (nesting depth added 28). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8034e209a04340a57a9b35e8f0f4670f7171c7a246853177dfeee23d9e7d199"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSourceV2Relation.transformV2Stats (cognitive 45): DataSourceV2Relation.transformV2Stats has cognitive complexity 45 (threshold 15). Drivers by points: if/else 25 (33 pts), match/switch 4 (12 pts) (nesting depth added 16). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala"},"region":{"startLine":761}}}],"partialFingerprints":{"codehealthFindingId/v1":"143b5db0e43dddeaf37ad68f9793250c0cbcc8111a1a126146947b15362da3b7"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcSerializer.newConverter (cognitive 45): OrcSerializer.newConverter has cognitive complexity 45 (threshold 15). Drivers by points: if/else 22 (37 pts), loops 3 (7 pts), match/switch 1 (nesting depth added 19). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcSerializer.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f48c0b84a67fd511b7dc181544496e2c40967c73697181180276c350dd2f753"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.indexOf (cognitive 45): UTF8String.indexOf has cognitive complexity 45 (threshold 15). Drivers by points: if/else 13 (28 pts), loops 6 (14 pts), boolean chains 3 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1320}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc8c29061939a62c709545227ad4999a54fbdf8a452cb6c503e7cb7108632248"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasOnSparkTestUtils.assert_eq (cognitive 45): PandasOnSparkTestUtils.assert_eq has cognitive complexity 45 (threshold 15). Drivers by points: if/else 17 (35 pts), boolean chains 8, loops 1 (2 pts) (nesting depth added 19). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"8eb74bdbf9e0734956674ba0ae649703444a7bb14993cf113b57e4b0b6022e2c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext.addJar (cognitive 44): SparkContext.addJar has cognitive complexity 44 (threshold 15). Drivers by points: if/else 20 (36 pts), error handling 2 (3 pts), match/switch 1 (3 pts), boolean chains 2 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2479}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee72e73d4ea663571c55dd71745b2aa633e876cffff67945536731896c1a5cbf"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskRunner.run (cognitive 44): TaskRunner.run has cognitive complexity 44 (threshold 15). Drivers by points: if/else 24 (29 pts), error handling 7 (9 pts), boolean chains 5, match/switch 1 (nesting depth added 7). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"5559de914f2b45ca2ea9f9856da0d7f31a3c1bfb71cde2d7f601f2f70aed1852"}},{"ruleId":"D2","level":"warning","message":{"text":"DetectAmbiguousSelfJoin.apply (cognitive 44): DetectAmbiguousSelfJoin.apply has cognitive complexity 44 (threshold 15). Drivers by points: if/else 15 (32 pts), match/switch 4 (8 pts), boolean chains 4 (nesting depth added 21). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/analysis/DetectAmbiguousSelfJoin.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"c88b688eaa312839b7117db682056b62d50409fae5185a8ab65b22e7796f79ff"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticGradient.compute (cognitive 43): LogisticGradient.compute has cognitive complexity 43 (threshold 15). Drivers by points: if/else 17 (28 pts), loops 3 (8 pts), match/switch 3 (5 pts), boolean chains 2 (nesting depth added 18). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ab3c0e9b58ca0affa562f2e4506f38d12837fb28983a7de221027e50135b66a"}},{"ruleId":"D2","level":"warning","message":{"text":"UnivocityGenerator.makeConverter (cognitive 43): UnivocityGenerator.makeConverter has cognitive complexity 43 (threshold 15). Drivers by points: if/else 15 (33 pts), loops 3 (9 pts), match/switch 1 (nesting depth added 24). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityGenerator.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d4aaf178e41c0f9514fee3ea6ba756a24e38f0974ccb2b0a0f10e50ad910782"}},{"ruleId":"D2","level":"warning","message":{"text":"UnwrapCastInBinaryComparison.simplifyNumericComparison (cognitive 43): UnwrapCastInBinaryComparison.simplifyNumericComparison has cognitive complexity 43 (threshold 15). Drivers by points: match/switch 7 (22 pts), if/else 17 (20 pts), boolean chains 1 (nesting depth added 18). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"13433afe71c63a3b101319d4d42417303c327068deb144d0f226e8d077d8b305"}},{"ruleId":"D2","level":"warning","message":{"text":"RuleExecutor.execute (cognitive 43): RuleExecutor.execute has cognitive complexity 43 (threshold 15). Drivers by points: if/else 15 (33 pts), match/switch 2 (6 pts), boolean chains 3, loops 1 (nesting depth added 22). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/rules/RuleExecutor.scala"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"98e0f35f05aa7bcc322a85878b015bedc6412416f0f88adc0d38d0df520251d0"}},{"ruleId":"D2","level":"warning","message":{"text":"ToNumberParser.parse (cognitive 43): ToNumberParser.parse has cognitive complexity 43 (threshold 15). Drivers by points: if/else 13 (20 pts), match/switch 7 (20 pts), boolean chains 2, loops 1 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7aaab9601e42dd2414119aeabd84337d4fe8577ced1454d1c3f83dd429db018"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkPlan.executeTake (cognitive 43): SparkPlan.executeTake has cognitive complexity 43 (threshold 15). Drivers by points: if/else 16 (28 pts), loops 4 (12 pts), boolean chains 3 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":525}}}],"partialFingerprints":{"codehealthFindingId/v1":"6214cc553c96606bda909177944f00819b779e3e5a2431cc19739441439a280e"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinSelection.apply (cognitive 43): JoinSelection.apply has cognitive complexity 43 (threshold 15). Drivers by points: if/else 18 (29 pts), boolean chains 7, match/switch 4 (7 pts) (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"a53fed2d90bbab1f543c0cd0d9aa5033e5d619d6a48cea7cdf39319636106d0d"}},{"ruleId":"D2","level":"warning","message":{"text":"EvaluatePython.makeFromJavaDefault (cognitive 43): EvaluatePython.makeFromJavaDefault has cognitive complexity 43 (threshold 15). Drivers by points: match/switch 18 (35 pts), if/else 2 (4 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 21). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvaluatePython.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbd4a30a7c0311dbec0edf822fb9b26c3148349e0d925ec2e575f057daf7ddd9"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleMigrationRunnable.run (cognitive 42): ShuffleMigrationRunnable.run has cognitive complexity 42 (threshold 15). Drivers by points: if/else 15 (27 pts), error handling 4 (10 pts), boolean chains 4, loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerDecommissioner.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"58603333b0960bf156546e438d876d020dd63829e5cfad8f62ea8c044a78df74"}},{"ruleId":"D2","level":"warning","message":{"text":"CodegenContext.collectInputs (cognitive 42): CodegenContext.collectInputs has cognitive complexity 42 (threshold 15). Drivers by points: if/else 8 (20 pts), boolean chains 12, match/switch 4 (9 pts), loops 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala"},"region":{"startLine":1331}}}],"partialFingerprints":{"codehealthFindingId/v1":"45c485ecfb9fbe21310e4cf4c6f1c21a5ce80abf1631426704982cf301d04f6c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformReadRel (cognitive 42): SparkConnectPlanner.transformReadRel has cognitive complexity 42 (threshold 15). Drivers by points: if/else 19 (35 pts), boolean chains 4, match/switch 2 (3 pts) (nesting depth added 17). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":1790}}}],"partialFingerprints":{"codehealthFindingId/v1":"e289f6da47086b3aab9aba807d62c37a132936c7f478d5f45871f477251acbfc"}},{"ruleId":"D2","level":"warning","message":{"text":"types.proto_schema_to_pyspark_data_type (cognitive 42): types.proto_schema_to_pyspark_data_type has cognitive complexity 42 (threshold 15). Drivers by points: ternaries 12 (24 pts), if/else 10 (16 pts), loops 1 (2 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"314eb05d23971851ba28dad54a35759ef7a69164d5ccaa55420331e720bf6ef2"}},{"ruleId":"D2","level":"warning","message":{"text":"UnsafeRowUtils.validateStructuralIntegrityWithReasonImpl (cognitive 41): UnsafeRowUtils.validateStructuralIntegrityWithReasonImpl has cognitive complexity 41 (threshold 15). Drivers by points: if/else 14 (29 pts), boolean chains 7, match/switch 3 (5 pts) (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowUtils.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"720edfbd0f11771180351371deead1795d3af542316deda0b9d0a54f9cc185f0"}},{"ruleId":"D2","level":"warning","message":{"text":"XmlTokenizer.readUntilEndElement (cognitive 41): XmlTokenizer.readUntilEndElement has cognitive complexity 41 (threshold 15). Drivers by points: if/else 19 (37 pts), boolean chains 3, loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1067}}}],"partialFingerprints":{"codehealthFindingId/v1":"a299843830869e71110307b3b2a6d0435722715a2fde58a4d100817fab3e9df4"}},{"ruleId":"D2","level":"warning","message":{"text":"HashAggregateExec.doProduceWithKeys (cognitive 41): HashAggregateExec.doProduceWithKeys has cognitive complexity 41 (threshold 15). Drivers by points: if/else 37 (40 pts), match/switch 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":574}}}],"partialFingerprints":{"codehealthFindingId/v1":"00d033011b01edc87c250ea22f53097ded802f4543feabc6809875b34bf9eeb2"}},{"ruleId":"D2","level":"warning","message":{"text":"InsertIntoHadoopFsRelationCommand.run (cognitive 41): InsertIntoHadoopFsRelationCommand.run has cognitive complexity 41 (threshold 15). Drivers by points: if/else 21 (35 pts), boolean chains 4, match/switch 1 (2 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcc9b843d151f06a31a153e69e8315ffda66368e7f233d20bc1b352a1d324d60"}},{"ruleId":"D2","level":"warning","message":{"text":"AvroStateEncoder.encodePrefixKeyForRangeScan (cognitive 41): AvroStateEncoder.encodePrefixKeyForRangeScan has cognitive complexity 41 (threshold 15). Drivers by points: if/else 21 (39 pts), match/switch 1 (2 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1063}}}],"partialFingerprints":{"codehealthFindingId/v1":"69e6f3a868eea5cc3e05a906d40514e0fdc537cfa66acf87d04ff84e6fe7aff5"}},{"ruleId":"D2","level":"warning","message":{"text":"Builder.getOrCreate (cognitive 41): Builder.getOrCreate has cognitive complexity 41 (threshold 15). Drivers by points: if/else 13 (28 pts), boolean chains 7, loops 2 (6 pts) (nesting depth added 19). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ea74e64eb65b02ae34cf21e5e61e52723d8ba159d665bdcaca30b7e6fdef9af"}},{"ruleId":"D2","level":"warning","message":{"text":"SummarizerBuffer.add (cognitive 40): SummarizerBuffer.add has cognitive complexity 40 (threshold 15). Drivers by points: if/else 19 (38 pts), boolean chains 2 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":499}}}],"partialFingerprints":{"codehealthFindingId/v1":"36576fb83f91ad3130c70930efb95c79bf4651a464eafee02b05eb6281adb181"}},{"ruleId":"D2","level":"warning","message":{"text":"RewriteDistinctAggregates.rewrite (cognitive 40): RewriteDistinctAggregates.rewrite has cognitive complexity 40 (threshold 15). Drivers by points: if/else 16 (20 pts), match/switch 8 (16 pts), boolean chains 4 (nesting depth added 12). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"da98bba6f7c0b39f7d271ed6cc32bb2653849d6d29221a2a7db1a155c42203de"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowColumnVector.initAccessor (cognitive 40): ArrowColumnVector.initAccessor has cognitive complexity 40 (threshold 15). Drivers by points: if/else 34 (36 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d9823d05fe32f5afab4768559e793b8105a6cd75cc1097ee44472f30eda7af3"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints._new_type_holders (cognitive 40): typehints._new_type_holders has cognitive complexity 40 (threshold 15). Drivers by points: if/else 13 (23 pts), ternaries 2 (10 pts), loops 2 (4 pts), boolean chains 3 (nesting depth added 20). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e2949d4e3f5ba4c8146ae467f07dd0f17a6d0612848fbe1a9f729564a1c01ec"}},{"ruleId":"D2","level":"warning","message":{"text":"plan_data_source_read.records_to_arrow_batches (cognitive 40): plan_data_source_read.records_to_arrow_batches has cognitive complexity 40 (threshold 15). Drivers by points: if/else 9 (22 pts), loops 6 (15 pts), boolean chains 2, error handling 1 (nesting depth added 22). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/plan_data_source_read.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"60fbdddb082bdf2df6267fd705bd983e8cfeae60fce8af3057c7b522db6d6139"}},{"ruleId":"D2","level":"warning","message":{"text":"IndylambdaScalaClosures.findAccessedFields (cognitive 39): IndylambdaScalaClosures.findAccessedFields has cognitive complexity 39 (threshold 15). Drivers by points: if/else 14 (22 pts), loops 7 (14 pts), boolean chains 3 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"e839b23cce9a972546dc02f18a1c9740190cc0951e89846336e47287bf51d711"}},{"ruleId":"D2","level":"warning","message":{"text":"Worker.receive (cognitive 39): Worker.receive has cognitive complexity 39 (threshold 15). Drivers by points: if/else 11 (23 pts), error handling 3 (8 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 20). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":534}}}],"partialFingerprints":{"codehealthFindingId/v1":"525d28773276143bf433b5f6553dc97ac129ce37d8b647aa22a1b846e2708c20"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveLateralColumnAliasReference.apply0 (cognitive 39): ResolveLateralColumnAliasReference.apply0 has cognitive complexity 39 (threshold 15). Drivers by points: match/switch 7 (18 pts), if/else 10 (17 pts), boolean chains 4 (nesting depth added 18). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveLateralColumnAliasReference.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a70421ea364ddfbf71f7ded07b45ff73552b9bbe7f7bd545ddab23845441dec"}},{"ruleId":"D2","level":"warning","message":{"text":"DataTypeUtils.canWrite (cognitive 39): DataTypeUtils.canWrite has cognitive complexity 39 (threshold 15). Drivers by points: if/else 16 (24 pts), boolean chains 12, match/switch 2 (3 pts) (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/DataTypeUtils.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"d407b325795d9eeb7041dd07acf68105bec1001ad89d5440d10fb43fdb91f318"}},{"ruleId":"D2","level":"warning","message":{"text":"StringUtils.splitSemiColon (cognitive 39): StringUtils.splitSemiColon has cognitive complexity 39 (threshold 15). Drivers by points: if/else 17 (24 pts), boolean chains 11, loops 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/StringUtils.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf881d0dce6b0ba0bfc565c3f5187e2234d2094b27bca32c85b2205840216b12"}},{"ruleId":"D2","level":"warning","message":{"text":"AvroSerializer.newConverter (cognitive 39): AvroSerializer.newConverter has cognitive complexity 39 (threshold 15). Drivers by points: if/else 14 (22 pts), match/switch 6 (11 pts), loops 2 (4 pts), boolean chains 2 (nesting depth added 15). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cf79ea87652754499852ff76070fda7e957fa0a49a54dc09ee34e33f113bae7"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrameWriter.saveCommand (cognitive 39): DataFrameWriter.saveCommand has cognitive complexity 39 (threshold 15). Drivers by points: if/else 16 (28 pts), match/switch 3 (8 pts), boolean chains 3 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0675d5c3120d9e59705d68fdcc86ab02d0f98031a69694c55982d279f1168bd"}},{"ruleId":"D2","level":"warning","message":{"text":"UnionLoopExec.doExecute (cognitive 39): UnionLoopExec.doExecute has cognitive complexity 39 (threshold 15). Drivers by points: if/else 13 (23 pts), match/switch 4 (12 pts), boolean chains 3, loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/UnionLoopExec.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"81ea8403a8d52aa77440679a25b55a379daa5bfb8f831ada650449894dd857f8"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkShreddingUtils.extractField (cognitive 39): SparkShreddingUtils.extractField has cognitive complexity 39 (threshold 15). Drivers by points: if/else 11 (27 pts), boolean chains 4, loops 2 (4 pts), match/switch 1 (4 pts) (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":788}}}],"partialFingerprints":{"codehealthFindingId/v1":"3386de2a010f61cf2c20b2c28bc389ed1ca0fa62fac76082cfe15a83743c6e11"}},{"ruleId":"D2","level":"warning","message":{"text":"Shim_v2_0.convertFilters (cognitive 39): Shim_v2_0.convertFilters has cognitive complexity 39 (threshold 15). Drivers by points: if/else 17 (18 pts), boolean chains 8, match/switch 8, loops 2 (5 pts) (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"20f15444df2aa25ec7609e93b16766d582244c6ea01e7b919c387dd530d2fce1"}},{"ruleId":"D2","level":"warning","message":{"text":"connect._convert_exception (cognitive 39): connect._convert_exception has cognitive complexity 39 (threshold 15). Drivers by points: if/else 9 (19 pts), ternaries 4 (13 pts), loops 2 (4 pts), boolean chains 3 (nesting depth added 21). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/connect.py"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1bbdd87a013303265353ea61a7a92f90f6d6b667c1bf8026d0e0d9009468e11"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext.holdExecutors (cognitive 38): SparkContext.holdExecutors has cognitive complexity 38 (threshold 15). Drivers by points: if/else 12 (25 pts), match/switch 4 (13 pts) (nesting depth added 22). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2178}}}],"partialFingerprints":{"codehealthFindingId/v1":"a655b59703cd442f5c1c0b4db696027b5c4a1f9b8ebe62de935c540e2b06968f"}},{"ruleId":"D2","level":"warning","message":{"text":"NewHadoopRDD.compute (cognitive 38): NewHadoopRDD.compute has cognitive complexity 38 (threshold 15). Drivers by points: error handling 10 (17 pts), if/else 12 (16 pts), match/switch 3, boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"5aa816df680fa8f96c110bbd7931dcf48d37f911ee9bb66c54ec5d969a55debc"}},{"ruleId":"D2","level":"warning","message":{"text":"CatalogTable.toJsonLinkedHashMap (cognitive 38): CatalogTable.toJsonLinkedHashMap has cognitive complexity 38 (threshold 15). Drivers by points: if/else 29 (37 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":642}}}],"partialFingerprints":{"codehealthFindingId/v1":"19a3185c462cbc1b5358b0c3356f1449f0136d7a0404eec106359cca1f3a1d02"}},{"ruleId":"D2","level":"warning","message":{"text":"StaxXmlParser.convertObject (cognitive 38): StaxXmlParser.convertObject has cognitive complexity 38 (threshold 15). Drivers by points: match/switch 5 (19 pts), if/else 7 (11 pts), error handling 2 (6 pts), loops 2 (nesting depth added 22). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7bab32c0fe8fd9f0042646ef55f6b890243a4fe9a15379d8a396b18fdfebadb"}},{"ruleId":"D2","level":"warning","message":{"text":"CommandBuilderUtils.parseOptionString (cognitive 38): CommandBuilderUtils.parseOptionString has cognitive complexity 38 (threshold 15). Drivers by points: if/else 13 (29 pts), match/switch 2 (6 pts), boolean chains 2, loops 1 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/CommandBuilderUtils.java"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e8aa335706cdc1d5285bf579a1fd83b46e04231a8dd7072c8dd05ffbd62a6fa"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDBProvider.initRockDB (cognitive 38): RocksDBProvider.initRockDB has cognitive complexity 38 (threshold 15). Drivers by points: if/else 6 (19 pts), error handling 5 (14 pts), loops 1 (5 pts) (nesting depth added 26). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/RocksDBProvider.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"e04a9b678b977570142e74adb36d3985a0450cb6a12142adb41a738a73824415"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.resolve_jira_issue (cognitive 38): merge_spark_pr.resolve_jira_issue has cognitive complexity 38 (threshold 15). Drivers by points: if/else 18 (28 pts), error handling 2 (4 pts), boolean chains 3, loops 2, ternaries 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":1880}}}],"partialFingerprints":{"codehealthFindingId/v1":"61bf8feb5aaaf7a4b3f3009f3e1a62d268ec0fd2e31556b50de848c4ce7b6aae"}},{"ruleId":"D2","level":"warning","message":{"text":"LocIndexer._get_from_multiindex_column (cognitive 38): LocIndexer._get_from_multiindex_column has cognitive complexity 38 (threshold 15). Drivers by points: if/else 12 (22 pts), ternaries 3 (9 pts), boolean chains 6, loops 1 (nesting depth added 16). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1246}}}],"partialFingerprints":{"codehealthFindingId/v1":"07b46a4cce72f1ee989b0dfde3950a3f2638e8ffdf5aa4c422acc50c96695d65"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleWriteProcessor.write (cognitive 37): ShuffleWriteProcessor.write has cognitive complexity 37 (threshold 15). Drivers by points: if/else 11 (25 pts), match/switch 2 (7 pts), error handling 2 (3 pts), boolean chains 2 (nesting depth added 20). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/ShuffleWriteProcessor.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"317429d7163f872e4fa7a4e41fc9fe6175344ea76c475ec4a215895894f8229c"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneralizedLinearAlgorithm.run (cognitive 37): GeneralizedLinearAlgorithm.run has cognitive complexity 37 (threshold 15). Drivers by points: if/else 24 (30 pts), boolean chains 4, loops 1 (3 pts) (nesting depth added 8). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"c01bd0d83892425a511b2ce9a39ce3817b38aa590284399fcd2bc608ddaba37f"}},{"ruleId":"D2","level":"warning","message":{"text":"SeptenaryExpression.eval (cognitive 37): SeptenaryExpression.eval has cognitive complexity 37 (threshold 15). Drivers by points: if/else 9 (37 pts) (nesting depth added 28). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1216}}}],"partialFingerprints":{"codehealthFindingId/v1":"d418c7f8ef9728f7b4fa359fb1eac209f1d6cf9623935351362b0b29d91d39d0"}},{"ruleId":"D2","level":"warning","message":{"text":"FilterEstimation.evaluateBinaryForNumeric (cognitive 37): FilterEstimation.evaluateBinaryForNumeric has cognitive complexity 37 (threshold 15). Drivers by points: if/else 15 (29 pts), match/switch 3 (7 pts), boolean chains 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":510}}}],"partialFingerprints":{"codehealthFindingId/v1":"694fa7eb2342954ae87982cc881acbd6a8adddd995711ab28dea2deffef8e508"}},{"ruleId":"D2","level":"warning","message":{"text":"ErrorUtils.throwableToProtoErrors (cognitive 37): ErrorUtils.throwableToProtoErrors has cognitive complexity 37 (threshold 15). Drivers by points: if/else 11 (29 pts), loops 2 (4 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/utils/ErrorUtils.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"946c2e7cdc007ace04f20784370908c152032db14b1bf91ba9ff33c80715d201"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSource.lookupDataSource (cognitive 37): DataSource.lookupDataSource has cognitive complexity 37 (threshold 15). Drivers by points: if/else 17 (24 pts), boolean chains 5, error handling 3 (4 pts), match/switch 3 (4 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"02ecddbb96ba60edec0fb9dead581b34ccbb20b329a7e34879d4946494156b23"}},{"ruleId":"D2","level":"warning","message":{"text":"XSDToSchema.getStructFieldsFromParticle (cognitive 37): XSDToSchema.getStructFieldsFromParticle has cognitive complexity 37 (threshold 15). Drivers by points: if/else 16 (30 pts), match/switch 4 (7 pts) (nesting depth added 17). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"b30e1fcd2bddad6132490cababa5cc3bcdf0b2c5c0cec5498e946411a57bf089"}},{"ruleId":"D2","level":"warning","message":{"text":"MicroBatchExecution.runBatch (cognitive 37): MicroBatchExecution.runBatch has cognitive complexity 37 (threshold 15). Drivers by points: if/else 14 (22 pts), match/switch 10 (15 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":1198}}}],"partialFingerprints":{"codehealthFindingId/v1":"e64f6668435cd783a3c6d8281f08acfb96e234975f454c24722eca69449708b8"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDBStateStoreChangeDataReader.getNext (cognitive 37): RocksDBStateStoreChangeDataReader.getNext has cognitive complexity 37 (threshold 15). Drivers by points: if/else 17 (30 pts), match/switch 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":1676}}}],"partialFingerprints":{"codehealthFindingId/v1":"67fec57a42e56669f5afc4ae7706dc6bbcab7b41223b2711db3436823d9b6ab5"}},{"ruleId":"D2","level":"warning","message":{"text":"LevelDBProvider.initLevelDB (cognitive 37): LevelDBProvider.initLevelDB has cognitive complexity 37 (threshold 15). Drivers by points: if/else 6 (19 pts), error handling 4 (12 pts), loops 1 (5 pts), boolean chains 1 (nesting depth added 25). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"19f85d2b9729f42719f0c260e3dc5c0da2b8c50aaddee861f35bacada1a27982"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorizedColumnReader.readBatch (cognitive 37): VectorizedColumnReader.readBatch has cognitive complexity 37 (threshold 15). Drivers by points: if/else 13 (28 pts), boolean chains 6, error handling 1 (2 pts), loops 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c1db0c851cc67d4181765fb02b9d84114e660da8b87221ae848be8f703aacec"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConversionMixin._convert_from_pandas (cognitive 37): SparkConversionMixin._convert_from_pandas has cognitive complexity 37 (threshold 15). Drivers by points: if/else 12 (31 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 22). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":703}}}],"partialFingerprints":{"codehealthFindingId/v1":"e266b3dbe450ba9febb19d976cf55dc32acdbdd0557f8e265c9a8733abc6541b"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorPodsAllocator.onNewSnapshots (cognitive 36): ExecutorPodsAllocator.onNewSnapshots has cognitive complexity 36 (threshold 15). Drivers by points: if/else 24 (29 pts), boolean chains 5, match/switch 2 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"9514b62969fcdccd0ddbfbd8d2a383c7de9cfa19a9617c2b5010cf88e77d7fc5"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveSQLFunctions.rewrite (cognitive 36): ResolveSQLFunctions.rewrite has cognitive complexity 36 (threshold 15). Drivers by points: if/else 12 (18 pts), match/switch 5 (11 pts), boolean chains 7 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2972}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea4ec6e7741be93660feb5c029f49728cf384f821c6a5062b73065e2059ae6fb"}},{"ruleId":"D2","level":"warning","message":{"text":"FunctionResolution.resolveProcedure (cognitive 36): FunctionResolution.resolveProcedure has cognitive complexity 36 (threshold 15). Drivers by points: error handling 7 (20 pts), if/else 4 (8 pts), match/switch 2 (6 pts), boolean chains 1, loops 1 (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":860}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca76a1d190a6852c03a1824c50a06f162cbb2b72a4b648de281cd546392e6823"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrayInsert.nullSafeEval (cognitive 36): ArrayInsert.nullSafeEval has cognitive complexity 36 (threshold 15). Drivers by points: if/else 18 (35 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":5652}}}],"partialFingerprints":{"codehealthFindingId/v1":"e617da380a88a78cd4b996ec73035a41f7ff94ef3da3229df303faef4309d275"}},{"ruleId":"D2","level":"warning","message":{"text":"InjectRuntimeFilter.extractSelectiveFilterOverScan (cognitive 36): InjectRuntimeFilter.extractSelectiveFilterOverScan has cognitive complexity 36 (threshold 15). Drivers by points: if/else 17 (26 pts), boolean chains 7, match/switch 2 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b954c7802f94d2c1b24bba845fb52fda46119c0a6c821c66130b6c1cfd98cea"}},{"ruleId":"D2","level":"warning","message":{"text":"SimplifyConditionals.apply (cognitive 36): SimplifyConditionals.apply has cognitive complexity 36 (threshold 15). Drivers by points: if/else 13 (28 pts), loops 1 (3 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 18). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":807}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c08775009390a23ea3482e0e5c6da778ac3323d0ce851e4163489d421dc9c65"}},{"ruleId":"D2","level":"warning","message":{"text":"PredicateUtils.toV1 (cognitive 36): PredicateUtils.toV1 has cognitive complexity 36 (threshold 15). Drivers by points: if/else 14 (23 pts), match/switch 5 (9 pts), boolean chains 4 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/connector/PredicateUtils.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"406e0ca1537ebab541e629c22000767411edd4d9df3a79c704e2edab2c16862b"}},{"ruleId":"D2","level":"warning","message":{"text":"AggregationIterator.generateProcessRow (cognitive 36): AggregationIterator.generateProcessRow has cognitive complexity 36 (threshold 15). Drivers by points: if/else 9 (19 pts), match/switch 6 (15 pts), loops 1 (2 pts) (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregationIterator.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6e0c2c6c1b3219ffdd5f681710bd58b3a892d829cd69e73a11cc55bb31ac975"}},{"ruleId":"D2","level":"warning","message":{"text":"HashAggregateExec.doConsumeWithKeys (cognitive 36): HashAggregateExec.doConsumeWithKeys has cognitive complexity 36 (threshold 15). Drivers by points: if/else 29 (34 pts), match/switch 2 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":966}}}],"partialFingerprints":{"codehealthFindingId/v1":"e49d7df7b36a3391d791e3c0725942e3294af21ecd28a5988453991372cdbc8d"}},{"ruleId":"D2","level":"warning","message":{"text":"DescribeColumnExec.run (cognitive 36): DescribeColumnExec.run has cognitive complexity 36 (threshold 15). Drivers by points: if/else 18 (31 pts), match/switch 2 (5 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeColumnExec.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ea4ff9821f977824f23804ec1075870ff83dc9977de28e657f3ffb4f8beacb9"}},{"ruleId":"D2","level":"warning","message":{"text":"StateDataSource.getStoreMetadataAndRunChecks (cognitive 36): StateDataSource.getStoreMetadataAndRunChecks has cognitive complexity 36 (threshold 15). Drivers by points: if/else 15 (32 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 18). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":297}}}],"partialFingerprints":{"codehealthFindingId/v1":"92acfaf8d875656a34ca248f5ff7632b319653e18b17e9bd96da7d605e4c5c3f"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingV2ScanPushDown.buildScan (cognitive 36): StreamingV2ScanPushDown.buildScan has cognitive complexity 36 (threshold 15). Drivers by points: if/else 19 (21 pts), match/switch 6 (9 pts), boolean chains 6 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":558}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2ef5ba664508167d79b7630dab9a0143fbee78a9218a05997920e34e87b1820"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmitCommandBuilder.buildSparkSubmitArgs (cognitive 36): SparkSubmitCommandBuilder.buildSparkSubmitArgs has cognitive complexity 36 (threshold 15). Drivers by points: if/else 23 (26 pts), boolean chains 7, loops 2 (3 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkSubmitCommandBuilder.java"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"337b76ffba5fca3dd4d8a88f07966a100a6015400d850241437025f08540aba0"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.appendWithSetImpl (cognitive 36): VariantBuilder.appendWithSetImpl has cognitive complexity 36 (threshold 15). Drivers by points: if/else 17 (24 pts), loops 4 (8 pts), boolean chains 4 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":730}}}],"partialFingerprints":{"codehealthFindingId/v1":"889a2fc14615f2da1f9d7aee15da963d4dfc406831ee220c2e339bcc033a3427"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupBy.aggregate (cognitive 36): GroupBy.aggregate has cognitive complexity 36 (threshold 15). Drivers by points: if/else 17 (29 pts), boolean chains 7 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a39f2a574cbe7f0b21a41a6e82d1f7f7f2dc928a96c7628367251c1a382209d"}},{"ruleId":"D2","level":"warning","message":{"text":"Logging.initializeLogging (cognitive 35): Logging.initializeLogging has cognitive complexity 35 (threshold 15). Drivers by points: if/else 12 (27 pts), match/switch 2 (7 pts), boolean chains 1 (nesting depth added 20). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/internal/Logging.scala"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeb176f79edc8e38f6e97e726443657e9f5e5cd87f80ee48344d4f26774b8f01"}},{"ruleId":"D2","level":"warning","message":{"text":"KMeans.trainWithBlock (cognitive 35): KMeans.trainWithBlock has cognitive complexity 35 (threshold 15). Drivers by points: if/else 16 (25 pts), match/switch 4 (7 pts), boolean chains 2, loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala"},"region":{"startLine":526}}}],"partialFingerprints":{"codehealthFindingId/v1":"804949a114a88200c825e68c5f1ced03c674f9e7d56deaadfc1a0960405efe3a"}},{"ruleId":"D2","level":"warning","message":{"text":"MultinomialLogisticBlockAggregator.add (cognitive 35): MultinomialLogisticBlockAggregator.add has cognitive complexity 35 (threshold 15). Drivers by points: loops 7 (17 pts), if/else 11 (16 pts), boolean chains 1, match/switch 1 (nesting depth added 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/MultinomialLogisticBlockAggregator.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"f28294d0cca3c77322d9813398dd218dae1ff0d31cd6537ce1db6493acd88e76"}},{"ruleId":"D2","level":"warning","message":{"text":"Client.monitorApplication (cognitive 35): Client.monitorApplication has cognitive complexity 35 (threshold 15). Drivers by points: if/else 10 (19 pts), match/switch 2 (7 pts), boolean chains 4, error handling 2 (4 pts), loops 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1210}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0dd9b330adb0634782c23fd076677d467ec18a082d81f64151839d24b848e8f"}},{"ruleId":"D2","level":"warning","message":{"text":"Row.equals (cognitive 35): Row.equals has cognitive complexity 35 (threshold 15). Drivers by points: if/else 11 (28 pts), boolean chains 3, match/switch 1 (3 pts), loops 1 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"cff86b667b49f6ebad3b14ff950f7dffc619108f6c33f6711bb38533ae6e8d62"}},{"ruleId":"D2","level":"warning","message":{"text":"AttributeNameParser.parseAttributeName (cognitive 35): AttributeNameParser.parseAttributeName has cognitive complexity 35 (threshold 15). Drivers by points: if/else 13 (31 pts), boolean chains 3, loops 1 (nesting depth added 18). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/AttributeNameParser.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"afc36a3427e9555aa4e18278e1f1ab6b7b980aaf953f69a2c23d44846c2fe1eb"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonInferSchema.inferField (cognitive 35): JsonInferSchema.inferField has cognitive complexity 35 (threshold 15). Drivers by points: if/else 15 (25 pts), loops 2 (4 pts), boolean chains 3, match/switch 2 (3 pts) (nesting depth added 13). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"1055c19bffc5f74a46c2ea840b76ddf5556cec482126f40a6a885e1f4147afb6"}},{"ruleId":"D2","level":"warning","message":{"text":"PushdownPredicatesAndPruneColumnsForCTEDef.removePushedDownFilter (cognitive 35): PushdownPredicatesAndPruneColumnsForCTEDef.removePushedDownFilter has cognitive complexity 35 (threshold 15). Drivers by points: if/else 19 (30 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushdownPredicatesAndPruneColumnsForCTEDef.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"d015d30b69fa4f28d3ddd61fb7214bc924e92ed5399723a4cd3387a3f969bf1d"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetFilters.createFilterHelper (cognitive 35): ParquetFilters.createFilterHelper has cognitive complexity 35 (threshold 15). Drivers by points: boolean chains 14, if/else 9 (13 pts), loops 2 (5 pts), match/switch 2 (3 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"965e039552e84e2fc8eb0a69412571f19ce63ee806443a0e5efac1e0c041197f"}},{"ruleId":"D2","level":"warning","message":{"text":"StateStoreCoordinator.receiveAndReply (cognitive 35): StateStoreCoordinator.receiveAndReply has cognitive complexity 35 (threshold 15). Drivers by points: if/else 9 (20 pts), match/switch 5 (12 pts), error handling 1 (3 pts) (nesting depth added 20). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreCoordinator.scala"},"region":{"startLine":317}}}],"partialFingerprints":{"codehealthFindingId/v1":"4554ebc8d4aa004b280082cd5c668cd319cdb1d325a4f540380dd6b9ef8c4e14"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.appendWithInsertionImpl (cognitive 35): VariantBuilder.appendWithInsertionImpl has cognitive complexity 35 (threshold 15). Drivers by points: if/else 14 (20 pts), loops 6 (12 pts), boolean chains 3 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":627}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc1e449be1ee40e3502ba11446e41d32a2a9b9635f1d5b54b345ac1881228af8"}},{"ruleId":"D2","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.loadNextRowGroup (cognitive 35): LateMaterializationParquetRecordReader.loadNextRowGroup has cognitive complexity 35 (threshold 15). Drivers by points: if/else 7 (15 pts), ternaries 6 (15 pts), boolean chains 2, error handling 1 (2 pts), loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e62ae33fee0bb9ebcbe57548f194ac8b8fbf3c6b3e18397fb8850011ff9dd64"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.get_input (cognitive 35): merge_spark_pr.get_input has cognitive complexity 35 (threshold 15). Drivers by points: if/else 13 (29 pts), loops 3 (6 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":572}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ffbe06f85fd52e160ceadbcf0227ab788599e43b514d9c09728644b2fe98052"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints.infer_return_type (cognitive 35): typehints.infer_return_type has cognitive complexity 35 (threshold 15). Drivers by points: if/else 10 (14 pts), ternaries 4 (11 pts), boolean chains 5, loops 2 (5 pts) (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"7332bb6a2e883de6e214adb6e1dc7c1d046075305f285a73745b4569f65acc98"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.liveReduceSet (cognitive 34): DAGScheduler.liveReduceSet has cognitive complexity 34 (threshold 15). Drivers by points: if/else 9 (18 pts), match/switch 5 (14 pts), boolean chains 1, loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2201}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd9b04dad9b1f10b9e0d208f4511bdb2975d48005101c515fb669254ce457760"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalSorter.writePartitionedMapOutput (cognitive 34): ExternalSorter.writePartitionedMapOutput has cognitive complexity 34 (threshold 15). Drivers by points: if/else 11 (22 pts), loops 4 (11 pts), boolean chains 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"d53edd44c6241978b749a5eed76190ef20b183da241a74aacf0afa7af5a6921c"}},{"ruleId":"D2","level":"warning","message":{"text":"YarnAllocator.processCompletedContainers (cognitive 34): YarnAllocator.processCompletedContainers has cognitive complexity 34 (threshold 15). Drivers by points: if/else 10 (20 pts), match/switch 3 (8 pts), loops 3 (6 pts) (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"58228741746d7626a87862055be4777635c81da99038eefbfde38362250eab99"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveRelations.lookupTableOrView (cognitive 34): ResolveRelations.lookupTableOrView has cognitive complexity 34 (threshold 15). Drivers by points: match/switch 5 (13 pts), if/else 8 (11 pts), error handling 2 (7 pts), boolean chains 3 (nesting depth added 16). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1463}}}],"partialFingerprints":{"codehealthFindingId/v1":"822165c2b9e24af2308ea155acee97fd6ec1be33c406a366db36fccf00943687"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantValueConverter.convertInput (cognitive 34): VariantValueConverter.convertInput has cognitive complexity 34 (threshold 15). Drivers by points: if/else 18 (24 pts), error handling 5 (6 pts), boolean chains 3, match/switch 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":480}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a922491403b7ab5756999c0cac7cfabbf9516aa93fc4a585eb3c5a468087557"}},{"ruleId":"D2","level":"warning","message":{"text":"InterpretedHashFunction.hash (cognitive 34): InterpretedHashFunction.hash has cognitive complexity 34 (threshold 15). Drivers by points: if/else 12 (20 pts), match/switch 4 (7 pts), loops 3 (6 pts), boolean chains 1 (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":717}}}],"partialFingerprints":{"codehealthFindingId/v1":"e221bcfe0896e544c79c9c29a2a9560f7ce3806c3cbe2ce9f0f208361947dc23"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetFilters.shreddedVariantEntries (cognitive 34): ParquetFilters.shreddedVariantEntries has cognitive complexity 34 (threshold 15). Drivers by points: match/switch 6 (19 pts), if/else 7 (14 pts), boolean chains 1 (nesting depth added 20). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"9547a81fa210a925b2b17ca6ca2f5e1635b0a217c3f917259e7e9afe603388ab"}},{"ruleId":"D2","level":"warning","message":{"text":"XmlRecordReader.readUntilEndElement (cognitive 34): XmlRecordReader.readUntilEndElement has cognitive complexity 34 (threshold 15). Drivers by points: if/else 15 (30 pts), boolean chains 3, loops 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala"},"region":{"startLine":231}}}],"partialFingerprints":{"codehealthFindingId/v1":"48d2c182703bc393d998386e7e7892b84dabcc63c362d36d95153cd46d6de34b"}},{"ruleId":"D2","level":"warning","message":{"text":"MapOutputTracker.convertMapStatuses (cognitive 33): MapOutputTracker.convertMapStatuses has cognitive complexity 33 (threshold 15). Drivers by points: if/else 6 (18 pts), loops 5 (12 pts), boolean chains 3 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1898}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d015b7a650636457a4ff4f2f62e2f366a9b9257d9e1c090093c2a7508abb6e8"}},{"ruleId":"D2","level":"warning","message":{"text":"ReaderInputStream.read (cognitive 33): ReaderInputStream.read has cognitive complexity 33 (threshold 15). Drivers by points: if/else 11 (28 pts), boolean chains 4, loops 1 (nesting depth added 17). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1413}}}],"partialFingerprints":{"codehealthFindingId/v1":"887ee4f7b29489f927375ee44456f33493362eb25c45faffe3763c51f18edf79"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorIndexerModel.getTransformFunc (cognitive 33): VectorIndexerModel.getTransformFunc has cognitive complexity 33 (threshold 15). Drivers by points: match/switch 4 (12 pts), if/else 7 (11 pts), error handling 2 (7 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 18). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"0237623c1a76e9b5aae25855008fce824dc355f686178e88be5527e6f0668dd7"}},{"ruleId":"D2","level":"warning","message":{"text":"RewritePredicateSubquery.apply (cognitive 33): RewritePredicateSubquery.apply has cognitive complexity 33 (threshold 15). Drivers by points: match/switch 7 (17 pts), if/else 7 (12 pts), boolean chains 4 (nesting depth added 15). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"1be6a3ebea3d56a23a34edf5ce9bb1f1508b6ef55c0451c1ad57c2852a101eb4"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecuteGrpcResponseSender.execute (cognitive 33): ExecuteGrpcResponseSender.execute has cognitive complexity 33 (threshold 15). Drivers by points: if/else 13 (23 pts), boolean chains 4, loops 2 (3 pts), match/switch 1 (3 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/execution/ExecuteGrpcResponseSender.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"e45f0e0d240c6384521b91ae6d8e1ceb5145749266ac748b2db9a306ce502846"}},{"ruleId":"D2","level":"warning","message":{"text":"InferVariantShreddingSchema.collectFieldStats (cognitive 33): InferVariantShreddingSchema.collectFieldStats has cognitive complexity 33 (threshold 15). Drivers by points: if/else 13 (23 pts), loops 3 (7 pts), boolean chains 2, match/switch 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/InferVariantShreddingSchema.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"14c395d6f0be5764fa6253a87a3ac6238f0e2b431ab6c3d64c7be3d3fda0de84"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnVectorUtils.populate (cognitive 33): ColumnVectorUtils.populate has cognitive complexity 33 (threshold 15). Drivers by points: if/else 22 (24 pts), ternaries 2 (5 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f64be45ae43c696aad2aa5de7b7560fbfcd231ebbf46e40f9d35fdb8efbfd7c"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.isin (cognitive 33): DataFrame.isin has cognitive complexity 33 (threshold 15). Drivers by points: if/else 8 (15 pts), ternaries 4 (13 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8682}}}],"partialFingerprints":{"codehealthFindingId/v1":"078bd0200ad49d50022158ce40c472462b4520c030ef1e263c6c991f1fe9fa34"}},{"ruleId":"D2","level":"warning","message":{"text":"iLocIndexer._select_rows_by_slice (cognitive 33): iLocIndexer._select_rows_by_slice has cognitive complexity 33 (threshold 15). Drivers by points: if/else 20 (28 pts), boolean chains 5 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1645}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c10ab84f38d2ac34a48dc85c23b489f0a5fa9e807affaaa3ed68246c20d5686"}},{"ruleId":"D2","level":"warning","message":{"text":"KafkaSourceProvider.validateGeneralOptions (cognitive 32): KafkaSourceProvider.validateGeneralOptions has cognitive complexity 32 (threshold 15). Drivers by points: if/else 21 (29 pts), boolean chains 2, match/switch 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f12f341d302d4b4007857bee73635c1364abf8be06e0eff8381f69ccdcee47d"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmit.runMain (cognitive 32): SparkSubmit.runMain has cognitive complexity 32 (threshold 15). Drivers by points: if/else 15 (20 pts), error handling 4 (5 pts), boolean chains 3, match/switch 2 (3 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":971}}}],"partialFingerprints":{"codehealthFindingId/v1":"8368847834d0ded6906b7c4a93237011859b60a93f0ce620c31845409a532af0"}},{"ruleId":"D2","level":"warning","message":{"text":"HadoopMapReduceCommitProtocol.commitJob (cognitive 32): HadoopMapReduceCommitProtocol.commitJob has cognitive complexity 32 (threshold 15). Drivers by points: if/else 8 (22 pts), loops 3 (8 pts), boolean chains 2 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/io/HadoopMapReduceCommitProtocol.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0febca0bed90b813eb243b00a62f23652629bb424abbd8486323f480ccc696b"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.submitStage (cognitive 32): DAGScheduler.submitStage has cognitive complexity 32 (threshold 15). Drivers by points: if/else 10 (24 pts), loops 1 (5 pts), boolean chains 3 (nesting depth added 18). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2887}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb985d2503551a2fcdc73c8f10d72c51a5e5a81671ebe21a42e98a77876c0e21"}},{"ruleId":"D2","level":"warning","message":{"text":"ALS.computeFactors (cognitive 32): ALS.computeFactors has cognitive complexity 32 (threshold 15). Drivers by points: if/else 8 (21 pts), loops 2 (5 pts), error handling 1 (4 pts), boolean chains 1, match/switch 1 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala"},"region":{"startLine":1773}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8f445eb6813bd24e3ebdb75e4cfce3495dde44e28324d2a47a6dead376361f3"}},{"ruleId":"D2","level":"warning","message":{"text":"LinearRegression.train (cognitive 32): LinearRegression.train has cognitive complexity 32 (threshold 15). Drivers by points: if/else 18 (21 pts), boolean chains 8, match/switch 3 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea4ad6c468bd240bce565faad230bed4f7b4a434dc1598dd8bba18234fd1d97e"}},{"ruleId":"D2","level":"warning","message":{"text":"Client.createContainerLaunchContext (cognitive 32): Client.createContainerLaunchContext has cognitive complexity 32 (threshold 15). Drivers by points: if/else 25 (29 pts), boolean chains 3 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1033}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e8d872c40c13f4c6fe9f84d9536d53c4fe9b14dc3c28f807eb7991c72f80e7c"}},{"ruleId":"D2","level":"warning","message":{"text":"AlterTableValidation.validate (cognitive 32): AlterTableValidation.validate has cognitive complexity 32 (threshold 15). Drivers by points: if/else 10 (20 pts), match/switch 4 (11 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlterTableValidation.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ad54f5e50a2534950e54f6c76e76322ee7ee1a153366d5bd96228da366ea92c"}},{"ruleId":"D2","level":"warning","message":{"text":"PullupCorrelatedPredicates.rewriteSubQueries (cognitive 32): PullupCorrelatedPredicates.rewriteSubQueries has cognitive complexity 32 (threshold 15). Drivers by points: if/else 16 (20 pts), match/switch 4 (8 pts), boolean chains 4 (nesting depth added 8). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":570}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9496986d6a250bd73e8cea973b48f690e1f29c8ae73a5989f565426ae64974f"}},{"ruleId":"D2","level":"warning","message":{"text":"GenericArrayData.equals (cognitive 32): GenericArrayData.equals has cognitive complexity 32 (threshold 15). Drivers by points: if/else 10 (24 pts), boolean chains 4, match/switch 1 (3 pts), loops 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"20029d6d99040ffdbf16c8d6e3196e148016071d6cac559bf3052eee9c6c5d97"}},{"ruleId":"D2","level":"warning","message":{"text":"Aggregation.apply (cognitive 32): Aggregation.apply has cognitive complexity 32 (threshold 15). Drivers by points: match/switch 8 (18 pts), if/else 10 (13 pts), boolean chains 1 (nesting depth added 13). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":670}}}],"partialFingerprints":{"codehealthFindingId/v1":"925ab1d5a495eef35847056711ed544dbfcd1f1b8278af9c8a819b187d6d4e76"}},{"ruleId":"D2","level":"warning","message":{"text":"AdaptiveSparkPlanExec.createNonResultQueryStages (cognitive 32): AdaptiveSparkPlanExec.createNonResultQueryStages has cognitive complexity 32 (threshold 15). Drivers by points: if/else 12 (24 pts), match/switch 3 (8 pts) (nesting depth added 17). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala"},"region":{"startLine":898}}}],"partialFingerprints":{"codehealthFindingId/v1":"f84a27f8844370b0f84cf25a32b480f381b3bb34c3793c61d1de13d1f05826ee"}},{"ruleId":"D2","level":"warning","message":{"text":"DemoteBroadcastHashJoin.selectJoinStrategy (cognitive 32): DemoteBroadcastHashJoin.selectJoinStrategy has cognitive complexity 32 (threshold 15). Drivers by points: if/else 13 (16 pts), match/switch 4 (9 pts), boolean chains 7 (nesting depth added 8). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/DemoteBroadcastHashJoin.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d89071d813f777528a5e1f208a6fd86dbbce490f2a81ed012b3534811aa02f7"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveInspectors.unwrapperFor (cognitive 32): HiveInspectors.unwrapperFor has cognitive complexity 32 (threshold 15). Drivers by points: if/else 18 (27 pts), loops 1 (4 pts), match/switch 1 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":852}}}],"partialFingerprints":{"codehealthFindingId/v1":"74738f22cbc5c94f5b63931a5cb450e6592c41b564011f0fadd4eeaa437e1271"}},{"ruleId":"D2","level":"warning","message":{"text":"DecryptionHandler.channelRead (cognitive 32): DecryptionHandler.channelRead has cognitive complexity 32 (threshold 15). Drivers by points: if/else 11 (26 pts), boolean chains 3, loops 2 (3 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/GcmTransportCipher.java"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4f07939257e26ab2ac379112d0746d5581acb3f3ca9dd872c762bf7be4d0e4d"}},{"ruleId":"D2","level":"warning","message":{"text":"ExpressionImplUtils.aesInternal (cognitive 32): ExpressionImplUtils.aesInternal has cognitive complexity 32 (threshold 15). Drivers by points: if/else 15 (28 pts), boolean chains 3, error handling 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java"},"region":{"startLine":277}}}],"partialFingerprints":{"codehealthFindingId/v1":"52674dc364379e8678748e09733acf1710e0c9cfabee5804a824f70235165bd9"}},{"ruleId":"D2","level":"warning","message":{"text":"RDD.histogram (cognitive 32): RDD.histogram has cognitive complexity 32 (threshold 15). Drivers by points: if/else 12 (23 pts), error handling 3 (6 pts), boolean chains 3 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":2210}}}],"partialFingerprints":{"codehealthFindingId/v1":"69e86a941b9c4e74e9209443a01eddf533e50dfd6a3f6fb1ed1def93855ac7b6"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowBatchedUDFArrowHandler.run (cognitive 32): ArrowBatchedUDFArrowHandler.run has cognitive complexity 32 (threshold 15). Drivers by points: if/else 9 (20 pts), ternaries 2 (5 pts), error handling 1 (3 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":878}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3e42e90feddfcfb902b759d42bf0aa542c260d7963e12aef112d6f9acd75b90"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext.addFile (cognitive 31): SparkContext.addFile has cognitive complexity 31 (threshold 15). Drivers by points: if/else 19 (23 pts), boolean chains 7, match/switch 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1867}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d266357cb8b8b7049b926a1b8bd09b72b7d03188b27da3d8d37e5b923440f10"}},{"ruleId":"D2","level":"warning","message":{"text":"HadoopRDD.compute (cognitive 31): HadoopRDD.compute has cognitive complexity 31 (threshold 15). Drivers by points: if/else 12 (15 pts), error handling 10 (13 pts), match/switch 2, boolean chains 1 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"aee1bae0f32b148860386628b641673cc19d07aba3e1e9f80fd134017bfe1f9e"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorResourcesAmounts.assignAddressesCustomResources (cognitive 31): ExecutorResourcesAmounts.assignAddressesCustomResources has cognitive complexity 31 (threshold 15). Drivers by points: if/else 7 (19 pts), loops 3 (9 pts), match/switch 1 (2 pts), boolean chains 1 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ExecutorResourcesAmounts.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"8db6d537776c11565572280ad2be55e478e293dc1d374851c5ab6ae32f1ec868"}},{"ruleId":"D2","level":"warning","message":{"text":"BasicBlockReplicationPolicy.prioritize (cognitive 31): BasicBlockReplicationPolicy.prioritize has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (27 pts), boolean chains 4 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockReplicationPolicy.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc4ba13e4b47cb876d5a7dc4254cb938cf2b573b426730866551f5ff8089f552"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveRelations.apply (cognitive 31): ResolveRelations.apply has cognitive complexity 31 (threshold 15). Drivers by points: match/switch 10 (21 pts), if/else 9, boolean chains 1 (nesting depth added 11). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1341}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea28df87edcb9f4cb6b24bfe669b06fc7a1fcfbda14cf6dfce6cb024b50c0943"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractGenerator.apply (cognitive 31): ExtractGenerator.apply has cognitive complexity 31 (threshold 15). Drivers by points: if/else 13 (22 pts), match/switch 4 (7 pts), boolean chains 2 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":3445}}}],"partialFingerprints":{"codehealthFindingId/v1":"d81a894596c48e5db3b415a9fd434a78ff475762a480c2b8b1c2434cbaa363c8"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveDeserializer.apply (cognitive 31): ResolveDeserializer.apply has cognitive complexity 31 (threshold 15). Drivers by points: match/switch 7 (24 pts), if/else 5 (7 pts) (nesting depth added 19). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":4103}}}],"partialFingerprints":{"codehealthFindingId/v1":"da262be7d13bfd0676bd9c5ea4bc74b496635eab12031aa8de5c35029febbb5f"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnResolutionHelper.resolveExpression (cognitive 31): ColumnResolutionHelper.resolveExpression has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (20 pts), match/switch 4 (7 pts), boolean chains 3, error handling 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ColumnResolutionHelper.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"4df054bf3dd4d07dc78f5e7cbe050a3f197de464f0f7e873c5ab9211b58b9010"}},{"ruleId":"D2","level":"warning","message":{"text":"GetJsonObjectEvaluator.evaluatePath (cognitive 31): GetJsonObjectEvaluator.evaluatePath has cognitive complexity 31 (threshold 15). Drivers by points: if/else 11 (18 pts), loops 5 (10 pts), match/switch 2 (3 pts) (nesting depth added 13). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1435}}}],"partialFingerprints":{"codehealthFindingId/v1":"57713c401f03689d65c24a2e2a54070e54caad963be081b4269e006095ebdc45"}},{"ruleId":"D2","level":"warning","message":{"text":"BaseGenericInternalRow.equals (cognitive 31): BaseGenericInternalRow.equals has cognitive complexity 31 (threshold 15). Drivers by points: if/else 10 (24 pts), boolean chains 3, match/switch 1 (3 pts), loops 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc20c80bbb878e41b59cef627f71838c6bde16e75fe9d7ca12e1023a9a6335a7"}},{"ruleId":"D2","level":"warning","message":{"text":"InjectRuntimeFilter.tryInjectRuntimeFilter (cognitive 31): InjectRuntimeFilter.tryInjectRuntimeFilter has cognitive complexity 31 (threshold 15). Drivers by points: if/else 7 (14 pts), boolean chains 11, match/switch 3 (6 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"d33c4e20b250ab76ed8e7d80d66565638b6bd6fc06675b599d4c6a908b2b9b59"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneratorNestedColumnAliasing.unapply (cognitive 31): GeneratorNestedColumnAliasing.unapply has cognitive complexity 31 (threshold 15). Drivers by points: match/switch 6 (16 pts), if/else 8 (11 pts), boolean chains 4 (nesting depth added 13). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e79e0052d3eb9e89a409fbf3125001cf05c697c6abfca88f19667357bd10713"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcUtils.requestedColumnIds (cognitive 31): OrcUtils.requestedColumnIds has cognitive complexity 31 (threshold 15). Drivers by points: if/else 15 (26 pts), match/switch 3, boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"35f160e67500486e9acb3dc7739f0f5b3326b4d3d746d2954940d5eda006e1a0"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkShreddingUtils.buildVariantSchema (cognitive 31): SparkShreddingUtils.buildVariantSchema has cognitive complexity 31 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 5 (12 pts), boolean chains 3 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":559}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1940b108e4807d9c775d90f59139f9b55d69ac12a624dcc21025de17dd52939"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ScanRelationPushDown.pushVariantExtractions (cognitive 31): V2ScanRelationPushDown.pushVariantExtractions has cognitive complexity 31 (threshold 15). Drivers by points: if/else 15 (20 pts), boolean chains 5, match/switch 2 (4 pts), loops 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":451}}}],"partialFingerprints":{"codehealthFindingId/v1":"769784e70cbec34ef22fec8c49127cb269bc8e82ecab9d2eeb0049156d227a02"}},{"ruleId":"D2","level":"warning","message":{"text":"BroadcastRangeJoinExec.makeCandidateFn (cognitive 31): BroadcastRangeJoinExec.makeCandidateFn has cognitive complexity 31 (threshold 15). Drivers by points: if/else 16 (26 pts), match/switch 3 (5 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4f284746768cf90deff5b4cf526bb79ad1b273ff7357581e38d682e9d0d5e2b"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamExecution.runStream (cognitive 31): StreamExecution.runStream has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (19 pts), error handling 4 (6 pts), boolean chains 3, match/switch 2 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"2eb468ff120575f84628a6a6f0d5eb760755a32fce769bbfb452625df563637c"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantShreddingWriter.castShredded (cognitive 31): VariantShreddingWriter.castShredded has cognitive complexity 31 (threshold 15). Drivers by points: if/else 13 (22 pts), loops 3 (7 pts), boolean chains 2 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantShreddingWriter.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcb7c24b2d0028e151d80669d6022de0009be6d21ac983bf1f47562fd9d20467"}},{"ruleId":"D2","level":"warning","message":{"text":"RecordBinaryComparator.compare (cognitive 31): RecordBinaryComparator.compare has cognitive complexity 31 (threshold 15). Drivers by points: if/else 7 (15 pts), ternaries 2 (7 pts), loops 3 (5 pts), boolean chains 4 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"c747f132ea38d00f7ff872ae9b8d08606146412e29820874950f6da405d9d3bd"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.compute_merge_default_fix_versions (cognitive 31): merge_spark_pr.compute_merge_default_fix_versions has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (28 pts), loops 2, boolean chains 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"618680ba54adbb911a20df09615ba0fb44356871da09eff59c9aa3608796106e"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.choose_jira_assignee (cognitive 31): merge_spark_pr.choose_jira_assignee has cognitive complexity 31 (threshold 15). Drivers by points: if/else 6 (14 pts), error handling 4 (10 pts), loops 2 (3 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":2088}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d373d3966b209bbab17f6f2d28aa06aba54401d06c1c55e7c9342624b59230b"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.droplevel (cognitive 31): DataFrame.droplevel has cognitive complexity 31 (threshold 15). Drivers by points: if/else 11 (29 pts), loops 1 (2 pts) (nesting depth added 19). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7636}}}],"partialFingerprints":{"codehealthFindingId/v1":"99eb9c006755f8ad3dead4977441ea9466da3e4862121c2a26ea12bedc5bda6c"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.rename (cognitive 31): DataFrame.rename has cognitive complexity 31 (threshold 15). Drivers by points: if/else 15 (24 pts), boolean chains 4, loops 1 (3 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12140}}}],"partialFingerprints":{"codehealthFindingId/v1":"af6f11e5db188858529d424719d75bd96dc559fcfa8571086ea6956bfe76ccac"}},{"ruleId":"D2","level":"warning","message":{"text":"UserCredentialManager.resolveCredentials (cognitive 30): UserCredentialManager.resolveCredentials has cognitive complexity 30 (threshold 15). Drivers by points: if/else 8 (17 pts), error handling 2 (7 pts), match/switch 1 (5 pts), loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/security/UserCredentialManager.scala"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dffcb2a77c2c2062aebf94e9328fbf9cc710f18e648a7ba228665309ff73000"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.handleFailedTask (cognitive 30): TaskSetManager.handleFailedTask has cognitive complexity 30 (threshold 15). Drivers by points: if/else 17 (27 pts), boolean chains 2, match/switch 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1001}}}],"partialFingerprints":{"codehealthFindingId/v1":"212ede0b05b6e4b7243fc630b38575b2d87a93829deefce1527c8e76a805f7f6"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockStoreUpdater.save (cognitive 30): BlockStoreUpdater.save has cognitive complexity 30 (threshold 15). Drivers by points: if/else 17 (24 pts), boolean chains 4, error handling 1 (2 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":536}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7af1fc3d1e9fbed192d5315ae02f87ab1c2d3dc3f0df81067eb106c9660de40"}},{"ruleId":"D2","level":"warning","message":{"text":"EdgePartition.aggregateMessagesIndexScan (cognitive 30): EdgePartition.aggregateMessagesIndexScan has cognitive complexity 30 (threshold 15). Drivers by points: if/else 18 (26 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfacc4bfe39df9f9dc014e343c4a239be47aeec45068fdd9eb95fb03ccc1174c"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemv (cognitive 30): BLAS.gemv has cognitive complexity 30 (threshold 15). Drivers by points: if/else 11 (17 pts), loops 4 (11 pts), boolean chains 2 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":774}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac5e71202a357d4f316f1a68f29f1706b138b8615eb1cba7f46e7db4b3872eda"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.argmax (cognitive 30): SparseVector.argmax has cognitive complexity 30 (threshold 15). Drivers by points: if/else 8 (16 pts), loops 3 (11 pts), boolean chains 3 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":735}}}],"partialFingerprints":{"codehealthFindingId/v1":"607effa33c727a61c38c369043a15ddeb06fd30ae38cc14bee4720cf2a57cfe6"}},{"ruleId":"D2","level":"warning","message":{"text":"DecisionTreeMetadata.buildMetadata (cognitive 30): DecisionTreeMetadata.buildMetadata has cognitive complexity 30 (threshold 15). Drivers by points: if/else 15 (22 pts), match/switch 5 (8 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"70b933a5ba8c10f52f059dc882be338daa711683fe2d0012bf6fd237f4126942"}},{"ruleId":"D2","level":"warning","message":{"text":"RankingMetrics.ndcgAt (cognitive 30): RankingMetrics.ndcgAt has cognitive complexity 30 (threshold 15). Drivers by points: if/else 11 (26 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"b991a0d1427ed24c522db5c7b10c4a25d570199cddd6e8e1a4102db7e75449f1"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemv (cognitive 30): BLAS.gemv has cognitive complexity 30 (threshold 15). Drivers by points: if/else 11 (17 pts), loops 4 (11 pts), boolean chains 2 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala"},"region":{"startLine":651}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bd4b7b4ffb4ae224a311f2608f31388fdc3a385808cf59957004c5dafb2b650"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.argmax (cognitive 30): SparseVector.argmax has cognitive complexity 30 (threshold 15). Drivers by points: if/else 8 (16 pts), loops 3 (11 pts), boolean chains 3 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala"},"region":{"startLine":890}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b7845b2c61d3262716e803a39342a150e6de404073c452dfb21210bb5095385"}},{"ruleId":"D2","level":"warning","message":{"text":"RowMatrix.computeSVD (cognitive 30): RowMatrix.computeSVD has cognitive complexity 30 (threshold 15). Drivers by points: if/else 12 (17 pts), loops 3 (6 pts), boolean chains 5, match/switch 2 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":341}}}],"partialFingerprints":{"codehealthFindingId/v1":"b23fe2aa44e926b0e2b92685e1b3fc24a6b41dd78b3357e038df4d64422e89e0"}},{"ruleId":"D2","level":"warning","message":{"text":"RowMatrix.columnSimilaritiesDIMSUM (cognitive 30): RowMatrix.columnSimilaritiesDIMSUM has cognitive complexity 30 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 4 (10 pts), boolean chains 4, match/switch 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":722}}}],"partialFingerprints":{"codehealthFindingId/v1":"f23be675f131252624e67fbd0ff0e46e15f76453b20d522f12338c426ffe7780"}},{"ruleId":"D2","level":"warning","message":{"text":"BasicExecutorFeatureStep.configurePod (cognitive 30): BasicExecutorFeatureStep.configurePod has cognitive complexity 30 (threshold 15). Drivers by points: if/else 23 (26 pts), boolean chains 2, match/switch 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b4e1d81a8807358108ad85bddde872a19e0587169e24e44d51f35341e57a5b5"}},{"ruleId":"D2","level":"warning","message":{"text":"FunctionResolution.validateFunction (cognitive 30): FunctionResolution.validateFunction has cognitive complexity 30 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 7, match/switch 3 (5 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"e373baedd6ca5a9a94309c6a9431a1efd85b58641ef5c6fa81eb25b18193e692"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveIdentifierClause.apply0 (cognitive 30): ResolveIdentifierClause.apply0 has cognitive complexity 30 (threshold 15). Drivers by points: if/else 10 (21 pts), match/switch 3 (6 pts), boolean chains 3 (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveIdentifierClause.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2ab0da66339c37a859dcede6eab2e5a54274e0a3f4646848dcdd65e08aef71e"}},{"ruleId":"D2","level":"warning","message":{"text":"TableOutputResolver.resolveColumnsByPosition (cognitive 30): TableOutputResolver.resolveColumnsByPosition has cognitive complexity 30 (threshold 15). Drivers by points: if/else 17 (24 pts), boolean chains 3, match/switch 2 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d276da80d487de521ea0be66eb27620d4e43535e1a4f6073633dd3d6cde96be"}},{"ruleId":"D2","level":"warning","message":{"text":"ImplicitTypeCoercion.apply (cognitive 30): ImplicitTypeCoercion.apply has cognitive complexity 30 (threshold 15). Drivers by points: if/else 15 (23 pts), match/switch 3 (5 pts), boolean chains 2 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"4aa62324d69e3e32d80884827715ad72c3d9fd27c03f30d13442c3dd9f084088"}},{"ruleId":"D2","level":"warning","message":{"text":"ToNumberParser.checkInputDataTypes (cognitive 30): ToNumberParser.checkInputDataTypes has cognitive complexity 30 (threshold 15). Drivers by points: if/else 14 (15 pts), match/switch 7 (9 pts), boolean chains 5, loops 1 (nesting depth added 3). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc5685818f75d7a224565a867a491be67fe72e1e4a940a6fa96306a46e9c8e69"}},{"ruleId":"D2","level":"warning","message":{"text":"WorkerInputStream.read (cognitive 30): WorkerInputStream.read has cognitive complexity 30 (threshold 15). Drivers by points: if/else 9 (23 pts), loops 2 (4 pts), boolean chains 3 (nesting depth added 16). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9efa668d317e4949aec7da70c3dd3386350749fc13c1f42f7e2cd6201e9da80"}},{"ruleId":"D2","level":"warning","message":{"text":"InsertIntoHiveTable.processInsert (cognitive 30): InsertIntoHiveTable.processInsert has cognitive complexity 30 (threshold 15). Drivers by points: if/else 10 (24 pts), match/switch 1 (4 pts), boolean chains 2 (nesting depth added 17). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a3138404bf5633479406dd920f32740f99dca4c307abde1ed67678a7b187c11"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.levenshteinDistance (cognitive 30): UTF8String.levenshteinDistance has cognitive complexity 30 (threshold 15). Drivers by points: if/else 13 (20 pts), ternaries 3 (6 pts), loops 3 (4 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":2228}}}],"partialFingerprints":{"codehealthFindingId/v1":"43f09444e17ba7d72c8b6c933178241415ea9c34905cbb081c458031f28b81f2"}},{"ruleId":"D2","level":"warning","message":{"text":"instrumentation_utils._attach (cognitive 30): instrumentation_utils._attach has cognitive complexity 30 (threshold 15). Drivers by points: loops 8 (13 pts), if/else 4 (10 pts), error handling 1 (3 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/instrumentation_utils.py"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfd1dffcf19ff2ee3dd227aee1951327c3362820efb511f984764fa1a6623823"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.select_dtypes (cognitive 30): DataFrame.select_dtypes has cognitive complexity 30 (threshold 15). Drivers by points: if/else 9 (11 pts), error handling 4 (8 pts), loops 5, ternaries 2 (4 pts), boolean chains 2 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7453}}}],"partialFingerprints":{"codehealthFindingId/v1":"a33d1147fa8fd00d9a00f24003df71a5c9b1f352a622816b71b0b2fa8555b9a3"}},{"ruleId":"D2","level":"warning","message":{"text":"worker.invoke_udf (cognitive 30): worker.invoke_udf has cognitive complexity 30 (threshold 15). Drivers by points: if/else 12 (19 pts), error handling 4 (8 pts), loops 1 (3 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/worker.py"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"c45bf25dee894c823b23984ae143c769c76dd1bddedbb394c8a43a3f8202c98b"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 30): (anonymous) has cognitive complexity 30 (threshold 15). Drivers by points: if/else 11 (14 pts), ternaries 5 (9 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 8). Most of this is not in the body itself: 2 of the 30 points are its own statements and the rest belongs to 16 function items inside it that branch (a function literal at line 126, a function literal at line 291, a function literal at line 171, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/historypage.js"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"a90207831f045cc4d10563f9637dd44569cfb29413b0484b768a4abf4d874ee3"}},{"ruleId":"D2","level":"warning","message":{"text":"FsHistoryProvider.checkForLogsInDir (cognitive 29): FsHistoryProvider.checkForLogsInDir has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (17 pts), error handling 7 (10 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":635}}}],"partialFingerprints":{"codehealthFindingId/v1":"c993f4de30975627ab8285581a59d76d0779ce585119743efbe2c82ecf7638c1"}},{"ruleId":"D2","level":"warning","message":{"text":"NettyBlockRpcServer.receive (cognitive 29): NettyBlockRpcServer.receive has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (25 pts), error handling 2, boolean chains 1, match/switch 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/network/netty/NettyBlockRpcServer.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"d79e8643dfd4a8b76fc2e6bdbeebdd4fbef1c05fb382711af4ed09ab335b9438"}},{"ruleId":"D2","level":"warning","message":{"text":"AppStatusListener.onTaskEnd (cognitive 29): AppStatusListener.onTaskEnd has cognitive complexity 29 (threshold 15). Drivers by points: if/else 23 (24 pts), boolean chains 3, match/switch 2 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":669}}}],"partialFingerprints":{"codehealthFindingId/v1":"7adf821300f8d747cf028f720facea957fcf37242230e1cd67a1ab87c1c8f307"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManager.getLocalValues (cognitive 29): BlockManager.getLocalValues has cognitive complexity 29 (threshold 15). Drivers by points: if/else 10 (22 pts), boolean chains 3, error handling 1 (3 pts), match/switch 1 (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1151}}}],"partialFingerprints":{"codehealthFindingId/v1":"12f37a52af677f0d084486aebe33e4168052ce5e5dfc01d8c267f93ef5cddbc8"}},{"ruleId":"D2","level":"warning","message":{"text":"AllJobsPage.render (cognitive 29): AllJobsPage.render has cognitive complexity 29 (threshold 15). Drivers by points: if/else 19 (25 pts), boolean chains 2, match/switch 2 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"393022dac00fc2569ebbc6b3be41b2045ee73b1dce4da013bde182162debd877"}},{"ruleId":"D2","level":"warning","message":{"text":"ImageSchema.decode (cognitive 29): ImageSchema.decode has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 4 (14 pts), error handling 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/image/ImageSchema.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dc953e7a103d47c1385f5515b1f72145625a99148e4a63655ca2e4c62ff3895"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomForest.findBestSplits (cognitive 29): RandomForest.findBestSplits has cognitive complexity 29 (threshold 15). Drivers by points: if/else 19 (26 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"29cebde49ac742de7e4e1081f4531631b4c8fe6fd8c243ac63386900b25470ad"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkDateTimeUtils.stringToDate (cognitive 29): SparkDateTimeUtils.stringToDate has cognitive complexity 29 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 9, error handling 1, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":577}}}],"partialFingerprints":{"codehealthFindingId/v1":"48cfe338b68242b80c7da4bf6a7346d25b566d209df1b2bd8fe6c6d6612c6263"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkDateTimeUtils.stringToTime (cognitive 29): SparkDateTimeUtils.stringToTime has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (21 pts), boolean chains 7, error handling 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1098}}}],"partialFingerprints":{"codehealthFindingId/v1":"98c6189e692c0800bbcf3e0ec28abac2001241d191b9a4cf3a22306fa60411e1"}},{"ruleId":"D2","level":"warning","message":{"text":"TableOutputResolver.reorderColumnsByName (cognitive 29): TableOutputResolver.reorderColumnsByName has cognitive complexity 29 (threshold 15). Drivers by points: if/else 17 (25 pts), match/switch 2 (4 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"797f1938d81db340348b969aedd92162dc53526d2d276361b20d32290f910b23"}},{"ruleId":"D2","level":"warning","message":{"text":"FunctionArgumentTypeCoercion.apply (cognitive 29): FunctionArgumentTypeCoercion.apply has cognitive complexity 29 (threshold 15). Drivers by points: match/switch 11 (21 pts), boolean chains 7, if/else 1 (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e4b83c2d8e42f0fde3fc079592175597d1094221dfe42fa2a4a1ebce7936c2d"}},{"ruleId":"D2","level":"warning","message":{"text":"JacksonParser.parseIterator (cognitive 29): JacksonParser.parseIterator has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (14 pts), error handling 8, match/switch 3 (4 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":908}}}],"partialFingerprints":{"codehealthFindingId/v1":"67c9ff5f1899810729bfa3eec006d95593f0e1b80a30fb5a6d114bd6c12386fa"}},{"ruleId":"D2","level":"warning","message":{"text":"InferWindowGroupLimit.apply (cognitive 29): InferWindowGroupLimit.apply has cognitive complexity 29 (threshold 15). Drivers by points: if/else 10 (20 pts), match/switch 3 (6 pts), boolean chains 3 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InferWindowGroupLimit.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"f23c769162cf8af84831bb2fdf2feb1a37c36b87c3ce01f7f67259c8ec51e11c"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.withSample (cognitive 29): AstBuilder.withSample has cognitive complexity 29 (threshold 15). Drivers by points: if/else 17 (25 pts), boolean chains 3, match/switch 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2828}}}],"partialFingerprints":{"codehealthFindingId/v1":"60f89cdaae342bf198d903da62d0ac6226a0da960acd268efce368767b025e47"}},{"ruleId":"D2","level":"warning","message":{"text":"ToNumberParser.format (cognitive 29): ToNumberParser.format has cognitive complexity 29 (threshold 15). Drivers by points: if/else 12 (23 pts), boolean chains 3, match/switch 1 (2 pts), loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":649}}}],"partialFingerprints":{"codehealthFindingId/v1":"523bc8ac8db6af43a939c764f05029c2624d5579eac61e3dfb2d28a67061e3c1"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowDeserializers.deserializerForDefault (cognitive 29): ArrowDeserializers.deserializerForDefault has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (18 pts), loops 3 (9 pts), boolean chains 1, match/switch 1 (nesting depth added 11). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b197bc916d89f2757e3ada42d3eaa979d85d9a0d210ceb3a3a7e9d848466df3"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveDataSource.apply (cognitive 29): ResolveDataSource.apply has cognitive complexity 29 (threshold 15). Drivers by points: if/else 12 (18 pts), match/switch 5 (9 pts), boolean chains 2 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"995f739c17aa9696386c980aad602b8aacda01ee73f6fee0b3e9e8f71c01e7f0"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcUtils.createAggInternalRowFromFooter (cognitive 29): OrcUtils.createAggInternalRowFromFooter has cognitive complexity 29 (threshold 15). Drivers by points: if/else 17 (22 pts), match/switch 4 (6 pts), error handling 1 (nesting depth added 7). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"149bfc1e06ef35ffaa23c85ea239a54f91aeaa7c487f22227eeef27b478e7f2d"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetReadSupport.findCheapestGroupField (cognitive 29): ParquetReadSupport.findCheapestGroupField has cognitive complexity 29 (threshold 15). Drivers by points: if/else 6 (16 pts), boolean chains 5, match/switch 3 (5 pts), loops 1 (3 pts) (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadSupport.scala"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c106e917bda560e02683f570151b1239ba1f9360fab838d75e6c8fa29e89de9"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeJoinExec.doProduce (cognitive 29): SortMergeJoinExec.doProduce has cognitive complexity 29 (threshold 15). Drivers by points: if/else 15, match/switch 9 (13 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":448}}}],"partialFingerprints":{"codehealthFindingId/v1":"45aff8fac4d53e8727921a04074099b42e269721cec25d7701ef3855abbe120f"}},{"ruleId":"D2","level":"warning","message":{"text":"UserDefinedPythonFunction.builder (cognitive 29): UserDefinedPythonFunction.builder has cognitive complexity 29 (threshold 15). Drivers by points: if/else 17 (19 pts), boolean chains 6, match/switch 2 (4 pts) (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbae1821ce697b61c9a2f88ffe292abc1aa88d3d5de90ad4a18f5dc42040b0e6"}},{"ruleId":"D2","level":"warning","message":{"text":"MicroBatchExecution.populateStartOffsets (cognitive 29): MicroBatchExecution.populateStartOffsets has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (15 pts), match/switch 5 (14 pts) (nesting depth added 16). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7557e5820c7f45be0db9274ea3bdb889b838c8b74fb696f59464d140f70cf48"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.trimRight (cognitive 29): CollationAwareUTF8String.trimRight has cognitive complexity 29 (threshold 15). Drivers by points: if/else 10 (17 pts), loops 5 (9 pts), boolean chains 3 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1588}}}],"partialFingerprints":{"codehealthFindingId/v1":"79b4925e261a47d009145c24674fa8933ea354aea7a5c125ad54d2469e20098e"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegressionModel.predict (cognitive 29): LogisticRegressionModel.predict has cognitive complexity 29 (threshold 15). Drivers by points: if/else 11 (20 pts), loops 2 (6 pts), ternaries 1 (3 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":235}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bc2d2b7cd50b87b4eae76cff5c7e5fe521333bc2d195c56ef15a1acd21c5470"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasToArrowConversion._convert_column_legacy (cognitive 29): PandasToArrowConversion._convert_column_legacy has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (18 pts), error handling 5 (10 pts), ternaries 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fa911470e49ce3d2baab8ae344ba1c8232180575e6ad10d739811cd1e5528d2"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowTableToRowsConversion._to_pylist (cognitive 29): ArrowTableToRowsConversion._to_pylist has cognitive complexity 29 (threshold 15). Drivers by points: if/else 10 (17 pts), ternaries 4 (9 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1141}}}],"partialFingerprints":{"codehealthFindingId/v1":"decd14c83e2fba15c55ef381e598ee940752d7710f29dd0842848965c79412d4"}},{"ruleId":"D2","level":"warning","message":{"text":"MapOutputTrackerWorker.getStatuses (cognitive 28): MapOutputTrackerWorker.getStatuses has cognitive complexity 28 (threshold 15). Drivers by points: if/else 9 (18 pts), error handling 2 (8 pts), boolean chains 2 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1618}}}],"partialFingerprints":{"codehealthFindingId/v1":"89727bf67acee331d67fbc88ffb185b47f93d6676dacd6f449c1e19a8dbadc45"}},{"ruleId":"D2","level":"warning","message":{"text":"Master.schedule (cognitive 28): Master.schedule has cognitive complexity 28 (threshold 15). Drivers by points: if/else 7 (14 pts), loops 3 (7 pts), match/switch 1 (4 pts), boolean chains 3 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":961}}}],"partialFingerprints":{"codehealthFindingId/v1":"d67a235dff28869c7bb849fd7c6759b9fb33356b97b751cdcfdaec084d12be12"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.cleanupStagesForJob (cognitive 28): DAGScheduler.cleanupStagesForJob has cognitive complexity 28 (threshold 15). Drivers by points: if/else 8 (20 pts), loops 2 (7 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":1738}}}],"partialFingerprints":{"codehealthFindingId/v1":"f61b7f57882b8f4a2b8e0786c240d254441854fa3b1becf9e40f5bb4544d46af"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegression.createBounds (cognitive 28): LogisticRegression.createBounds has cognitive complexity 28 (threshold 15). Drivers by points: if/else 12 (26 pts), loops 1 (2 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":730}}}],"partialFingerprints":{"codehealthFindingId/v1":"66aa7b5ec587e7b7b2b1c63173a1e170b2e9f4b32769a8220067557f956dc851"}},{"ruleId":"D2","level":"warning","message":{"text":"NNLS.solve (cognitive 28): NNLS.solve has cognitive complexity 28 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 4 (7 pts), boolean chains 2 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/NNLS.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"57ba5a55bac55f2eb972cfc3ac7c6660165b26c1da0393d2eb0a5382c3383a34"}},{"ruleId":"D2","level":"warning","message":{"text":"ApplicationMaster.allocationThreadImpl (cognitive 28): ApplicationMaster.allocationThreadImpl has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (18 pts), error handling 4 (8 pts), boolean chains 1, loops 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala"},"region":{"startLine":587}}}],"partialFingerprints":{"codehealthFindingId/v1":"96a9d2bd4e7c4e7a55685e378a7d41111033c2ca44d51528ac2dee9b8682f97f"}},{"ruleId":"D2","level":"warning","message":{"text":"CodeCompiler.forEachJavaSpan (cognitive 28): CodeCompiler.forEachJavaSpan has cognitive complexity 28 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 2 (6 pts), boolean chains 5, loops 2 (4 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":552}}}],"partialFingerprints":{"codehealthFindingId/v1":"104ff5f58ef0d6ca15e815b44354f79d673f5067f1e57b8d8f7754c7e7501317"}},{"ruleId":"D2","level":"warning","message":{"text":"InlineCTE.inlineCTE (cognitive 28): InlineCTE.inlineCTE has cognitive complexity 28 (threshold 15). Drivers by points: if/else 13 (23 pts), match/switch 3 (5 pts) (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InlineCTE.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"369f80e69085f5f22bef819f7adc8e90438bfcb82a76da6529b20731873c1c98"}},{"ruleId":"D2","level":"warning","message":{"text":"RewriteCorrelatedScalarSubquery.constructLeftJoins (cognitive 28): RewriteCorrelatedScalarSubquery.constructLeftJoins has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (18 pts), match/switch 3 (8 pts), boolean chains 2 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":901}}}],"partialFingerprints":{"codehealthFindingId/v1":"f93209a6d40cccea02322564d3713a3abb6ee462b39dc89526bec4ee2c50ca28"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitMergeIntoTable (cognitive 28): AstBuilder.visitMergeIntoTable has cognitive complexity 28 (threshold 15). Drivers by points: if/else 20 (24 pts), boolean chains 4 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1274}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bf607de746c8711ebc198c8ae70dff5e4e9241351a5e44d1b18d8c00630de8f"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaUtils.validateTypeCompatibility (cognitive 28): SchemaUtils.validateTypeCompatibility has cognitive complexity 28 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 2 (9 pts), boolean chains 4, match/switch 2 (3 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"33e159206bf3d9a151a61610f53fd42238d5341c6b0eb18f7a2672e112604714"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowSerializer.serializerForDefault (cognitive 28): ArrowSerializer.serializerForDefault has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (19 pts), match/switch 4 (8 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowSerializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"362f735897b7d64179b953ae4a26c412e6c520940231c4db42b299ef5502b430"}},{"ruleId":"D2","level":"warning","message":{"text":"ArtifactManager.addArtifact (cognitive 28): ArtifactManager.addArtifact has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (26 pts), boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/artifact/ArtifactManager.scala"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e50401290d53e858effce8583a57a3b799137cf874bbf5665f40db72ffd1e8d"}},{"ruleId":"D2","level":"warning","message":{"text":"TruncateTableCommand.run (cognitive 28): TruncateTableCommand.run has cognitive complexity 28 (threshold 15). Drivers by points: error handling 5 (14 pts), if/else 8 (10 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":449}}}],"partialFingerprints":{"codehealthFindingId/v1":"73b2e7fa60313b41fe80f6ffeec49edfdb5c8818fc6c0a61ae75713e7df588b4"}},{"ruleId":"D2","level":"warning","message":{"text":"PullOutVariantExtractions.pushSideAliases (cognitive 28): PullOutVariantExtractions.pushSideAliases has cognitive complexity 28 (threshold 15). Drivers by points: if/else 12 (21 pts), match/switch 2 (5 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PullOutVariantExtractions.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff9859597f020a5469dc086d6130523cf739b4fb13d6fe986553592a5241df2b"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetRowConverter.newConverterDefault (cognitive 28): ParquetRowConverter.newConverterDefault has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (14 pts), match/switch 5 (8 pts), boolean chains 6 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"47951b9ad00d2af6914dabb176c46dce6b287015e61b513b39cb11df4c89c403"}},{"ruleId":"D2","level":"warning","message":{"text":"DistributionAndOrderingUtils.prepareQuery (cognitive 28): DistributionAndOrderingUtils.prepareQuery has cognitive complexity 28 (threshold 15). Drivers by points: if/else 14 (24 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 11). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DistributionAndOrderingUtils.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc5f5a09dd370ca6016a54c94fe427c00b7cf83a4fac8815a7762c8715401390"}},{"ruleId":"D2","level":"warning","message":{"text":"NativePartitionReader.checkArrays (cognitive 28): NativePartitionReader.checkArrays has cognitive complexity 28 (threshold 15). Drivers by points: if/else 17, boolean chains 7, loops 1 (2 pts), match/switch 2 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c0668e6d3c15e144684bf58b864a72a395c449e1b4787ad8c2e02c00841a19b"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleStatefulProcessorCall (cognitive 28): TransformWithStateInPySparkStateServer.handleStatefulProcessorCall has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (23 pts), match/switch 3 (5 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8cabe55f56972f83413e0f8a472ba77be9853006a2c9abed9bec974d26b8df1"}},{"ruleId":"D2","level":"warning","message":{"text":"UnsafeRowDataEncoder.encodePrefixKeyForRangeScan (cognitive 28): UnsafeRowDataEncoder.encodePrefixKeyForRangeScan has cognitive complexity 28 (threshold 15). Drivers by points: if/else 14 (26 pts), match/switch 1 (2 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"92c7784302ab4f4b564612c0e72a31300c27fe9ec49d1ae17579b15d449a26af"}},{"ruleId":"D2","level":"warning","message":{"text":"TriggeredGraphExecution.topologicalExecution (cognitive 28): TriggeredGraphExecution.topologicalExecution has cognitive complexity 28 (threshold 15). Drivers by points: if/else 8 (14 pts), boolean chains 5, error handling 2 (4 pts), loops 2 (3 pts), match/switch 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/TriggeredGraphExecution.scala"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"e636da04c684c987b5f8cd89fc2efe1aae6841bd9fd312230ca21ae081e2e151"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.toInt (cognitive 28): UTF8String.toInt has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (18 pts), boolean chains 6, loops 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (UTF8String.toLong) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1922}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b253a5498715745f23a614593b25f950f809f571ab377c67a52ca4115938c4d"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.toLong (cognitive 28): UTF8String.toLong has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (18 pts), boolean chains 6, loops 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (UTF8String.toInt) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1825}}}],"partialFingerprints":{"codehealthFindingId/v1":"17faf442b8e822bc7c088f57b26ed77007e8b77512d866b1daeeaf2799ca22ad"}},{"ruleId":"D2","level":"warning","message":{"text":"MutableColumnarRow.copy (cognitive 28): MutableColumnarRow.copy has cognitive complexity 28 (threshold 15). Drivers by points: if/else 23 (26 pts), boolean chains 1, loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"5929b3ce5ac3e1944e566a00a45da045ced84eaa08c7a93c6338f6fba44a7158"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.prepare_merge_title (cognitive 28): merge_spark_pr.prepare_merge_title has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (22 pts), boolean chains 2, error handling 1 (2 pts), loops 1 (2 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3015}}}],"partialFingerprints":{"codehealthFindingId/v1":"081a6dd71fd212cc99332bca0030b8475d96ce9b45757c9142abc68b445bb6d8"}},{"ruleId":"D2","level":"warning","message":{"text":"structured_logging_style.main (cognitive 28): structured_logging_style.main has cognitive complexity 28 (threshold 15). Drivers by points: if/else 6 (15 pts), loops 5 (12 pts), boolean chains 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/structured_logging_style.py"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"a226356a90b34c76f3f99de803dd9dcbf05dbf6b8e0ef52d7de3b0ceda8936e8"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.__init__ (cognitive 28): DataFrame.__init__ has cognitive complexity 28 (threshold 15). Drivers by points: if/else 13 (23 pts), ternaries 1 (3 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":553}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c44e3815af90fb089b75166c42134bfd25464b944d10a0b8e2ad9ef721eb4df"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.corrwith (cognitive 28): DataFrame.corrwith has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (19 pts), loops 4 (8 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1765}}}],"partialFingerprints":{"codehealthFindingId/v1":"909d55e1661257b56c1d9945f8ef54a9205db14fe042335c9447683a3b86d963"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.align (cognitive 28): DataFrame.align has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (19 pts), boolean chains 4, loops 2 (4 pts), ternaries 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13800}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad04919cdc1a5b046a5a3762180b625e275dbd1f6f822e03fad492910ce2f83c"}},{"ruleId":"D2","level":"warning","message":{"text":"InternalFrame.with_new_columns (cognitive 28): InternalFrame.with_new_columns has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (22 pts), loops 3 (6 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":1275}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8288804667412b36be0af836aa9826acf85ff8f1d2c4de9d3387d17d9d79e36"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasSQLStringFormatter._convert_value (cognitive 28): PandasSQLStringFormatter._convert_value has cognitive complexity 28 (threshold 15). Drivers by points: if/else 9 (21 pts), loops 2 (7 pts) (nesting depth added 17). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/sql_formatter.py"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"675755ceb2073a6fa20d0d93fb0da269bda83f9ee0c6cbda5e5bf0d613bbd3fb"}},{"ruleId":"D2","level":"warning","message":{"text":"types.parse_attr_name (cognitive 28): types.parse_attr_name has cognitive complexity 28 (threshold 15). Drivers by points: if/else 10 (24 pts), boolean chains 3, loops 1 (nesting depth added 14). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5b7f7aef08f14fbd0e8c008f745456fc94c7a22448d23b1e295334e754a028b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConversionMixin._create_from_pandas_with_arrow (cognitive 28): SparkConversionMixin._create_from_pandas_with_arrow has cognitive complexity 28 (threshold 15). Drivers by points: if/else 10 (18 pts), loops 2 (6 pts), ternaries 2 (3 pts), boolean chains 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":907}}}],"partialFingerprints":{"codehealthFindingId/v1":"03319d2d46ca4d9c5bc1b086bb4d3ae0640c56cdc9c930cb5ddac23367543095"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 28): (anonymous) has cognitive complexity 28 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 13, ternaries 1 (nesting depth added 4). Most of this is not in the body itself: 1 of the 28 points is its own statement and the rest belongs to 12 function items inside it that branch (init::renderSummary, a function literal at line 152, init::render, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":22}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab2b9fd0838770f2d5a4c297e967a87a0f8fb62e07fb9365b0f8a95018232603"}},{"ruleId":"D2","level":"warning","message":{"text":"updateDetailsPanel (cognitive 28): updateDetailsPanel has cognitive complexity 28 (threshold 15). Drivers by points: if/else 15 (19 pts), boolean chains 7, ternaries 2 (nesting depth added 4). Of this number, 19 points are the body\u0027s own statements and 9 belong to 4 function literals inside it that branch. To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"5871acc64ad20ecc64153670fa21ccb37f8cd75f6793365b4ee7e7f3dd98b3d8"}},{"ruleId":"D2","level":"warning","message":{"text":"ProtobufSerializer.newConverter (cognitive 27): ProtobufSerializer.newConverter has cognitive complexity 27 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 4, loops 2 (4 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a6647393898b6d76c013833336506f974366fc33fa99c947771095e81933376"}},{"ruleId":"D2","level":"warning","message":{"text":"FsHistoryProvider.doMergeApplicationListingInternal (cognitive 27): FsHistoryProvider.doMergeApplicationListingInternal has cognitive complexity 27 (threshold 15). Drivers by points: if/else 7 (14 pts), boolean chains 9, error handling 1 (3 pts), match/switch 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":1056}}}],"partialFingerprints":{"codehealthFindingId/v1":"e86eb14f7d60c9d59a454b047234ba8b415f9610b59b08e0a67c35efdb9a4b5d"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskReaper.run (cognitive 27): TaskReaper.run has cognitive complexity 27 (threshold 15). Drivers by points: if/else 11 (19 pts), error handling 1 (4 pts), boolean chains 3, loops 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":1274}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a2c6095436657897d7970ada5c40d6e6f1277bd276adff72559627e247891af"}},{"ruleId":"D2","level":"warning","message":{"text":"IndexShuffleBlockResolver.writeMetadataFileAndCommit (cognitive 27): IndexShuffleBlockResolver.writeMetadataFileAndCommit has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (20 pts), error handling 2 (4 pts), boolean chains 3 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39d63de2c38dcd9519d0aaa9e656b4d946e5aded2c1f6102a1efa82f0b5374c"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManager.doPutIterator (cognitive 27): BlockManager.doPutIterator has cognitive complexity 27 (threshold 15). Drivers by points: if/else 11 (20 pts), match/switch 2 (6 pts), boolean chains 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1864}}}],"partialFingerprints":{"codehealthFindingId/v1":"41217df64cec818883dee502112730e77ecb9d27595a8f11351043f26242782e"}},{"ruleId":"D2","level":"warning","message":{"text":"JobPage.render (cognitive 27): JobPage.render has cognitive complexity 27 (threshold 15). Drivers by points: if/else 19 (22 pts), boolean chains 3, loops 1, match/switch 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a1b1de8825df52955cd7039f356facd6363ba5c83a84476e33d276b126518e9"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.slice (cognitive 27): SparseVector.slice has cognitive complexity 27 (threshold 15). Drivers by points: if/else 6 (16 pts), loops 3 (8 pts), boolean chains 3 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":792}}}],"partialFingerprints":{"codehealthFindingId/v1":"251863ffc37ea97c58d3897521801a5105272404beca08fb2251a4cb167c08fb"}},{"ruleId":"D2","level":"warning","message":{"text":"YarnAllocator.updateResourceRequests (cognitive 27): YarnAllocator.updateResourceRequests has cognitive complexity 27 (threshold 15). Drivers by points: if/else 11 (21 pts), loops 1 (3 pts), match/switch 1 (2 pts), boolean chains 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":498}}}],"partialFingerprints":{"codehealthFindingId/v1":"6eebca590d8724463fe61d93be4b053ca52c46b837b9a9f0171c3814247e94c5"}},{"ruleId":"D2","level":"warning","message":{"text":"InterpretedUnsafeProjection.generateFieldWriter (cognitive 27): InterpretedUnsafeProjection.generateFieldWriter has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (17 pts), match/switch 5 (10 pts) (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/InterpretedUnsafeProjection.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"537e6f7cce38fceb7e264f28440156fe67a2a2ea17b4ff7693c15010592f5fb8"}},{"ruleId":"D2","level":"warning","message":{"text":"DivModLike.doGenCode (cognitive 27): DivModLike.doGenCode has cognitive complexity 27 (threshold 15). Drivers by points: if/else 17 (23 pts), boolean chains 3, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":750}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc9cc038a12ae6d0ee8432572bf3c6491b4bbeb3de2aabcd6bb6b863022f8c95"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonTableEvaluator.positionAt (cognitive 27): JsonTableEvaluator.positionAt has cognitive complexity 27 (threshold 15). Drivers by points: if/else 9 (18 pts), loops 2 (6 pts), boolean chains 2, match/switch 1 (nesting depth added 13). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":998}}}],"partialFingerprints":{"codehealthFindingId/v1":"352425a931eb4ee1dca09b51bec0cf94152114c0ea34f25c073e68b47c51bdcd"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonTable.checkInputDataTypes (cognitive 27): JsonTable.checkInputDataTypes has cognitive complexity 27 (threshold 15). Drivers by points: match/switch 6 (17 pts), if/else 6 (9 pts), boolean chains 1 (nesting depth added 14). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":459}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a3b25b4703e54c0b9ed6b204c2cad28e6a1f8fb18115401c9f88d7ba0ff812e"}},{"ruleId":"D2","level":"warning","message":{"text":"ReorderAssociativeOperator.apply (cognitive 27): ReorderAssociativeOperator.apply has cognitive complexity 27 (threshold 15). Drivers by points: if/else 10 (20 pts), boolean chains 4, match/switch 2 (3 pts) (nesting depth added 11). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"b22866c9bd40b2567867032d367e9ca4fc86ad3f8dd9aca3cbd439668484f662"}},{"ruleId":"D2","level":"warning","message":{"text":"XmlTokenizer.readUntilStartElement (cognitive 27): XmlTokenizer.readUntilStartElement has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (25 pts), boolean chains 1, loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1006}}}],"partialFingerprints":{"codehealthFindingId/v1":"f24c747ea1c8bb290d134f24004c9f68a3f2952bcc27e943aa98c6c739bbd2a9"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitCreateUserDefinedFunction (cognitive 27): SparkSqlAstBuilder.visitCreateUserDefinedFunction has cognitive complexity 27 (threshold 15). Drivers by points: if/else 9 (16 pts), loops 3 (6 pts), boolean chains 5 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"a85b0fb9eced94a2fa169b641c9a9cd147e9b486a5f404d4226463e6cf7d01f6"}},{"ruleId":"D2","level":"warning","message":{"text":"WholeStageCodegenExec.decideFromTrials (cognitive 27): WholeStageCodegenExec.decideFromTrials has cognitive complexity 27 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 4 (11 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"873bcd30729dbbf172d868b53a34e539e8dcd027184a416f6f98710b18766f89"}},{"ruleId":"D2","level":"warning","message":{"text":"PushDownShuffleExchangeThroughUnion.apply (cognitive 27): PushDownShuffleExchangeThroughUnion.apply has cognitive complexity 27 (threshold 15). Drivers by points: if/else 15 (19 pts), boolean chains 6, match/switch 2 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PushDownShuffleExchangeThroughUnion.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"8485aaf77982f3dc715e19263c15c6fcd0c7df31b384d83e47e424fbf055c845"}},{"ruleId":"D2","level":"warning","message":{"text":"FileSourceStrategy.apply (cognitive 27): FileSourceStrategy.apply has cognitive complexity 27 (threshold 15). Drivers by points: if/else 10 (15 pts), match/switch 6 (11 pts), boolean chains 1 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ab6ef58bee7a424ecc41d9e8706f22540e2b19a3a31e6667a811fb5b59ee01d"}},{"ruleId":"D2","level":"warning","message":{"text":"PreprocessTableCreation.apply (cognitive 27): PreprocessTableCreation.apply has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (23 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 11). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"7595f52c49726ba1dfb98e5b03ec3036996b6ef3080e73f38fee16ad2d8f0023"}},{"ruleId":"D2","level":"warning","message":{"text":"PrepareExternalLookupJoin.prepare (cognitive 27): PrepareExternalLookupJoin.prepare has cognitive complexity 27 (threshold 15). Drivers by points: if/else 15 (16 pts), match/switch 8 (9 pts), boolean chains 2 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9999fb6234b4cfb06c7bad0a32bb1709da311574c204be91709d7e12b6fa421"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleMapStateRequest (cognitive 27): TransformWithStateInPySparkStateServer.handleMapStateRequest has cognitive complexity 27 (threshold 15). Drivers by points: if/else 17 (26 pts), match/switch 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":595}}}],"partialFingerprints":{"codehealthFindingId/v1":"baccdd74931e56b2ae1a263bf2f7dd8cff2496b5b5439804a7320f926f3dc9e0"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDB.loadWithCheckpointId (cognitive 27): RocksDB.loadWithCheckpointId has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (19 pts), match/switch 1 (4 pts), boolean chains 3, error handling 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":474}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac0fdf5162d6e74394d95becff39698b77bfebb07b814620c191a31095f68676"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseIndexOfSlow (cognitive 27): CollationAwareUTF8String.lowercaseIndexOfSlow has cognitive complexity 27 (threshold 15). Drivers by points: if/else 11 (23 pts), loops 2 (4 pts) (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":836}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f82115f1712142235c5b2e0e52a54eeb4142b13fab67c375ef1e9471a2bab15"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ExpressionSQLBuilder.build (cognitive 27): V2ExpressionSQLBuilder.build has cognitive complexity 27 (threshold 15). Drivers by points: if/else 24 (27 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e45c233c997a1349d67ee7fe4a83bd60921b9e6dc11b2d927d0cc60697e677c"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnVectorUtils.appendValue (cognitive 27): ColumnVectorUtils.appendValue has cognitive complexity 27 (threshold 15). Drivers by points: if/else 24 (26 pts), boolean chains 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3cfb4c0aadaabdaa83e7a66ba54566e18529a5a06cc37b3845b1981e8fa372f"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._assign (cognitive 27): DataFrame._assign has cognitive complexity 27 (threshold 15). Drivers by points: if/else 6 (16 pts), loops 4 (5 pts), boolean chains 3, ternaries 3 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5852}}}],"partialFingerprints":{"codehealthFindingId/v1":"350212a12e248b58169f077d3d58f5c544ae6b1df29351039cbbdece82623492"}},{"ruleId":"D2","level":"warning","message":{"text":"Frame.to_csv (cognitive 27): Frame.to_csv has cognitive complexity 27 (threshold 15). Drivers by points: if/else 15 (19 pts), ternaries 2 (4 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"107f926da3294ead1e23b301db0b3c6cd70135272144a9e1bcb5c2301620316e"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.replace (cognitive 27): DataFrame.replace has cognitive complexity 27 (threshold 15). Drivers by points: if/else 18 (22 pts), boolean chains 5 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1550}}}],"partialFingerprints":{"codehealthFindingId/v1":"020f8efc053f6227be18372795f46978eb83711bdb283c53f8171a640c55d42c"}},{"ruleId":"D2","level":"warning","message":{"text":"transpile._transpile_func (cognitive 27): transpile._transpile_func has cognitive complexity 27 (threshold 15). Drivers by points: if/else 12 (15 pts), boolean chains 5, error handling 2 (4 pts), loops 2 (3 pts) (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":1399}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9597105216469591c123ee8cfcd4dff77d73f60bd96aa7ef1cc6b2317e2f942"}},{"ruleId":"D2","level":"warning","message":{"text":"FsHistoryProvider.skipToLineStart (cognitive 26): FsHistoryProvider.skipToLineStart has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (8 pts), boolean chains 3 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":1792}}}],"partialFingerprints":{"codehealthFindingId/v1":"1eddefffd398ef44ddc0de08d0037dd2fb7101976a9397a9db7d3ce404cc9405"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.executorLost (cognitive 26): TaskSetManager.executorLost has cognitive complexity 26 (threshold 15). Drivers by points: if/else 7 (13 pts), match/switch 2 (6 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1219}}}],"partialFingerprints":{"codehealthFindingId/v1":"bed9ec09e2d92d317fa41549b27e5f5e761764c6fa0b0d5e56013a99dc5feedf"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManagerMasterEndpoint.updateBlockInfo (cognitive 26): BlockManagerMasterEndpoint.updateBlockInfo has cognitive complexity 26 (threshold 15). Drivers by points: if/else 16 (22 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":828}}}],"partialFingerprints":{"codehealthFindingId/v1":"b90e4b207c457bc60086ad7bec7ef027326f37b8032537119d43eabdea731961"}},{"ruleId":"D2","level":"warning","message":{"text":"MemoryStore.putIterator (cognitive 26): MemoryStore.putIterator has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (22 pts), boolean chains 3, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"c14f7f52272b893c50972fabd23666de6fcb166b56731bf0616e27e6305e4e78"}},{"ruleId":"D2","level":"warning","message":{"text":"StronglyConnectedComponents.run (cognitive 26): StronglyConnectedComponents.run has cognitive complexity 26 (threshold 15). Drivers by points: if/else 9 (18 pts), boolean chains 5, loops 2 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/StronglyConnectedComponents.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5a38f84fb4a6c4773ec44d107868942fd7679583658a45ebae4b611cb6d471a"}},{"ruleId":"D2","level":"warning","message":{"text":"Postfix.project (cognitive 26): Postfix.project has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (21 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"90ab21bbf403be66508e1f497de0545d9231fdc0f7b31b2530f1122b3af2b9dc"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveQualify.apply (cognitive 26): ResolveQualify.apply has cognitive complexity 26 (threshold 15). Drivers by points: if/else 11 (21 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":4388}}}],"partialFingerprints":{"codehealthFindingId/v1":"7117031600ade002561b704d0c4d1873d425cffcbdd78c4757dd21ba17a5a43f"}},{"ruleId":"D2","level":"warning","message":{"text":"BinByResolution.validateAndComputeParameters (cognitive 26): BinByResolution.validateAndComputeParameters has cognitive complexity 26 (threshold 15). Drivers by points: if/else 14 (19 pts), error handling 2 (4 pts), match/switch 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BinByResolution.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"c355f8102cb0cbb73906757899a643342b4908d9dc732c6edde1fe7bfaf9b082"}},{"ruleId":"D2","level":"warning","message":{"text":"CodegenContext.subexpressionEliminationForWholeStageCodegen (cognitive 26): CodegenContext.subexpressionEliminationForWholeStageCodegen has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (19 pts), match/switch 3 (7 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala"},"region":{"startLine":2194}}}],"partialFingerprints":{"codehealthFindingId/v1":"27eee8bf8c1a799aa96a9173aa7050d20afb95e1b222678c1768f5acd700c7ea"}},{"ruleId":"D2","level":"warning","message":{"text":"InsertMapSortInAggregate.apply (cognitive 26): InsertMapSortInAggregate.apply has cognitive complexity 26 (threshold 15). Drivers by points: if/else 11 (15 pts), match/switch 4 (9 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortExpression.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"7da9db1485318856e4bc2dba15208d4513a5b399328a977482b035afb99cb227"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinSelectionHelper.getNonEquiJoinBuildSide (cognitive 26): JoinSelectionHelper.getNonEquiJoinBuildSide has cognitive complexity 26 (threshold 15). Drivers by points: if/else 17 (18 pts), boolean chains 6, match/switch 1 (2 pts) (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"e92259b91ed4d36c052324b088fa5fa39f36dd8246a6b79e199e36230ea00ae9"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.withJoinRelation (cognitive 26): AstBuilder.withJoinRelation has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (21 pts), match/switch 3 (5 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2600}}}],"partialFingerprints":{"codehealthFindingId/v1":"9042511833142c45481d5934554cd1c988e7f7478c5813b8c3e6d0e70f64e9cd"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitTypeConstructor (cognitive 26): AstBuilder.visitTypeConstructor has cognitive complexity 26 (threshold 15). Drivers by points: if/else 13 (18 pts), error handling 2 (4 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":4851}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc6d5e0e51cf610b654b208698f6ab434e20e1c830957b11b304de32da2887a7"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanExecution.processAsArrowBatches (cognitive 26): SparkConnectPlanExecution.processAsArrowBatches has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (11 pts), loops 2 (7 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/execution/SparkConnectPlanExecution.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9901fefe899af2f8e2c422720f800a775c0debcb5218c2b49ad1ac937437a11"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformTypedGroupMap (cognitive 26): SparkConnectPlanner.transformTypedGroupMap has cognitive complexity 26 (threshold 15). Drivers by points: if/else 16 (22 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":777}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2c6ee7bb76f4a445fc636b8a3ad05510cce268135de08f4273229505bfc4b7c"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractBroadcastRangeJoinStage.unapply (cognitive 26): ExtractBroadcastRangeJoinStage.unapply has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (15 pts), match/switch 3 (10 pts), boolean chains 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStageStrategy.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c2da709d5f6123044b2a468a0804ef9d0291bdf486dee673e8db3bd11618e06"}},{"ruleId":"D2","level":"warning","message":{"text":"EmbeddedArraySplitter.consumeValue (cognitive 26): EmbeddedArraySplitter.consumeValue has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (18 pts), boolean chains 4, loops 2 (4 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/EmbeddedArrayJsonDataSource.scala"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"5aaadd09b5143b1b39e60c0975afec5582002afdf052d59af97f53b741e4abe0"}},{"ruleId":"D2","level":"warning","message":{"text":"TableCapabilityCheck.apply (cognitive 26): TableCapabilityCheck.apply has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (13 pts), match/switch 5 (7 pts), boolean chains 6 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/TableCapabilityCheck.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"50d956525215ad1161df8ea070e120263deead9537aca482f03d23f1a7b7c282"}},{"ruleId":"D2","level":"warning","message":{"text":"StateStoreSaveExec.doExecute (cognitive 26): StateStoreSaveExec.doExecute has cognitive complexity 26 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 3 (6 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":880}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe4b83dc8ea722237df04ea4ab24d60f9b8517aca65838424e2905884ba6b07e"}},{"ruleId":"D2","level":"warning","message":{"text":"FileStreamSource.fetchMaxOffset (cognitive 26): FileStreamSource.fetchMaxOffset has cognitive complexity 26 (threshold 15). Drivers by points: if/else 13 (17 pts), match/switch 4 (6 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/FileStreamSource.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"240ec0d088922fbe873610e71a24a2be0ba3131f7ce3b0388c02de64e1161a14"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkGetSchemasOperation.runInternal (cognitive 26): SparkGetSchemasOperation.runInternal has cognitive complexity 26 (threshold 15). Drivers by points: if/else 13 (20 pts), boolean chains 3, match/switch 1 (3 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkGetSchemasOperation.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"61e6735ce12d263f39a9a948c992d5497e82700bb1262d610a68d17c33936041"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseTrimRight (cognitive 26): CollationAwareUTF8String.lowercaseTrimRight has cognitive complexity 26 (threshold 15). Drivers by points: if/else 13 (18 pts), loops 4 (5 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1490}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc37e23166a08e0ce8460c4eaa8455c7fef33985d7ed106aa378a35b72cc30ec"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.pickImpl (cognitive 26): VariantBuilder.pickImpl has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (22 pts), loops 2 (4 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":1046}}}],"partialFingerprints":{"codehealthFindingId/v1":"75c3b9c80008d8472d1e20ecf9b83c3c48ab5d6714f1be5ea1b723a8e2d86401"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetColumnVector.\u003Cinit\u003E (cognitive 26): ParquetColumnVector.\u003Cinit\u003E has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (20 pts), ternaries 1 (3 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetColumnVector.java"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"98db83ba56d56afcb0e0af85fc19676fc403c1a72a722f8c88275161312c5330"}},{"ruleId":"D2","level":"warning","message":{"text":"GetColumnsOperation.runInternal (cognitive 26): GetColumnsOperation.runInternal has cognitive complexity 26 (threshold 15). Drivers by points: loops 5 (10 pts), ternaries 2 (8 pts), if/else 3 (6 pts), boolean chains 1, error handling 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetColumnsOperation.java"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b2be095aa11c704b057ae68c3161d1fe5670657143aa2d29bb11e34e836b873"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.prompt_for_components (cognitive 26): merge_spark_pr.prompt_for_components has cognitive complexity 26 (threshold 15). Drivers by points: if/else 9 (20 pts), loops 3 (4 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":2949}}}],"partialFingerprints":{"codehealthFindingId/v1":"595f9e6a14a01ebf2b66732f7ed4184ab013af87c3affb0fe3f3ef43056f64c2"}},{"ruleId":"D2","level":"warning","message":{"text":"TorchDistributor._execute_command (cognitive 26): TorchDistributor._execute_command has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (18 pts), error handling 2 (6 pts), boolean chains 1, loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":495}}}],"partialFingerprints":{"codehealthFindingId/v1":"31afdd797171f297d7bfed01e9be7329a4df3f3a4be6b83f10bfeef619a63e36"}},{"ruleId":"D2","level":"warning","message":{"text":"Frame.groupby (cognitive 26): Frame.groupby has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (24 pts), loops 1 (2 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2395}}}],"partialFingerprints":{"codehealthFindingId/v1":"c84d94c9ad982f4625342bb3ca0639a615e96aa1e3e6814c863bd9372e535714"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints.spark_type_to_pandas_dtype (cognitive 26): typehints.spark_type_to_pandas_dtype has cognitive complexity 26 (threshold 15). Drivers by points: if/else 14 (24 pts), boolean chains 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b1dd96a2154e0395abf5bceae738f65bc67bb35a28ab09e4d3a51881c094c9b"}},{"ruleId":"D2","level":"warning","message":{"text":"utils.align_diff_frames (cognitive 26): utils.align_diff_frames has cognitive complexity 26 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 5 (7 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/utils.py"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c4cffeace393fc45498d6ea7734dff9c8f213fff57b8ce3e8910540c78fe0dc"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutePlanResponseReattachableIterator._has_next (cognitive 26): ExecutePlanResponseReattachableIterator._has_next has cognitive complexity 26 (threshold 15). Drivers by points: error handling 3 (11 pts), if/else 4 (8 pts), loops 2 (6 pts), boolean chains 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/reattach.py"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ca8bda83a0aa1713b1e84f0189ec869b4e60e4a4e7c14f788ab0707c8a1b6af"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.replace (cognitive 26): DataFrame.replace has cognitive complexity 26 (threshold 15). Drivers by points: if/else 16 (20 pts), boolean chains 5, loops 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1516}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e73bd2725c95b4293a0fff7874beec0178b9dc870178f629a3928700cbaae04"}},{"ruleId":"D2","level":"warning","message":{"text":"types._check_arrow_array_timestamps_localize (cognitive 26): types._check_arrow_array_timestamps_localize has cognitive complexity 26 (threshold 15). Drivers by points: if/else 11 (15 pts), boolean chains 7, ternaries 2 (4 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"dba349ff80323b65f2f2202cb7dbf61047778b51d815fb35a55e919b11b22953"}},{"ruleId":"D2","level":"warning","message":{"text":"DefaultPartitionCoalescer.throwBalls (cognitive 25): DefaultPartitionCoalescer.throwBalls has cognitive complexity 25 (threshold 15). Drivers by points: loops 5 (12 pts), if/else 6 (11 pts), boolean chains 2 (nesting depth added 12). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8391525b6ea440a3eace570ee52c636aa895bf557a11bdbfefa1f681329f02e"}},{"ruleId":"D2","level":"warning","message":{"text":"PipedRDD.compute (cognitive 25): PipedRDD.compute has cognitive complexity 25 (threshold 15). Drivers by points: if/else 14 (16 pts), error handling 3 (4 pts), loops 3 (4 pts), match/switch 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PipedRDD.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"0acca57eaa2ba3e3f33cddeb07e50028eb1e8203463eab73a08369496ec84c02"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.getCallSite (cognitive 25): Utils.getCallSite has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (24 pts), boolean chains 1 (nesting depth added 13). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":1517}}}],"partialFingerprints":{"codehealthFindingId/v1":"acd72eef78f348d38bf934e7df86209aa3e8787cced1baec58b537daf1151280"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.nthSmallest (cognitive 25): Utils.nthSmallest has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 4 (12 pts), boolean chains 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":3247}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd62571938b05a677a51153f278cf8ecfebca418c26638a9049e04d463086347"}},{"ruleId":"D2","level":"warning","message":{"text":"GradientBoostedTrees.boost (cognitive 25): GradientBoostedTrees.boost has cognitive complexity 25 (threshold 15). Drivers by points: if/else 12 (21 pts), boolean chains 3, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"26c607ca25102b7ac2d11a9a00c317541be6159d0fa2a156b61d27e143c15d0b"}},{"ruleId":"D2","level":"warning","message":{"text":"GradientDescent.runMiniBatchSGD (cognitive 25): GradientDescent.runMiniBatchSGD has cognitive complexity 25 (threshold 15). Drivers by points: if/else 13 (21 pts), boolean chains 3, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"65dc57270710fdc1221c71f01118410560c63a9c89bc262b23f8c5a31959c596"}},{"ruleId":"D2","level":"warning","message":{"text":"TableOutputResolver.resolveMapType (cognitive 25): TableOutputResolver.resolveMapType has cognitive complexity 25 (threshold 15). Drivers by points: if/else 17 (23 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":745}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c1c6754b1fd4f38c8d578daed6b15aa686681327e9d7358b79690d579c91e36"}},{"ruleId":"D2","level":"warning","message":{"text":"ConvertToCatalyst.applyExpr (cognitive 25): ConvertToCatalyst.applyExpr has cognitive complexity 25 (threshold 15). Drivers by points: match/switch 4 (12 pts), if/else 8 (9 pts), boolean chains 4 (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1322}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b35011aa656769beba3bb588e5e233390862593ffddc6722a7c53181a71c892"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeUpdateFields.optimizeFieldOps (cognitive 25): OptimizeUpdateFields.optimizeFieldOps has cognitive complexity 25 (threshold 15). Drivers by points: match/switch 7 (14 pts), if/else 10 (11 pts) (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UpdateFields.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"2998949038846504d392d47b5bfa830404ecf0300b44453aad0b434610c52404"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitCommonSelectQueryClausePlan (cognitive 25): AstBuilder.visitCommonSelectQueryClausePlan has cognitive complexity 25 (threshold 15). Drivers by points: if/else 15 (17 pts), match/switch 3 (7 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1936}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a4331775181de37c9dfdd1b3ce56c0915ece30e5f4e7c6107013fb984257333"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeSkewedJoin.tryOptimizeJoinChildren (cognitive 25): OptimizeSkewedJoin.tryOptimizeJoinChildren has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 3 (6 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeSkewedJoin.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"a72da834203d73cd1a8798932def7911bb11aa7ed9cfbf255992c60abedb730d"}},{"ruleId":"D2","level":"warning","message":{"text":"ShufflePartitionsUtil.coalescePartitionsAndGetSpecs (cognitive 25): ShufflePartitionsUtil.coalescePartitionsAndGetSpecs has cognitive complexity 25 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 6, loops 2 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ShufflePartitionsUtil.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ee070a0fb0ac9047bdf433d957c980aa7b7cdd844965f0cbeebcdb17724619e"}},{"ruleId":"D2","level":"warning","message":{"text":"PartitioningUtils.parsePartitions (cognitive 25): PartitioningUtils.parsePartitions has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 2 (4 pts), error handling 1 (3 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa8902e436fc3453bce94685b8f75ee5e539020d01494649ac5b9a732234ddf5"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkShreddingUtils.getFieldsToExtract (cognitive 25): SparkShreddingUtils.getFieldsToExtract has cognitive complexity 25 (threshold 15). Drivers by points: if/else 7 (14 pts), match/switch 2 (5 pts), boolean chains 3, loops 1 (3 pts) (nesting depth added 12). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":724}}}],"partialFingerprints":{"codehealthFindingId/v1":"58a13cc1bcbd6b8be19dd5c2b75cf4814e526c2a1efb62e885269da06142e65a"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ScanRelationPushDown.pushDownLimitAndOffset (cognitive 25): V2ScanRelationPushDown.pushDownLimitAndOffset has cognitive complexity 25 (threshold 15). Drivers by points: if/else 14 (24 pts), match/switch 1 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":1199}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd0d0d681bb5f170b8b036021bf029bf0a5a03e20b6b22b6f09a47cc137ca676"}},{"ruleId":"D2","level":"warning","message":{"text":"StateDataSource.runStateVarChecks (cognitive 25): StateDataSource.runStateVarChecks has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 3 (6 pts), boolean chains 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1b277565f12d8039dd7f76ba07d848d8eac34258551ddc64f3730bb7fb61328"}},{"ruleId":"D2","level":"warning","message":{"text":"HashJoin.outerJoin (cognitive 25): HashJoin.outerJoin has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (20 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"815ea7f0684b2ddb265746ba3aaa26e95ba4b86c1f32ad43d2cda39c9330cc0b"}},{"ruleId":"D2","level":"warning","message":{"text":"HDFSBackedStateStoreProvider.updateFromDeltaFile (cognitive 25): HDFSBackedStateStoreProvider.updateFromDeltaFile has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (23 pts), error handling 1, loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"d26a7601392945ed057ec38a48c51cde5214ff55d4611cacdc25ac0a2abb7f8d"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskMemoryManager.acquireExecutionMemory (cognitive 25): TaskMemoryManager.acquireExecutionMemory has cognitive complexity 25 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 2 (4 pts), ternaries 1 (4 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"add18105c14816b672b61e05ebe3c72ae07e2b133d8ad4054a9e73f37141ac1b"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.addOrRemove (cognitive 25): Index.addOrRemove has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9 (15 pts), ternaries 3 (6 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c12d85f8fc13b7ddd68f6ba5d4ee69307ea3aa041ccd35f318ac8bdbc1bc03e"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.addOrRemove (cognitive 25): Index.addOrRemove has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9 (15 pts), ternaries 3 (6 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"1502c875e4f077a4ed1ab33761bd98b912425a0642dc3e8d4038496087cf0ad4"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.finishWritingObject (cognitive 25): VariantBuilder.finishWritingObject has cognitive complexity 25 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 4 (8 pts), ternaries 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5dc7a2ebb4f3f216a3685d40596d7ea1f1ee5fed5d5d96a1a7952f98847a831"}},{"ruleId":"D2","level":"warning","message":{"text":"AwsStsCredentialProvider.resolve (cognitive 25): AwsStsCredentialProvider.resolve has cognitive complexity 25 (threshold 15). Drivers by points: if/else 13 (16 pts), boolean chains 7, error handling 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/credential-aws/src/main/java/org/apache/spark/security/aws/AwsStsCredentialProvider.java"},"region":{"startLine":310}}}],"partialFingerprints":{"codehealthFindingId/v1":"00683eee86f678647ea06f13be2462a59a45ffee5ee3e5a699697c0101324eef"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnarBatchRow.get (cognitive 25): ColumnarBatchRow.get has cognitive complexity 25 (threshold 15). Drivers by points: if/else 22, boolean chains 3. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcba6858d546a43cbf3207b7bcef7707995c46e219fadcdcd0ab9ec5bdaa29d6"}},{"ruleId":"D2","level":"warning","message":{"text":"generate_srs_registry.parse_sql_values (cognitive 25): generate_srs_registry.parse_sql_values has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (13 pts), loops 4 (9 pts), boolean chains 3 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/generate_srs_registry.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"ede0e2ad10b54453fff9dd7989f954c7f0a0cf624cc3403d0cc2e47661966173"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowGroupedAggIncrementalFinalUDFHandler.run (cognitive 25): ArrowGroupedAggIncrementalFinalUDFHandler.run has cognitive complexity 25 (threshold 15). Drivers by points: loops 5 (12 pts), ternaries 2 (8 pts), if/else 1 (5 pts) (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":566}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e65aae9ca0a16254947003cab3dfcb56558c84ae0f5d3a5c62befcdf7057158"}},{"ruleId":"D2","level":"warning","message":{"text":"java_gateway.launch_gateway (cognitive 25): java_gateway.launch_gateway has cognitive complexity 25 (threshold 15). Drivers by points: if/else 10 (15 pts), loops 2 (5 pts), ternaries 2 (4 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/java_gateway.py"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d3d54a6c9678bb5c5f11ac162d691c39e70a0e5f65036fdca657923d1801aeb"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasOnSparkFrameMethods.transform_batch (cognitive 25): PandasOnSparkFrameMethods.transform_batch has cognitive complexity 25 (threshold 15). Drivers by points: if/else 12 (24 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3d3712da4a15c991963665a67518584d1c426180ec4cbeed9b044e7a253e9a0"}},{"ruleId":"D2","level":"warning","message":{"text":"IndexOpsMixin.factorize (cognitive 25): IndexOpsMixin.factorize has cognitive complexity 25 (threshold 15). Drivers by points: if/else 14 (20 pts), loops 2 (4 pts), ternaries 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1649}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ce41e32190b87cebd46d0ab6e14e2aefc6462658560a94008c7e0655dadab96"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._map_series_op (cognitive 25): DataFrame._map_series_op has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9 (17 pts), loops 2 (6 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":922}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd01fb75860e5a607041f58175c9523a8c4600027205ba7bd4056121744ed9f4"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.quantile (cognitive 25): DataFrame.quantile has cognitive complexity 25 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 4 (8 pts), boolean chains 2, ternaries 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13034}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a71cec2248ee547b3325a245f00a7353cb2262b55ae7b71ad12fbbd96e6cde1"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.fillna (cognitive 25): DataFrame.fillna has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (20 pts), loops 2 (5 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1366}}}],"partialFingerprints":{"codehealthFindingId/v1":"67756d74b143d5a0713174cf4674ab7bd9559fc889f72330f17f4d039236e055"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowBatchTransformer.enforce_schema (cognitive 25): ArrowBatchTransformer.enforce_schema has cognitive complexity 25 (threshold 15). Drivers by points: if/else 10 (13 pts), ternaries 2 (6 pts), error handling 1 (3 pts), boolean chains 2, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8e2d3ba435449506ca610b10aeaf753294e5c9e0dae88e551cdeca52997eac1"}},{"ruleId":"D2","level":"warning","message":{"text":"runPlanVizSearch (cognitive 25): runPlanVizSearch has cognitive complexity 25 (threshold 15). Drivers by points: if/else 11 (14 pts), boolean chains 8, loops 1 (2 pts), ternaries 1 (nesting depth added 4). Most of this is not in the body itself: 6 of the 25 points are its own statements and the rest belongs to 3 function literals inside it that branch (lines 951, 980, 979). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"53943f647d691bda97c51110f4ffe699c6cbd37a55347378fcdfa50b429b1292"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkThrowableHelper.getMessage (cognitive 24): SparkThrowableHelper.getMessage has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (20 pts), match/switch 2 (4 pts) (nesting depth added 14). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/SparkThrowableHelper.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0e401e853b9a28a4aec016d9b585bafe63dd0edb1073edacf93bd169e8c4ffd"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmitArguments.validateSubmitArguments (cognitive 24): SparkSubmitArguments.validateSubmitArguments has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (13 pts), boolean chains 11 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"80fc966609400e4e0dde930a241b9ea0702f81829a3334230af878c148b0fc06"}},{"ruleId":"D2","level":"warning","message":{"text":"CoarseGrainedExecutorBackend.decommissionSelf (cognitive 24): CoarseGrainedExecutorBackend.decommissionSelf has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 4, error handling 1, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"53daccef42c312ee1b13db0dd7fa333475e68400a87e1c5ac6668db75b0f4a9f"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.handleJobSubmitted (cognitive 24): DAGScheduler.handleJobSubmitted has cognitive complexity 24 (threshold 15). Drivers by points: if/else 14 (17 pts), boolean chains 3, error handling 3, match/switch 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2619}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f326eb7c70d25bd78598cabef1160eea3d3339911a31fb0171d94c215012e57"}},{"ruleId":"D2","level":"warning","message":{"text":"DriverEndpoint.receiveAndReply (cognitive 24): DriverEndpoint.receiveAndReply has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (18 pts), loops 2 (4 pts), boolean chains 1, match/switch 1 (nesting depth added 11). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"34f00fc48c7990635abb2b6194c481e0e4a646f27a8223f67f2c26e00f94e8ae"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockPusher.prepareBlockPushRequests (cognitive 24): ShuffleBlockPusher.prepareBlockPushRequests has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (22 pts), boolean chains 1, loops 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/ShuffleBlockPusher.scala"},"region":{"startLine":395}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fadc192557656dac11a9821eedff43aa4ff08e10eb98360d71f958cb97b2b71"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManagerInfo.updateBlockInfo (cognitive 24): BlockManagerInfo.updateBlockInfo has cognitive complexity 24 (threshold 15). Drivers by points: if/else 13 (23 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":1200}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6faf8e0d4ded634f0ad599587784fe150d488080efa3a99171ae388dbd766b3"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.fetchUpToMaxBytes (cognitive 24): ShuffleBlockFetcherIterator.fetchUpToMaxBytes has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (14 pts), loops 3 (6 pts), boolean chains 4 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":1182}}}],"partialFingerprints":{"codehealthFindingId/v1":"c647facc92ac550b5b91978556c2cdc8058c4c343117a55f1016f2e9720d2c65"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.mergeContinuousShuffleBlockIdsIfNeeded (cognitive 24): ShuffleBlockFetcherIterator.mergeContinuousShuffleBlockIdsIfNeeded has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (21 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 12). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":1471}}}],"partialFingerprints":{"codehealthFindingId/v1":"19526364ccc395612df0896262a10add52403737971b61a3eb19b14327f56c9d"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.splitCommandString (cognitive 24): Utils.splitCommandString has cognitive complexity 24 (threshold 15). Drivers by points: if/else 13 (21 pts), boolean chains 2, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":1720}}}],"partialFingerprints":{"codehealthFindingId/v1":"078aad59d4e1aeeb7265bdbc5151bc2c177628fc5202b5230c744f18ff3fc386"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseMatrix.toSparseMatrix (cognitive 24): SparseMatrix.toSparseMatrix has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 2 (7 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":789}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd612671e0a651609071c46911e629f7a9ad98626dfeb8c89a20d2cf7831200e"}},{"ruleId":"D2","level":"warning","message":{"text":"MinHashLSHModel.keyDistance (cognitive 24): MinHashLSHModel.keyDistance has cognitive complexity 24 (threshold 15). Drivers by points: if/else 13 (22 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"be7acb345478e260b5d16ecfbdfa24a25851b7d105b266f9bbaf582d18894c0f"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomForest.runBagged (cognitive 24): RandomForest.runBagged has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (19 pts), loops 2, match/switch 2, boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2f6da39be74adc7160ac65bb826b881176af19081639eb288cfee90781b4f54"}},{"ruleId":"D2","level":"warning","message":{"text":"LocalKMeans.kMeansPlusPlus (cognitive 24): LocalKMeans.kMeansPlusPlus has cognitive complexity 24 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 6 (10 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LocalKMeans.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"4026904e09edb4d5e9b03d9da8576e9048568fd89bbb8e02a9a191219284e2e9"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveAggregateFunctions.buildAggExprList (cognitive 24): ResolveAggregateFunctions.buildAggExprList has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (14 pts), match/switch 4 (10 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":3301}}}],"partialFingerprints":{"codehealthFindingId/v1":"e808f8832a02c23af0f04ac58004597034da1298fe8215c3a98508467b1a0f61"}},{"ruleId":"D2","level":"warning","message":{"text":"ApplyCharTypePaddingHelper.singleNodePaddingForStringComparison (cognitive 24): ApplyCharTypePaddingHelper.singleNodePaddingForStringComparison has cognitive complexity 24 (threshold 15). Drivers by points: match/switch 6 (14 pts), if/else 7 (9 pts), boolean chains 1 (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ApplyCharTypePaddingHelper.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"07b8c86d4692717753aaee9237fca6b633d2a98ef854786b0815b9baa526f4af"}},{"ruleId":"D2","level":"warning","message":{"text":"AssignmentUtils.applyAssignments (cognitive 24): AssignmentUtils.applyAssignments has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 3, match/switch 1 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AssignmentUtils.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6485ae1cc8e0a86eb7bd7d90e7202b3e88402718b015c69100a76a56198fa07"}},{"ruleId":"D2","level":"warning","message":{"text":"RewriteMergeIntoTable.apply (cognitive 24): RewriteMergeIntoTable.apply has cognitive complexity 24 (threshold 15). Drivers by points: match/switch 7 (16 pts), if/else 5, boolean chains 3 (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d3875a261f80da129836e25cca137cddf441826f6be1477167d40a236256091"}},{"ruleId":"D2","level":"warning","message":{"text":"TypeCoercionHelper.findWiderDateTimeType (cognitive 24): TypeCoercionHelper.findWiderDateTimeType has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (19 pts), boolean chains 4, match/switch 1 (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"87645d1811f1712422af676ecffda00cc0a74778862b8aa61025939a4a58c59b"}},{"ruleId":"D2","level":"warning","message":{"text":"ValidateSubqueryExpression.checkCorrelationsInSubquery (cognitive 24): ValidateSubqueryExpression.checkCorrelationsInSubquery has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (12 pts), boolean chains 7, match/switch 4 (5 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ValidateSubqueryExpression.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"232a13697e62dcdff33db774b02c06b5b415016338e6bf090516f96ba22660e7"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalCatalogUtils.unescapePathName (cognitive 24): ExternalCatalogUtils.unescapePathName has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (17 pts), boolean chains 5, loops 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogUtils.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ba89a93621f2397378d696c297487f54ba19584cb9c45575390f9e5905d97c0"}},{"ruleId":"D2","level":"warning","message":{"text":"ToTimestamp.eval (cognitive 24): ToTimestamp.eval has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (17 pts), error handling 1 (5 pts), match/switch 1 (2 pts) (nesting depth added 14). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":2314}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed76d104434f38ddf8e501805bd8ddea2a28bbead26fee98200c4122e6a903b5"}},{"ruleId":"D2","level":"warning","message":{"text":"MapObjects.doGenCode (cognitive 24): MapObjects.doGenCode has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (14 pts), match/switch 5 (6 pts), boolean chains 4 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":1089}}}],"partialFingerprints":{"codehealthFindingId/v1":"38f9322ec94f140dc9f109d665996a5634a56b569eddcda1d65b1881c40a8ffe"}},{"ruleId":"D2","level":"warning","message":{"text":"RemoveRedundantAliases.removeRedundantAliases (cognitive 24): RemoveRedundantAliases.removeRedundantAliases has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 5 (10 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a6581f1b08cfa90a91508929475bd4ba631b4968e52227b88c9c8f7d80b5de8"}},{"ruleId":"D2","level":"warning","message":{"text":"IntervalUtils.castStringToDTInterval (cognitive 24): IntervalUtils.castStringToDTInterval has cognitive complexity 24 (threshold 15). Drivers by points: match/switch 5 (11 pts), boolean chains 8, if/else 5 (nesting depth added 6). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":275}}}],"partialFingerprints":{"codehealthFindingId/v1":"38b40b2648006e2d3a15fb959b8c15a1ac2c6f03186c07fbdabc6eb34d9fd679"}},{"ruleId":"D2","level":"warning","message":{"text":"QuantileSummaries.merge (cognitive 24): QuantileSummaries.merge has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (17 pts), loops 3 (6 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/QuantileSummaries.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"6af8efc4c1b352a74f18288a2541859d9ed7fa023fdbd7edb2555d8748ecb202"}},{"ruleId":"D2","level":"warning","message":{"text":"ToNumberParser.formatDigitGroups (cognitive 24): ToNumberParser.formatDigitGroups has cognitive complexity 24 (threshold 15). Drivers by points: match/switch 4 (12 pts), loops 3 (7 pts), if/else 2 (4 pts), boolean chains 1 (nesting depth added 14). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":788}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c617184803c695b01d0dec62d35fa5ea878c09efbd80b8396754e575b4dfa0b"}},{"ruleId":"D2","level":"warning","message":{"text":"Decoder.decompress (cognitive 24): Decoder.decompress has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 2 (4 pts), match/switch 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9d4ae9144c494088cb64bed3b555e6836a515f5f7c19af33ebdffa56dc703e7"}},{"ruleId":"D2","level":"warning","message":{"text":"FilePartitionReader.next (cognitive 24): FilePartitionReader.next has cognitive complexity 24 (threshold 15). Drivers by points: error handling 7 (15 pts), if/else 5 (6 pts), boolean chains 3 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FilePartitionReader.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"67e70b8f151f33cb9bc6e62255004fdb5fc9e4025f2bb43f50256c8e8847fd74"}},{"ruleId":"D2","level":"warning","message":{"text":"PushDownUtils.replanWithRuntimeFilters (cognitive 24): PushDownUtils.replanWithRuntimeFilters has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (18 pts), match/switch 3 (5 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PushDownUtils.scala"},"region":{"startLine":407}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcfa28125894fd3461cee4aee47e79fe1bf7687dc5561bc424c04a7b3d71b739"}},{"ruleId":"D2","level":"warning","message":{"text":"PartitionPruning.prune (cognitive 24): PartitionPruning.prune has cognitive complexity 24 (threshold 15). Drivers by points: if/else 7 (14 pts), boolean chains 5, match/switch 3 (5 pts) (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala"},"region":{"startLine":321}}}],"partialFingerprints":{"codehealthFindingId/v1":"522e8c232bc1648257a1519b58a5d2fef6bfc80cf1c4da16eeb757a1426448f0"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleExchangeExec.prepareShuffleDependency (cognitive 24): ShuffleExchangeExec.prepareShuffleDependency has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (13 pts), boolean chains 7, loops 1 (2 pts), match/switch 2 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a7625dfb936828c460ad6a90be1e28ba33bd1eab11172ecba8f07c9bfc11144"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeJoinScanner.findNextInnerJoinRows (cognitive 24): SortMergeJoinScanner.findNextInnerJoinRows has cognitive complexity 24 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":1176}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbfd2428b0b1e5be74ca617eda6723287380b360553700332392667c2303c2a1"}},{"ruleId":"D2","level":"warning","message":{"text":"ReuseExchangeAndSubquery.apply (cognitive 24): ReuseExchangeAndSubquery.apply has cognitive complexity 24 (threshold 15). Drivers by points: if/else 9 (18 pts), match/switch 2 (5 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/reuse/ReuseExchangeAndSubquery.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b2639eb18877f2063d78228661db3de1034e2a803c55bab6c1ccea478e421aa"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDB.rangeScan (cognitive 24): RocksDB.rangeScan has cognitive complexity 24 (threshold 15). Drivers by points: if/else 16 (22 pts), match/switch 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1798}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7c51072e2917d74c0101846ef3cc0068ff5c7564b3e45277d2e13e98d8b82d"}},{"ruleId":"D2","level":"warning","message":{"text":"SortState.gallopLeft (cognitive 24): SortState.gallopLeft has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (5 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SortState.gallopRight) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f35cf28666766694f4c1a18796ffbd1f22526991a3d1a43b58a93f2a8766f52"}},{"ruleId":"D2","level":"warning","message":{"text":"SortState.gallopRight (cognitive 24): SortState.gallopRight has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (5 pts), boolean chains 4 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SortState.gallopLeft) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":611}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ee01935e35438fc71f0693894435f48e8ee5baaeb2c0ede2ad15855a78c9110"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnarBatchRow.copy (cognitive 24): ColumnarBatchRow.copy has cognitive complexity 24 (threshold 15). Drivers by points: if/else 20 (23 pts), loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"f04f7265009d1f31d9e2030ade2aba4ab2c4fb4b4e1b62d9786da2f726e0762a"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnarRow.copy (cognitive 24): ColumnarRow.copy has cognitive complexity 24 (threshold 15). Drivers by points: if/else 20 (23 pts), loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b9590eece5bf158b2eb54f8a1096e74313f72e895cbc49e7ec56554d76afe7b"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnarRow.get (cognitive 24): ColumnarRow.get has cognitive complexity 24 (threshold 15). Drivers by points: if/else 22, boolean chains 2. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a3f96a233b7396e91c9be268b7b8909c096a5b45c9e673825c8a5bc4c26ba36"}},{"ruleId":"D2","level":"warning","message":{"text":"base.align_diff_index_ops (cognitive 24): base.align_diff_index_ops has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (13 pts), ternaries 3 (9 pts), boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4614dab960e846659d4af4b8ffdf81c073dc8531ca4a9441a5bf0dd94f53803"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._reduce_for_stat_function (cognitive 24): DataFrame._reduce_for_stat_function has cognitive complexity 24 (threshold 15). Drivers by points: if/else 8 (18 pts), boolean chains 2, loops 1 (2 pts), ternaries 1 (2 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":771}}}],"partialFingerprints":{"codehealthFindingId/v1":"947190f634870b0e4fb6e1725ed252d5721ee64b8fb63083ecf090612cb059a5"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._fillna_with_method (cognitive 24): DataFrame._fillna_with_method has cognitive complexity 24 (threshold 15). Drivers by points: if/else 11 (18 pts), loops 1 (3 pts), ternaries 1 (3 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6416}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa5b6d388ea9ce1a7c97feff809f712617bbd1bfc2228eb252f39eced50614ff"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints.infer_pandas_eval_type (cognitive 24): typehints.infer_pandas_eval_type has cognitive complexity 24 (threshold 15). Drivers by points: boolean chains 12, if/else 10 (11 pts), loops 1 (nesting depth added 1). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"921511fadbc76eee71b2dcad42f8c5fbf2b4edfce327665373951ca4217a39b3"}},{"ruleId":"D2","level":"warning","message":{"text":"spark-sql-viz.document.addEventListener(\u0022DOMContentLoaded\u0022) (cognitive 24): spark-sql-viz.document.addEventListener(\u0022DOMContentLoaded\u0022) has cognitive complexity 24 (threshold 15). Drivers by points: if/else 14 (16 pts), boolean chains 6, ternaries 1 (2 pts) (nesting depth added 3). Most of this is not in the body itself: 6 of the 24 points are its own statements and the rest belongs to 4 function literals inside it that branch (lines 1118, 1139, 1142, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"51e882b2e6f4ed9c32ef92b679077f976f3b29ec4e93c40be86c5b817a6c5963"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 24): (anonymous) has cognitive complexity 24 (threshold 15). Drivers by points: if/else 14 (16 pts), boolean chains 6, ternaries 1 (2 pts) (nesting depth added 3). Most of this is not in the body itself: 6 of the 24 points are its own statements and the rest belongs to 7 function literals inside it that branch (lines 1118, 1139, 1142, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1093}}}],"partialFingerprints":{"codehealthFindingId/v1":"62bf81b69a70aedaae91cd1162c2c09d34f096e758f5f4a68f8f5be754763635"}},{"ruleId":"D2","level":"warning","message":{"text":"MapOutputTrackerMaster.getPreferredLocationsForShuffle (cognitive 23): MapOutputTrackerMaster.getPreferredLocationsForShuffle has cognitive complexity 23 (threshold 15). Drivers by points: if/else 12 (21 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1205}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcb5a3ac8fcdf66ce71299d245d245844053f10d517e89569cdc1ce551bc0a94"}},{"ruleId":"D2","level":"warning","message":{"text":"BasePythonRunner.createPipelinedDataIn (cognitive 23): BasePythonRunner.createPipelinedDataIn has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (19 pts), error handling 1 (2 pts), boolean chains 1, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":813}}}],"partialFingerprints":{"codehealthFindingId/v1":"12ac68784f59145123adfc636a7db6994e26780724e39b988beb801e71b0f5c1"}},{"ruleId":"D2","level":"warning","message":{"text":"Worker.reregisterWithMaster (cognitive 23): Worker.reregisterWithMaster has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 2 (6 pts), match/switch 1 (2 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"081cf8d0876525bb6c1923080e4c12761a73493e6d1f732a046c7d77ec9b4253"}},{"ruleId":"D2","level":"warning","message":{"text":"ReplayListenerBus.replayEntries (cognitive 23): ReplayListenerBus.replayEntries has cognitive complexity 23 (threshold 15). Drivers by points: error handling 8 (11 pts), if/else 4 (10 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"302b6143c616a21b4b8bc0af95705d1c8040e6eba76c6a800b793c3e1f78b256"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalSorter.mergeWithAggregation (cognitive 23): ExternalSorter.mergeWithAggregation has cognitive complexity 23 (threshold 15). Drivers by points: if/else 6 (13 pts), loops 3 (7 pts), boolean chains 3 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala"},"region":{"startLine":411}}}],"partialFingerprints":{"codehealthFindingId/v1":"23bcaa85fa719208d4a6d87e451bc6587154152ce825996b0b446bfd8a2efb0a"}},{"ruleId":"D2","level":"warning","message":{"text":"Literal.valueSizeInBytes (cognitive 23): Literal.valueSizeInBytes has cognitive complexity 23 (threshold 15). Drivers by points: loops 4 (9 pts), match/switch 3 (7 pts), if/else 4 (6 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"96eba7b6a7abc3d11adb0dd91f37e02c599d67666d7b515023c057ec9442e562"}},{"ruleId":"D2","level":"warning","message":{"text":"PushDownLeftSemiAntiJoin.apply (cognitive 23): PushDownLeftSemiAntiJoin.apply has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (15 pts), boolean chains 4, match/switch 2 (4 pts) (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushDownLeftSemiAntiJoin.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"425d332fe22d6a2192a7db4e83ebf3e3f7e4ff34d6ca41c6dbb1f6587aadbfdf"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitOperatorPipeAggregate (cognitive 23): AstBuilder.visitOperatorPipeAggregate has cognitive complexity 23 (threshold 15). Drivers by points: match/switch 6 (11 pts), if/else 6 (9 pts), boolean chains 3 (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":8495}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b415f15fd56716ee2865c28b779ad2e347e4ed3ad8f0bc253c7c2060df06e46"}},{"ruleId":"D2","level":"warning","message":{"text":"StringUtils.stripComment (cognitive 23): StringUtils.stripComment has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (17 pts), boolean chains 3, match/switch 1 (2 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/StringUtils.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"62e6ceb6865c7843dab66c906fd450ab804049b5464b9d5b2c849db8c3910db3"}},{"ruleId":"D2","level":"warning","message":{"text":"PipelinesHandler.buildAutoCdcFlow (cognitive 23): PipelinesHandler.buildAutoCdcFlow has cognitive complexity 23 (threshold 15). Drivers by points: if/else 18, boolean chains 3, match/switch 2. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala"},"region":{"startLine":440}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb425371417598ffc81ef4a2be91bb28c374d54b5f29d31a0c3304444a56624c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitManageResource (cognitive 23): SparkSqlAstBuilder.visitManageResource has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (16 pts), match/switch 4 (6 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":723}}}],"partialFingerprints":{"codehealthFindingId/v1":"565953880468b547feceed4f1afce56f56d01736ee266b132bf51c119b070904"}},{"ruleId":"D2","level":"warning","message":{"text":"SupportsArchiveFormat.readArchiveEntries (cognitive 23): SupportsArchiveFormat.readArchiveEntries has cognitive complexity 23 (threshold 15). Drivers by points: if/else 6 (9 pts), error handling 3 (6 pts), boolean chains 3, loops 2 (3 pts), match/switch 1 (2 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"1524ae534e1ca16150e7af62467617c60ddea9dcdbf34e69f18daf638515df51"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcDeserializer.newWriter (cognitive 23): OrcDeserializer.newWriter has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 3 (6 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1254d282697393fca5f325a52bdbeb2d71b4b8e9f9e2ee5bc187788019199d5"}},{"ruleId":"D2","level":"warning","message":{"text":"InferVariantShreddingSchema.buildSchemaFromStats (cognitive 23): InferVariantShreddingSchema.buildSchemaFromStats has cognitive complexity 23 (threshold 15). Drivers by points: if/else 12 (16 pts), match/switch 3 (5 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/InferVariantShreddingSchema.scala"},"region":{"startLine":491}}}],"partialFingerprints":{"codehealthFindingId/v1":"cba8bc5f900e23ccb6aafeb58df5f3bdf9df8576323d1783fe637e4078bd4e79"}},{"ruleId":"D2","level":"warning","message":{"text":"AnalyzedSchemaProjection.projectToType (cognitive 23): AnalyzedSchemaProjection.projectToType has cognitive complexity 23 (threshold 15). Drivers by points: if/else 15 (22 pts), match/switch 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AnalyzedSchemaProjection.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e935b4b0289196e1a0677bd6709fc8a5f7467a49fe5f3fba086c9915ac56485"}},{"ruleId":"D2","level":"warning","message":{"text":"V2ScanRelationPushDown.pushDownLimit (cognitive 23): V2ScanRelationPushDown.pushDownLimit has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (18 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":1136}}}],"partialFingerprints":{"codehealthFindingId/v1":"3afb5ea4764cdfff337c3b35f378aad39c055605e082fc67cfdae9130f9941a3"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaUtil.isValidSchema (cognitive 23): SchemaUtil.isValidSchema has cognitive complexity 23 (threshold 15). Drivers by points: if/else 15 (21 pts), match/switch 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/utils/SchemaUtil.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9526891162cf3358126687d54796d0b3a45f27d67a9d31a7208e5126eab9b25"}},{"ruleId":"D2","level":"warning","message":{"text":"GraphValidations.validateFlowStreamingness (cognitive 23): GraphValidations.validateFlowStreamingness has cognitive complexity 23 (threshold 15). Drivers by points: if/else 9 (17 pts), match/switch 3 (6 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/GraphValidations.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"70e6a7a8143843fe3b0a3ba66ceac7912561300b8d89addce5bd38cd70aa42e0"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmitOptionParser.parse (cognitive 23): SparkSubmitOptionParser.parse has cognitive complexity 23 (threshold 15). Drivers by points: if/else 9 (22 pts), loops 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkSubmitOptionParser.java"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"19febf338bac6d27c028badbe384c217c2c604d2297a62262bb29b15427834e8"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.toKey (cognitive 23): Index.toKey has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (13 pts), loops 3 (6 pts), ternaries 2 (4 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"87566ef2d05c318daf332154582cf913e851084bc6e70eba858c2b48c92ce5d0"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.toKey (cognitive 23): Index.toKey has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (13 pts), loops 3 (6 pts), ternaries 2 (4 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java"},"region":{"startLine":459}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae063db2545f167f58de4a2104a92c5bcc80b5348afa9fad12d5601f783c30f7"}},{"ruleId":"D2","level":"warning","message":{"text":"ExpressionImplUtils.jaroWinklerSimilarity (cognitive 23): ExpressionImplUtils.jaroWinklerSimilarity has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 5 (7 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff6f65da55fe6a4bc479b370b3902899e62da20ce338d929987ad5399f4c0d17"}},{"ruleId":"D2","level":"warning","message":{"text":"SpecializedGettersReader.read (cognitive 23): SpecializedGettersReader.read has cognitive complexity 23 (threshold 15). Drivers by points: if/else 20, boolean chains 3. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/SpecializedGettersReader.java"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"954af485fe6fac26d3783352bdd2f249c71586f3f4f0549fb7d7c3bc539a9697"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetBlockAccounting.compressedBytesForRowRanges (cognitive 23): ParquetBlockAccounting.compressedBytesForRowRanges has cognitive complexity 23 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 2 (3 pts), boolean chains 2, error handling 1 (2 pts), ternaries 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetBlockAccounting.java"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"21969cffa7e1ce5d5ef2f749539c28a32b60a994a149361a9ec04925d7deed76"}},{"ruleId":"D2","level":"warning","message":{"text":"Distributor._get_num_tasks (cognitive 23): Distributor._get_num_tasks has cognitive complexity 23 (threshold 15). Drivers by points: if/else 9 (23 pts) (nesting depth added 14). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"aff800224c9d8c7460ce981b895c15770ae426647e1d6b9475da603dce43f4ab"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.apply (cognitive 23): DataFrame.apply has cognitive complexity 23 (threshold 15). Drivers by points: if/else 13 (23 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3017}}}],"partialFingerprints":{"codehealthFindingId/v1":"3201f444d5ebc76fa0812e71125b3d77d405950197d0bbfaf6040aacd59c92e7"}},{"ruleId":"D2","level":"warning","message":{"text":"Series._fillna (cognitive 23): Series._fillna has cognitive complexity 23 (threshold 15). Drivers by points: if/else 13 (20 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2255}}}],"partialFingerprints":{"codehealthFindingId/v1":"5738a10190d028a3602d2448205ecc10777161e7a04623fa73c22fbd7c4ffc01"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._to_cols (cognitive 23): DataFrame._to_cols has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (20 pts), boolean chains 2, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ba6041f02fd633e883af58712b7e95731123711dbf297b8b7dba36e36a6be7f"}},{"ruleId":"D2","level":"warning","message":{"text":"WindowExpression.to_plan (cognitive 23): WindowExpression.to_plan has cognitive complexity 23 (threshold 15). Drivers by points: if/else 14 (23 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":1119}}}],"partialFingerprints":{"codehealthFindingId/v1":"f12fbc710243958647dbc8b1a0b8c8d8f1b4b989c857726306b35a4512cb124a"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasConversionMixin._to_pandas (cognitive 23): PandasConversionMixin._to_pandas has cognitive complexity 23 (threshold 15). Drivers by points: if/else 11 (16 pts), error handling 2 (5 pts), ternaries 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc7c80a5662832555462aa8443c487fd5eb1bd65f6fd708d3e0ba4de5c668e6c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession.addArtifacts (cognitive 23): SparkSession.addArtifacts has cognitive complexity 23 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 5 (8 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":2260}}}],"partialFingerprints":{"codehealthFindingId/v1":"3698a1d9f0a6e3fe494c7b768a3869025308095ba09d52cf707325f72e3cbe17"}},{"ruleId":"D2","level":"warning","message":{"text":"UserDefinedFunction.__call__ (cognitive 23): UserDefinedFunction.__call__ has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (17 pts), boolean chains 4, loops 1 (2 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":573}}}],"partialFingerprints":{"codehealthFindingId/v1":"27712d519dbbeefe73e739568b2457161ceed791ddefb07b724f1247080d20ad"}},{"ruleId":"D2","level":"warning","message":{"text":"makeSortable::innerSortFunction (cognitive 23): makeSortable::innerSortFunction has cognitive complexity 23 (threshold 15). Drivers by points: if/else 5 (10 pts), loops 5 (7 pts), ternaries 3 (5 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b9064c1d1c2695b811e5a196caae5966607fe0130890287c3f50344ce629d4e"}},{"ruleId":"D2","level":"warning","message":{"text":"MavenUtils.resolveMavenCoordinatesInternal (cognitive 22): MavenUtils.resolveMavenCoordinatesInternal has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (20 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/MavenUtils.scala"},"region":{"startLine":633}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3d3caeabd246cb009921831655e777631f30d8d50af4808bc479bd03f66b936"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorAllocationManager.doUpdateRequest (cognitive 22): ExecutorAllocationManager.doUpdateRequest has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (19 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":558}}}],"partialFingerprints":{"codehealthFindingId/v1":"664324e8f53d010b33f3c5622dc731cec103a970fde2b3ff43411c9415728cc8"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkEnv.create (cognitive 22): SparkEnv.create has cognitive complexity 22 (threshold 15). Drivers by points: if/else 21, boolean chains 1. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkEnv.scala"},"region":{"startLine":689}}}],"partialFingerprints":{"codehealthFindingId/v1":"7afccd7f3a176397a82c54cbecb8ffedf8f0ed75dacc4bad25b86b470e4a240c"}},{"ruleId":"D2","level":"warning","message":{"text":"BasePythonRunner.compute (cognitive 22): BasePythonRunner.compute has cognitive complexity 22 (threshold 15). Drivers by points: if/else 16 (17 pts), boolean chains 3, error handling 1 (2 pts) (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":690}}}],"partialFingerprints":{"codehealthFindingId/v1":"783a0f9b8d1eafdab9f582d08e7cee67ccd8a2613309be27a0b2318390dc5f14"}},{"ruleId":"D2","level":"warning","message":{"text":"Inbox.process (cognitive 22): Inbox.process has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (14 pts), error handling 1 (3 pts), boolean chains 2, match/switch 1 (2 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/netty/Inbox.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"9812b418963aa7f99a62c241c60c5bbbff5f78a78e1621c69f7d66144541eeb5"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.checkPipelinedShuffleRepeatedReads (cognitive 22): DAGScheduler.checkPipelinedShuffleRepeatedReads has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (15 pts), match/switch 2 (5 pts), loops 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":1531}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f6ab0a8d0f70a7c7b5aa14cdfec1889569ca1ce5df8242b47b37f1478658b7f"}},{"ruleId":"D2","level":"warning","message":{"text":"HighlyCompressedMapStatus.apply (cognitive 22): HighlyCompressedMapStatus.apply has cognitive complexity 22 (threshold 15). Drivers by points: if/else 14 (17 pts), boolean chains 4, loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/MapStatus.scala"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4e52a9fab1c6d204e58c614eefba37cf8841b4462a190db1a2b2c8b10488b5e"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.startServiceOnPort (cognitive 22): Utils.startServiceOnPort has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (17 pts), boolean chains 2, error handling 1 (2 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":2323}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b2024bd38f7862dc5b79a35773ab45d64802a1d5eb109f570c45f0ef57c6292"}},{"ruleId":"D2","level":"warning","message":{"text":"LSHModel.approxNearestNeighbors (cognitive 22): LSHModel.approxNearestNeighbors has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (19 pts), loops 1 (3 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/LSH.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e76680512402046115c308d60034d3e585e03a74fe533465f85ce1f0f86de72"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomForest.binsToBestSplit (cognitive 22): RandomForest.binsToBestSplit has cognitive complexity 22 (threshold 15). Drivers by points: if/else 14 (18 pts), loops 2 (4 pts) (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"651a8bd49dbc9a168543efa7fff3e5d816965d810c2c77a39d5c5f6c1780f794"}},{"ruleId":"D2","level":"warning","message":{"text":"BisectingKMeans.runWithWeight (cognitive 22): BisectingKMeans.runWithWeight has cognitive complexity 22 (threshold 15). Drivers by points: if/else 12 (16 pts), loops 2 (4 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3397ecb4551ccfec3ee24de327f55d407e66cb65ac422be1f2d5dea6829d86b"}},{"ruleId":"D2","level":"warning","message":{"text":"Word2Vec.createBinaryTree (cognitive 22): Word2Vec.createBinaryTree has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 6 (8 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec0ed0f18e881c54ec143110e28d7cccd76b5661df9e0d94ac0f5efa282cb17c"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorPodsLifecycleManager.onNewSnapshots (cognitive 22): ExecutorPodsLifecycleManager.onNewSnapshots has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 3, match/switch 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsLifecycleManager.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"6170346c120d3fd9cd7d7660098460c515e8de1f311ec3eadd451fabc4c641fe"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorPodsSnapshot.toState (cognitive 22): ExecutorPodsSnapshot.toState has cognitive complexity 22 (threshold 15). Drivers by points: match/switch 3 (11 pts), if/else 7 (9 pts), boolean chains 2 (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsSnapshot.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2bcce8c33d48f754b9255814fbcdf8b9596f4241556f264e255de8772b1d28a"}},{"ruleId":"D2","level":"warning","message":{"text":"ApplyCharTypePaddingHelper.padAttrLitCmp (cognitive 22): ApplyCharTypePaddingHelper.padAttrLitCmp has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (20 pts), match/switch 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ApplyCharTypePaddingHelper.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"937b96ba45b75ba7b32b135e5b6a95ad69c6980534a280f96706f9e7aac1da9e"}},{"ruleId":"D2","level":"warning","message":{"text":"CTESubstitution.resolveCTERelations (cognitive 22): CTESubstitution.resolveCTERelations has cognitive complexity 22 (threshold 15). Drivers by points: if/else 12 (19 pts), boolean chains 2, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CTESubstitution.scala"},"region":{"startLine":264}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b7751958374a1eafcd10f12ff9ff5fd269f26e147ffd7e8dfbd124fd8db3ab7"}},{"ruleId":"D2","level":"warning","message":{"text":"FunctionResolution.lookupFunctionType (cognitive 22): FunctionResolution.lookupFunctionType has cognitive complexity 22 (threshold 15). Drivers by points: if/else 6 (9 pts), error handling 2 (6 pts), match/switch 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"72550eab3ddd3e689c16e0842944089a2d449a42313d0ec7bbad9785775454c0"}},{"ruleId":"D2","level":"warning","message":{"text":"InsertionResolution.resolveInsertInto (cognitive 22): InsertionResolution.resolveInsertInto has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (18 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/InsertionResolution.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3fecc9a41178393a95e24e62511777857e1051ff1d100eab544fea3bb0591cf"}},{"ruleId":"D2","level":"warning","message":{"text":"TimeWindowing.apply (cognitive 22): TimeWindowing.apply has cognitive complexity 22 (threshold 15). Drivers by points: match/switch 5 (13 pts), if/else 5 (8 pts), boolean chains 1 (nesting depth added 11). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident. This shape REPEATS in the file: one other method here (SessionWindowing.apply) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTimeWindows.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"403708c9ee5d9d1361350a9183ee52e663578cd852d2607da698a8667ec2d9c6"}},{"ruleId":"D2","level":"warning","message":{"text":"SessionWindowing.apply (cognitive 22): SessionWindowing.apply has cognitive complexity 22 (threshold 15). Drivers by points: match/switch 5 (13 pts), if/else 5 (8 pts), boolean chains 1 (nesting depth added 11). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident. This shape REPEATS in the file: one other method here (TimeWindowing.apply) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTimeWindows.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3eab90aa8791f4be88050f3d1329e4446e97cb6aec742259aec6cb81623889d"}},{"ruleId":"D2","level":"warning","message":{"text":"WidenSetOperationTypes.apply (cognitive 22): WidenSetOperationTypes.apply has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 5, match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"098573b5dc779a55abb4fa653d5017542ca000a1d6d1e782820973d86410c8d5"}},{"ruleId":"D2","level":"warning","message":{"text":"Pmod.doGenCode (cognitive 22): Pmod.doGenCode has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (18 pts), boolean chains 3, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":1239}}}],"partialFingerprints":{"codehealthFindingId/v1":"0882dee1b30ded2762a9ebaa09e38575624916b01d10b83653d296262f207d9d"}},{"ruleId":"D2","level":"warning","message":{"text":"JdkCodeCompiler.narrowingVerdict (cognitive 22): JdkCodeCompiler.narrowingVerdict has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (12 pts), boolean chains 8, error handling 2 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1225}}}],"partialFingerprints":{"codehealthFindingId/v1":"84d808d93d58d1f2964c8c6d649e6077c3e17f92ea90f9dc0ffd52aff82c08e6"}},{"ruleId":"D2","level":"warning","message":{"text":"MultiGetJsonObjectEvaluator.copyCurrentStructure (cognitive 22): MultiGetJsonObjectEvaluator.copyCurrentStructure has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (12 pts), error handling 2 (3 pts), match/switch 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1741}}}],"partialFingerprints":{"codehealthFindingId/v1":"52a8ee70b92aff159c196e56a4fa4d19389b37a2f3c8b31d5e77e30ea397fc62"}},{"ruleId":"D2","level":"warning","message":{"text":"StarSchemaDetection.isUnique (cognitive 22): StarSchemaDetection.isUnique has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (14 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/StarSchemaDetection.scala"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"41f90ae389279c96c99599720f943826f2cf6cbce0871aad0f4fe879fcb5a8aa"}},{"ruleId":"D2","level":"warning","message":{"text":"UnionEstimation.computeColumnStats (cognitive 22): UnionEstimation.computeColumnStats has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (15 pts), match/switch 4 (6 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fa952cf325f9b34108f536ce210293c6f6672bcfd6f08722af785812cfc957c"}},{"ruleId":"D2","level":"warning","message":{"text":"CatalogV2Util.applySchemaChanges (cognitive 22): CatalogV2Util.applySchemaChanges has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (11 pts), match/switch 5 (11 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"0990498e70e7b69a9ff54d70664842fe90c09cffb6e0590d584985782a7730fd"}},{"ruleId":"D2","level":"warning","message":{"text":"AlterTableChangeColumnCommand.run (cognitive 22): AlterTableChangeColumnCommand.run has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (18 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5759a7ff3b84b01bc06c4a0a047ec73029063206305d47d3e069942f2536653"}},{"ruleId":"D2","level":"warning","message":{"text":"DynamicPartitionDataConcurrentWriter.write (cognitive 22): DynamicPartitionDataConcurrentWriter.write has cognitive complexity 22 (threshold 15). Drivers by points: if/else 12 (19 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ed1c517aa52a6a06c73b74d8c79a4eed449d0ed9a9ccd8d365e90f5ccf77d11"}},{"ruleId":"D2","level":"warning","message":{"text":"PreprocessTableInsertion.preprocess (cognitive 22): PreprocessTableInsertion.preprocess has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (12 pts), boolean chains 6, match/switch 2 (3 pts), error handling 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"6220e960ed735ea2da5cb1a9e8a48c5a2410a0af476208795fd99ad6eb65f277"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaUtil.unifyMapStateRowPair (cognitive 22): SchemaUtil.unifyMapStateRowPair has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (18 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/utils/SchemaUtil.scala"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc2d382da29d5d11cea25f0c44a22047feedb5f3aa246c86bf1f34784b06a5dd"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeAsOfJoinScanner.findWithCursor (cognitive 22): SortMergeAsOfJoinScanner.findWithCursor has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (18 pts), boolean chains 3, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeAsOfJoinExec.scala"},"region":{"startLine":876}}}],"partialFingerprints":{"codehealthFindingId/v1":"21e1a9ef136da4c1adebc8d6f83171679d6e14b9fd485ddd7ba58058decea8c3"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeAsOfJoinScanner.findNearest (cognitive 22): SortMergeAsOfJoinScanner.findNearest has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (18 pts), boolean chains 3, loops 1 (nesting depth added 10). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeAsOfJoinExec.scala"},"region":{"startLine":958}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f514fda0adf02617bf4c89d2fd08f9132615eb0e550849a307e99a508b8dca9"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.initializeStateVariable (cognitive 22): TransformWithStateInPySparkStateServer.initializeStateVariable has cognitive complexity 22 (threshold 15). Drivers by points: if/else 12 (21 pts), match/switch 1 (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":693}}}],"partialFingerprints":{"codehealthFindingId/v1":"58b7ab66360efb23e0e41710129409609113552b6e4f7490854baab5061e91aa"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingSymmetricHashJoinExec.processPartitions (cognitive 22): StreamingSymmetricHashJoinExec.processPartitions has cognitive complexity 22 (threshold 15). Drivers by points: if/else 14, match/switch 5 (8 pts) (nesting depth added 3). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7dd15b202876b4b8a5d6495d85157c7753376b9841c6a9fe53a2be5c8aee509"}},{"ruleId":"D2","level":"warning","message":{"text":"SlidingWindowMinMaxFunctionFrame.write (cognitive 22): SlidingWindowMinMaxFunctionFrame.write has cognitive complexity 22 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 5 (9 pts), boolean chains 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/SlidingWindowMinMaxFunctionFrame.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"2882333b20fc1f13823c823b05ca7ed1a5ff1f62ebf4e048ef77481bfa064718"}},{"ruleId":"D2","level":"warning","message":{"text":"ProcessIterator.advance (cognitive 22): ProcessIterator.advance has cognitive complexity 22 (threshold 15). Drivers by points: if/else 6 (11 pts), match/switch 2 (5 pts), error handling 1 (3 pts), boolean chains 2, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/grpc/src/main/scala/org/apache/spark/udf/worker/grpc/GrpcWorkerSession.scala"},"region":{"startLine":923}}}],"partialFingerprints":{"codehealthFindingId/v1":"f826cd90cbf8eb1e26e893c1f7d402952981095034926ab46a09093dc69899ea"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkLauncher.startApplication (cognitive 22): SparkLauncher.startApplication has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (13 pts), boolean chains 5, ternaries 1 (2 pts), error handling 1, loops 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkLauncher.java"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"157e9d24d9983c05b1c1075634ce28106d7560845653250f8466a50b69943af3"}},{"ruleId":"D2","level":"warning","message":{"text":"LevelDBIterator.loadNext (cognitive 22): LevelDBIterator.loadNext has cognitive complexity 22 (threshold 15). Drivers by points: if/else 6 (12 pts), ternaries 3 (7 pts), error handling 1 (2 pts), loops 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"09a4d6b2b07422df3438b49beab1d31b4a6a2b5f4191ababfa0b5c59ea8de287"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalBlockHandler.handleMessage (cognitive 22): ExternalBlockHandler.handleMessage has cognitive complexity 22 (threshold 15). Drivers by points: if/else 14 (19 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6521cbff409d06a7ec2e2fa46228a6fd8fb1683c8c3ac821fe30e0d4fe2206"}},{"ruleId":"D2","level":"warning","message":{"text":"PushBlockStreamCallback.onComplete (cognitive 22): PushBlockStreamCallback.onComplete has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (15 pts), error handling 2 (6 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":1533}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc530629c223e89ae7dc3623dec240c38dfe3733a306a2848ef20c97f1dbf825"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.soundex (cognitive 22): UTF8String.soundex has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 5, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":2334}}}],"partialFingerprints":{"codehealthFindingId/v1":"00d4bea8fda7155864b0209fab280e3fb041dafcb745644757cdb1a51d39e702"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveFunctionRegistryUtils.filterMethodsByTypeAffinity (cognitive 22): HiveFunctionRegistryUtils.filterMethodsByTypeAffinity has cognitive complexity 22 (threshold 15). Drivers by points: if/else 6 (16 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/HiveFunctionRegistryUtils.java"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"862d8e15c8702b01c25292e22312eaa0fd9607e671650a283f74121cd258f08d"}},{"ruleId":"D2","level":"warning","message":{"text":"DataTypeOps.__new__ (cognitive 22): DataTypeOps.__new__ has cognitive complexity 22 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 4 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"1dd56681c313f19b43ddea9cf6329744d34b258780e5327b6c8203590d3b1eab"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._update_internal_frame (cognitive 22): DataFrame._update_internal_frame has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (18 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":669}}}],"partialFingerprints":{"codehealthFindingId/v1":"43c739549671e4eaba9bfb79a1f3e5d76b0417caadf0e7a1e968ef938048b36c"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.update (cognitive 22): DataFrame.update has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (12 pts), ternaries 2 (6 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9373}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae9893541424a61830cb323557a71e53d9099189c22ba443966992a746172df9"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupBy._prepare_return (cognitive 22): GroupBy._prepare_return has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 1 (3 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":3724}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c75fa0bf1151570e9c21b7b934dbef9fc5ab744542d3affbe776c9f1ccf6ea6"}},{"ruleId":"D2","level":"warning","message":{"text":"Series._rank (cognitive 22): Series._rank has cognitive complexity 22 (threshold 15). Drivers by points: if/else 14 (18 pts), ternaries 2 (4 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":4350}}}],"partialFingerprints":{"codehealthFindingId/v1":"23b2813b34fccb8064d6ab1383e4ee113c94e4d56452bde87db4a8f874556477"}},{"ruleId":"D2","level":"warning","message":{"text":"api.create_auto_cdc_flow (cognitive 22): api.create_auto_cdc_flow has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (14 pts), boolean chains 7, loops 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"42e87d89725b713e668169cf027a515f46e865cb63259d53daf8acc4505bb105"}},{"ruleId":"D2","level":"warning","message":{"text":"shuffle.get_used_memory (cognitive 22): shuffle.get_used_memory has cognitive complexity 22 (threshold 15). Drivers by points: if/else 9 (17 pts), loops 1 (3 pts), boolean chains 1, error handling 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"426b2bfb6abb87d34f75a97dab6013319a21f286be599d73714761659108e246"}},{"ruleId":"D2","level":"warning","message":{"text":"LiteralExpression._to_value (cognitive 22): LiteralExpression._to_value has cognitive complexity 22 (threshold 15). Drivers by points: boolean chains 15, if/else 4 (7 pts) (nesting depth added 3). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb18fdcd2d169050d3423f04fa14e70899a108db6569843ca5c00fe6b427abf2"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession.createDataFrame (cognitive 22): SparkSession.createDataFrame has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (13 pts), boolean chains 4, error handling 3, ternaries 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1428}}}],"partialFingerprints":{"codehealthFindingId/v1":"c41c95faf2d3c0d9e31bf0c58346853b07daa813ab92d37d55a987ce5ef1b4fe"}},{"ruleId":"D2","level":"warning","message":{"text":"makeSortable (cognitive 22): makeSortable has cognitive complexity 22 (threshold 15). Drivers by points: if/else 16 (40 pts), loops 8 (21 pts), ternaries 3 (11 pts), boolean chains 2 (nesting depth added 45). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc0906f755c64649a034b1b2987740b9b2f9c43d6312757cc0ae85d68648a93e"}},{"ruleId":"D2","level":"warning","message":{"text":"ClosureCleaner.clean (cognitive 21): ClosureCleaner.clean has cognitive complexity 21 (threshold 15). Drivers by points: if/else 11 (18 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":233}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5505fbc80f616320264da72c6d094733442714c02f53f8998451d38494073e6"}},{"ruleId":"D2","level":"warning","message":{"text":"KafkaDataConsumer.get (cognitive 21): KafkaDataConsumer.get has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (17 pts), error handling 1 (2 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/KafkaDataConsumer.scala"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb5f4473cd281346b2fc29a7b18f59a6886e2a782f1d6cafab13f4b88e556248"}},{"ruleId":"D2","level":"warning","message":{"text":"ProtobufDeserializer.checkAnyJsonRecursion (cognitive 21): ProtobufDeserializer.checkAnyJsonRecursion has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (20 pts), loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"558ea5a8232703ff5c63abc7d00a16f2663a7514ea23ba6118fed101f7008fd4"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskContextImpl.markTaskCompleted (cognitive 21): TaskContextImpl.markTaskCompleted has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (15 pts), error handling 3, boolean chains 2, loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9e7072709c31ccdd40d2f2b0ec0a3e9369412c0566af172befdb63ce0d14d57"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskContextImpl.invokeListeners (cognitive 21): TaskContextImpl.invokeListeners has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (11 pts), error handling 5 (7 pts), boolean chains 2, loops 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":596}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f9051ea4d6f627a13cb41dfbbcd62f64d9e0c53686ff0d3f3072fcf177f27e9"}},{"ruleId":"D2","level":"warning","message":{"text":"ClientEndpoint.reportDriverStatus (cognitive 21): ClientEndpoint.reportDriverStatus has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 3 (8 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Client.scala"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0855caf98d0faae62fda1120101385670ebc10aea9aa147037a2f58c66be59b"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.classifyJobShuffleShape (cognitive 21): DAGScheduler.classifyJobShuffleShape has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (16 pts), match/switch 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":1248}}}],"partialFingerprints":{"codehealthFindingId/v1":"febbe0165818b80475511c176a3b67779b43565ecf601b2ad8cd4cc41ee51304"}},{"ruleId":"D2","level":"warning","message":{"text":"UIUtils.makeProgressBar (cognitive 21): UIUtils.makeProgressBar has cognitive complexity 21 (threshold 15). Drivers by points: if/else 20, boolean chains 1. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":509}}}],"partialFingerprints":{"codehealthFindingId/v1":"76bd19ce7596eaeb3748f2d49545d6afadef591f8f9908b55d7e7b91663d0dfb"}},{"ruleId":"D2","level":"warning","message":{"text":"RDDOperationGraph.makeOperationGraph (cognitive 21): RDDOperationGraph.makeOperationGraph has cognitive complexity 21 (threshold 15). Drivers by points: if/else 13 (17 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/scope/RDDOperationGraph.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"1791c2aa8794a9c56eb2e67456d72adbc25173678de7b49087b7700dce5f4290"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegression.createInitialSolution (cognitive 21): LogisticRegression.createInitialSolution has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (16 pts), boolean chains 2, loops 1 (2 pts), match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":820}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1a537f4669d67f0ae1ab0c927692c9ff298e12b80a26886f85996ef432696f2"}},{"ruleId":"D2","level":"warning","message":{"text":"ALS.train (cognitive 21): ALS.train has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 2 (4 pts), boolean chains 1, error handling 1, match/switch 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala"},"region":{"startLine":1024}}}],"partialFingerprints":{"codehealthFindingId/v1":"39f2de504db35ef4b0e21ab9d664402508fbb2cf2ca1c0edbb9103e396944631"}},{"ruleId":"D2","level":"warning","message":{"text":"SlidingRDD.getPartitions (cognitive 21): SlidingRDD.getPartitions has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (14 pts), loops 2 (6 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/rdd/SlidingRDD.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e53caee579b49a1e1bcc9aaef12307762247e5c235ce8468ca6344ffbf197e4"}},{"ruleId":"D2","level":"warning","message":{"text":"InTypeCoercion.apply (cognitive 21): InTypeCoercion.apply has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 4 (9 pts), boolean chains 2 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"a560d6da3fc77daa7fd19375d1957a0586f713203fe923735545be6773d25e5a"}},{"ruleId":"D2","level":"warning","message":{"text":"WidenStatefulOperatorAttributeNullability.apply (cognitive 21): WidenStatefulOperatorAttributeNullability.apply has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (13 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/WidenStatefulOperatorAttributeNullability.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f5dde50acfc50d7b7b023f34d8173e2bdaedc008810b2ea328508c55cb6da68"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupingAndAggregateExpressionsExtractor.extractReferencedGroupingAndAggregateExpressions (cognitive 21): GroupingAndAggregateExpressionsExtractor.extractReferencedGroupingAndAggregateExpressions has cognitive complexity 21 (threshold 15). Drivers by points: match/switch 4 (12 pts), if/else 8 (9 pts) (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/GroupingAndAggregateExpressionsExtractor.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"80af751be7d7387449426b0c4ac99576832cf605a572e0786d1292d79da76bdb"}},{"ruleId":"D2","level":"warning","message":{"text":"LogicalPlanDifference.apply (cognitive 21): LogicalPlanDifference.apply has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (14 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/LogicalPlanDifference.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"53d776de632fe2a8fb2f9eb56aa9f168c6c5e9d605db27e06ad3e912a77e79b5"}},{"ruleId":"D2","level":"warning","message":{"text":"CSVHeaderChecker.checkHeaderColumnNames (cognitive 21): CSVHeaderChecker.checkHeaderColumnNames has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (17 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"803d10b6de19db57b245cad56aa5f8345d11e0c6c3a304127301bfd392a22794"}},{"ruleId":"D2","level":"warning","message":{"text":"GenerateUnsafeProjection.writeExpressionsToBuffer (cognitive 21): GenerateUnsafeProjection.writeExpressionsToBuffer has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (12 pts), match/switch 3 (6 pts), boolean chains 3 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateUnsafeProjection.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4479f00464f71a82a6b5cf8288d92ae1a7e13397d85408d2c523ca0ea207f4d"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonObjectExpr.checkInputDataTypes (cognitive 21): JsonObjectExpr.checkInputDataTypes has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 2 (5 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":2688}}}],"partialFingerprints":{"codehealthFindingId/v1":"682b1ead68d3175c35daf7ac88b25fef2c0a1b5f5ebd0b063fa69e09669de1c7"}},{"ruleId":"D2","level":"warning","message":{"text":"InterpretedOrdering.compare (cognitive 21): InterpretedOrdering.compare has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (16 pts), match/switch 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ordering.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ea8e6beebf2a7642c8949d4c2e0b8d2b597098be1652a184df6b99ad0625e7d"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeJoinCondition.optimizeCondition (cognitive 21): OptimizeJoinCondition.optimizeCondition has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (11 pts), boolean chains 8, match/switch 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJoinCondition.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"bad5ea215a90aeeef822facb4ce45e930a3b73e9a729c638883e8a49c80b27a9"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.withQueryResultClauses (cognitive 21): AstBuilder.withQueryResultClauses has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12, boolean chains 9. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1636}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad00811bec8092e0d7ec3a75a42a3f7ca084c71944f19fbae9777db7c95fc51a"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.withAggregationClause (cognitive 21): AstBuilder.withAggregationClause has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (19 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2234}}}],"partialFingerprints":{"codehealthFindingId/v1":"d88bc2b49c088b12afaf98e2aad66c2f115328b3e6fffb44390bc81f0a336859"}},{"ruleId":"D2","level":"warning","message":{"text":"EstimationUtils.getOverlappedRanges (cognitive 21): EstimationUtils.getOverlappedRanges has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 7 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/EstimationUtils.scala"},"region":{"startLine":293}}}],"partialFingerprints":{"codehealthFindingId/v1":"49c15b02f2d818c39347ed92600940c5c1556a098e49a0818d60b73fd4baf336"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinEstimation.estimateInnerOuterJoin (cognitive 21): JoinEstimation.estimateInnerOuterJoin has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (9 pts), match/switch 4 (9 pts), boolean chains 3 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"90cc681daeace5952df924f515ec35ee84675eb14607ffc6fb25cbb991053ebd"}},{"ruleId":"D2","level":"warning","message":{"text":"ParseSqlResult.collectPlanReferences (cognitive 21): ParseSqlResult.collectPlanReferences has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (12 pts), match/switch 4 (5 pts), boolean chains 4 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"adba2d46de226bf2e6c8093a7ae2ab43b0e737a943497ed70f802b2409cb448a"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitCreatePipelineDataset (cognitive 21): SparkSqlAstBuilder.visitCreatePipelineDataset has cognitive complexity 21 (threshold 15). Drivers by points: if/else 16 (18 pts), match/switch 1 (3 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":1640}}}],"partialFingerprints":{"codehealthFindingId/v1":"55b47534cc248b9652767e4a9bf85a4bfd6668f8ad4d878e5b5bc97afce086cd"}},{"ruleId":"D2","level":"warning","message":{"text":"AdaptiveSparkPlanExec.cancelObsoleteStages (cognitive 21): AdaptiveSparkPlanExec.cancelObsoleteStages has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (14 pts), boolean chains 3, error handling 1 (2 pts), match/switch 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d028000ed85399fb73219635ca9907054ddd42b579e115d00ab6dfd724672b4"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetToSparkSchemaConverter.convertGroupField (cognitive 21): ParquetToSparkSchemaConverter.convertGroupField has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (18 pts), boolean chains 2, match/switch 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":402}}}],"partialFingerprints":{"codehealthFindingId/v1":"d777365f863224d3955ea68ecd99dadbfecf89fc396ee91e2a86c396ef9635a6"}},{"ruleId":"D2","level":"warning","message":{"text":"StructReader.readFromTyped (cognitive 21): StructReader.readFromTyped has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (16 pts), boolean chains 4, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"386b034ceb577a98ed023683e988809ec3cafb38e489a0040f27b47a554dd089"}},{"ruleId":"D2","level":"warning","message":{"text":"ViewSyncSchemaToMetaStore.apply (cognitive 21): ViewSyncSchemaToMetaStore.apply has cognitive complexity 21 (threshold 15). Drivers by points: if/else 4 (7 pts), boolean chains 6, match/switch 2 (5 pts), error handling 1 (3 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":615}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca2c0d1f6bc5d5ec4942498c01b8e3b3d93f7370737a29855ae736cf410b56b1"}},{"ruleId":"D2","level":"warning","message":{"text":"PushDownUtils.pushFilters (cognitive 21): PushDownUtils.pushFilters has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 2 (4 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PushDownUtils.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"adff33a8481f45657e931557c3f1bd462a1a470d3c3c3e77be9dfd7b33b846cc"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeJoinScanner.findNextOuterJoinRows (cognitive 21): SortMergeJoinScanner.findNextOuterJoinRows has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 1 (4 pts), boolean chains 3 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":1232}}}],"partialFingerprints":{"codehealthFindingId/v1":"d53adf59fa1aa0524507103b6a5c5eabab40e5359598203a313113b1a5883769"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractPythonUDFFromLambda.overArray (cognitive 21): ExtractPythonUDFFromLambda.overArray has cognitive complexity 21 (threshold 15). Drivers by points: match/switch 5 (13 pts), if/else 5 (8 pts) (nesting depth added 11). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ExtractPythonUDFFromLambda.scala"},"region":{"startLine":584}}}],"partialFingerprints":{"codehealthFindingId/v1":"eda2b0ed3b8bc16b50958542495eedfb6800732230eecffe623091b9bd9be51f"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractPythonUDFs.extract (cognitive 21): ExtractPythonUDFs.extract has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (16 pts), match/switch 2 (5 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ExtractPythonUDFs.scala"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"47f127b38cb9af0d3267accf2acb774d33c0791d32bbc3ca3c8f23a65a8a996b"}},{"ruleId":"D2","level":"warning","message":{"text":"ProgressContext.legacyExtractSourceToNumInputRows (cognitive 21): ProgressContext.legacyExtractSourceToNumInputRows has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (12 pts), match/switch 5 (9 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/ProgressReporter.scala"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc96fa0dc77212717599ececc502304a5fb188cd935e71c359f39134eb9fcc56"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDBFileManager.deleteOldVersions (cognitive 21): RocksDBFileManager.deleteOldVersions has cognitive complexity 21 (threshold 15). Drivers by points: if/else 15 (16 pts), error handling 2, match/switch 2, boolean chains 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala"},"region":{"startLine":659}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc1218f112dd20ee77a4c5ccf7bc60d1f356db4cf1c0ce252456409bede4479d"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveExternalCatalog.alterTable (cognitive 21): HiveExternalCatalog.alterTable has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (18 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":642}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d8c169d1e309052410c68adedcfdbaff6c2f844b355569802484d169585a6a2"}},{"ruleId":"D2","level":"warning","message":{"text":"LevelDBIterator.\u003Cinit\u003E (cognitive 21): LevelDBIterator.\u003Cinit\u003E has cognitive complexity 21 (threshold 15). Drivers by points: if/else 13 (19 pts), boolean chains 1, ternaries 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"1de9af1c74d57144c2697293ebf08cfb54b40dbdf2f47a43e584ebd676221d3b"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDBIterator.loadNext (cognitive 21): RocksDBIterator.loadNext has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (17 pts), ternaries 1 (3 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1888c0e40c2b7a383ae62e40c02e9a3cbd3badd56debe476dfe18bee34a4028"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationFactory.getClosestSuggestionsOnInvalidName (cognitive 21): CollationFactory.getClosestSuggestionsOnInvalidName has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (14 pts), loops 3 (4 pts), boolean chains 2, error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java"},"region":{"startLine":1421}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7b065c228431423e94752d62e79426cd56663c91b04ad28ce0534d8b111ff01"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.getIsValid (cognitive 21): UTF8String.getIsValid has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3 (5 pts), ternaries 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":469}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b3d9b048c5333a61863dc46807e7acc3ce889cf7e7ce881ba4d40d871946788"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.appendWithDeletionImpl (cognitive 21): VariantBuilder.appendWithDeletionImpl has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (15 pts), boolean chains 4, loops 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":570}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e8ead24e1114193f99f9f9d38aca735f429da7b14a3b9d0b0f157490bdf5f80"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcColumnarBatchReader.initBatch (cognitive 21): OrcColumnarBatchReader.initBatch has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/orc/OrcColumnarBatchReader.java"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6c1eada38f1d778c4a4d5f8531c8f09f372227e1a7c1a9fc6be84c3f21e4158"}},{"ruleId":"D2","level":"warning","message":{"text":"ThriftHttpServlet.doPost (cognitive 21): ThriftHttpServlet.doPost has cognitive complexity 21 (threshold 15). Drivers by points: if/else 12 (18 pts), boolean chains 2, error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftHttpServlet.java"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"f841bade583ac015fa1ee2548975dab90833976275b3fc0ef4e154273222473a"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.reconcile_jira_affects_versions (cognitive 21): merge_spark_pr.reconcile_jira_affects_versions has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (11 pts), boolean chains 4, error handling 2 (4 pts), loops 1, ternaries 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":1775}}}],"partialFingerprints":{"codehealthFindingId/v1":"384cd06ef5e74d19750237ecba91d3e6ee869c6e1c71fba5463c0735b9619e2e"}},{"ruleId":"D2","level":"warning","message":{"text":"install.install_spark (cognitive 21): install.install_spark has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (15 pts), error handling 2 (4 pts), loops 1, ternaries 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/install.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c382f439139ed7b6738d4d59b1cf1848ebb1c0eb91df28e13245c0dd9f2c0c8"}},{"ruleId":"D2","level":"warning","message":{"text":"BooleanOps.astype (cognitive 21): BooleanOps.astype has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (14 pts), boolean chains 4, ternaries 1 (3 pts) (nesting depth added 9). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf9f63e3265937826e7a3af65b9af2270601342ded6ba866bb699e92eacc7eef"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.droplevel (cognitive 21): Index.droplevel has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (20 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1326}}}],"partialFingerprints":{"codehealthFindingId/v1":"faa3693c45ae54bf6b23e19881f0151f5ef2bb5da6445f083f370be25a077463"}},{"ruleId":"D2","level":"warning","message":{"text":"Index.difference (cognitive 21): Index.difference has cognitive complexity 21 (threshold 15). Drivers by points: if/else 11 (15 pts), boolean chains 5, ternaries 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2031}}}],"partialFingerprints":{"codehealthFindingId/v1":"811f56e97c8f271c45095f3a4695a0cdf0ce614f56f5d827714ad755538c8feb"}},{"ruleId":"D2","level":"warning","message":{"text":"Series._drop (cognitive 21): Series._drop has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (15 pts), error handling 1 (3 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2720}}}],"partialFingerprints":{"codehealthFindingId/v1":"be3d2f522b8b07206acefee9304bd52246dd8e30fd37d5c6e0ac671cbbff7906"}},{"ruleId":"D2","level":"warning","message":{"text":"ArtifactManager._parse_artifacts (cognitive 21): ArtifactManager._parse_artifacts has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (13 pts), boolean chains 7, error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9053d5fb599dc20ff0817522b637575f7e8e93db1ae138a4519061c5233a1ff"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectClient._truncate (cognitive 21): SparkConnectClient._truncate has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (20 pts), loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1353}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfb66d4202df6ea4c1aa6fc91a67eb02b013e76cadce006b889f8467296247e5"}},{"ruleId":"D2","level":"warning","message":{"text":"functions._validate_vectorized_udf (cognitive 21): functions._validate_vectorized_udf has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (11 pts), boolean chains 7, error handling 1 (2 pts), ternaries 1 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/functions.py"},"region":{"startLine":882}}}],"partialFingerprints":{"codehealthFindingId/v1":"d83c4a2ee0bb93e3cbbfb209daba4b07bc05715fc90566268324b8e2bb9cae5c"}},{"ruleId":"D2","level":"warning","message":{"text":"typehints.infer_arrow_eval_type (cognitive 21): typehints.infer_arrow_eval_type has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (11 pts), boolean chains 9, loops 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4413469bb6c3647214c66d9d5115276e88125fa250fddb9bdc8ff2fe206ff37"}},{"ruleId":"D2","level":"warning","message":{"text":"GoldenFileTestMixin.compare_or_generate_golden_matrix (cognitive 21): GoldenFileTestMixin.compare_or_generate_golden_matrix has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3 (5 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/goldenutils.py"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0d1b39293c7dad67c6d72e4996fe365979d0414d4b048a3477e2f4079c2cbfe"}},{"ruleId":"D2","level":"warning","message":{"text":"sql-table-utils.getSqlTableColumns (cognitive 21): sql-table-utils.getSqlTableColumns has cognitive complexity 21 (threshold 15). Drivers by points: if/else 13, boolean chains 8. Most of this is not in the body itself: 1 of the 21 points is its own statement and the rest belongs to 9 function literals inside it that branch (lines 263, 202, 254, \u2026). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/sql-table-utils.js"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"0aee50e90190c1852e1c3e2bf961e2de937729108741d52d86d9ee7b9cc92745"}},{"ruleId":"D2","level":"warning","message":{"text":"ClosureCleaner.cleanNonIndyLambdaClosure (cognitive 20): ClosureCleaner.cleanNonIndyLambdaClosure has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (15 pts), loops 2 (3 pts), boolean chains 2 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"69317d2ca759cc11987a1cd769609e213f0742d5c849f5e179c05925e81ebeb0"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorAllocationManager.removeExecutors (cognitive 20): ExecutorAllocationManager.removeExecutors has cognitive complexity 20 (threshold 15). Drivers by points: if/else 15 (19 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":675}}}],"partialFingerprints":{"codehealthFindingId/v1":"3636828f1e1e009d7d2bef6aaedc4f2c5dfaddc04de1ae243f914be861468f96"}},{"ruleId":"D2","level":"warning","message":{"text":"PythonWorkerFactory.startDaemon (cognitive 20): PythonWorkerFactory.startDaemon has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (13 pts), boolean chains 4, error handling 3 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"54d82e746f931c7d51ee06faf54935501783a2bf4ba2d405c2242420352ab2fe"}},{"ruleId":"D2","level":"warning","message":{"text":"ResourceProfileManager.isSupported (cognitive 20): ResourceProfileManager.isSupported has cognitive complexity 20 (threshold 15). Drivers by points: boolean chains 12, if/else 5 (8 pts) (nesting depth added 3). To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ResourceProfileManager.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cf7fb540ac631a4556325234fa771fed6b55ae4468dac26505c3f903a4fc92d"}},{"ruleId":"D2","level":"warning","message":{"text":"ResourceUtils.warnOnWastedResources (cognitive 20): ResourceUtils.warnOnWastedResources has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (17 pts), boolean chains 3 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ResourceUtils.scala"},"region":{"startLine":424}}}],"partialFingerprints":{"codehealthFindingId/v1":"beed96eb74a245bbe8140cdee6a1ccd3882f4eed86f307290887e339a1ea01e0"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorMonitor.onBlockUpdated (cognitive 20): ExecutorMonitor.onBlockUpdated has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 3, match/switch 1 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/dynalloc/ExecutorMonitor.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ffcd46cbd77a4c1b73e73bca1a3646e98699bf7a4375a1518c4426d7a57b68d"}},{"ruleId":"D2","level":"warning","message":{"text":"ChannelShuffleWriter.write (cognitive 20): ChannelShuffleWriter.write has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (18 pts), loops 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/local/pipelined/ChannelShuffleWriterReader.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"85a483a2fae885183b01e5979ce51c62345f92bbaa584ed75947c0d1b7ee1d55"}},{"ruleId":"D2","level":"warning","message":{"text":"AppStatusListener.updateRDDBlock (cognitive 20): AppStatusListener.updateRDDBlock has cognitive complexity 20 (threshold 15). Drivers by points: if/else 16 (20 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":1088}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fc5552bd791d822a6881aafc5187aec6c6aa0dd8635e3ffb91548baffb39cb5"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.collectFetchRequests (cognitive 20): ShuffleBlockFetcherIterator.collectFetchRequests has cognitive complexity 20 (threshold 15). Drivers by points: if/else 6 (12 pts), match/switch 2 (4 pts), boolean chains 3, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff550e1ba44abbce02551b4ec587fb56736c4b51e6f2b7b9a3ccf7a8812a7b63"}},{"ruleId":"D2","level":"warning","message":{"text":"EdgePartition.aggregateMessagesEdgeScan (cognitive 20): EdgePartition.aggregateMessagesEdgeScan has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 2, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeb16af9edb3ef3c4874ac4ae7a5ae4dce50c740a5ef61b0d25a03487154ea46"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegression.trainImpl (cognitive 20): LogisticRegression.trainImpl has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (14 pts), boolean chains 4, loops 1, match/switch 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":935}}}],"partialFingerprints":{"codehealthFindingId/v1":"df4a79d682fdf8ca4e5ea5d592ad8d77f6d44d46982e55d88c49143e1dc6e56c"}},{"ruleId":"D2","level":"warning","message":{"text":"KMeans.runAlgorithmWithWeight (cognitive 20): KMeans.runAlgorithmWithWeight has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 2, loops 1, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"89a0411c5d2a4f7bdfa729ab03d4e0e0dc1607ea87712f63de5310af75431f69"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveQualify.resolveQualifyCondition (cognitive 20): ResolveQualify.resolveQualifyCondition has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 5 (12 pts), if/else 4 (6 pts), boolean chains 2 (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":4318}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c6f810a61c3dbe3c2d00d9bef27354a64482f15533d0403c88c54a8da60f547"}},{"ruleId":"D2","level":"warning","message":{"text":"CTESubstitution.apply (cognitive 20): CTESubstitution.apply has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (14 pts), match/switch 4 (5 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CTESubstitution.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"b33d50e4b1208e852aa4883255660e1b5303fa00fa263d562b63135091bef8d8"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationTypeCoercion.findCollationContext (cognitive 20): CollationTypeCoercion.findCollationContext has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 5 (9 pts), boolean chains 1 (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CollationTypeCoercion.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c741c15613e732678be1d08fb313ca733015ee6381d84a10159aaa619331523"}},{"ruleId":"D2","level":"warning","message":{"text":"TypeCoercion.findCommonTypeForBinaryComparison (cognitive 20): TypeCoercion.findCommonTypeForBinaryComparison has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (19 pts), match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f6bcfa12ce75cca2812cdb4a21381387a6ce1250939fe3dd0735b70194437d3"}},{"ruleId":"D2","level":"warning","message":{"text":"TypeCoercion.implicitCast (cognitive 20): TypeCoercion.implicitCast has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 5, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"101cb59b2bee6a6ad720e79bd818cf3493bd9db84500b366ca669555aec2cf5b"}},{"ruleId":"D2","level":"warning","message":{"text":"SessionCatalog.registerUserDefinedFunction (cognitive 20): SessionCatalog.registerUserDefinedFunction has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":2342}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a49ced62a70cfbc24dba6ebc2af0ec2600dcc85428ff6894b2249672577bdae"}},{"ruleId":"D2","level":"warning","message":{"text":"UnivocityParser.convert (cognitive 20): UnivocityParser.convert has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (15 pts), error handling 2 (4 pts), loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":394}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ffaece96d0add4578adec119f7017c9987be07d2c8907fbc92aa27b1f19697f"}},{"ruleId":"D2","level":"warning","message":{"text":"UnBase64.isValidBase64 (cognitive 20): UnBase64.isValidBase64 has cognitive complexity 20 (threshold 15). Drivers by points: if/else 6 (12 pts), boolean chains 5, match/switch 1 (2 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala"},"region":{"startLine":3421}}}],"partialFingerprints":{"codehealthFindingId/v1":"9aba64271ef06fcf582c3357d4148231e329062eca1d46a6e7639519d929d20f"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantExpressionEvalUtils.buildVariant (cognitive 20): VariantExpressionEvalUtils.buildVariant has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (13 pts), loops 3 (6 pts), match/switch 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d92b3f1dbd603e839dc54dcb8301e24df7f260cd90f8691c3c2f82eeecb4743"}},{"ruleId":"D2","level":"warning","message":{"text":"JacksonParser.convertObject (cognitive 20): JacksonParser.convertObject has cognitive complexity 20 (threshold 15). Drivers by points: error handling 4 (12 pts), if/else 3, boolean chains 2, match/switch 1 (2 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"25c1e8ab25a36e4d9056f26bfb9a26b78398a364bf1eed6fbfe139b4cb7973a5"}},{"ruleId":"D2","level":"warning","message":{"text":"InjectRuntimeFilter.extractBeneficialFilterCreatePlan (cognitive 20): InjectRuntimeFilter.extractBeneficialFilterCreatePlan has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (11 pts), match/switch 3 (7 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b0f8eb24b072783ce0564eedd85e8d1bdb51705bb6189b96b1259507c388196"}},{"ruleId":"D2","level":"warning","message":{"text":"InlineCTE.buildCTEMap (cognitive 20): InlineCTE.buildCTEMap has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (13 pts), match/switch 3 (7 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InlineCTE.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"301e97f134535fc3d40128482bd6b613d6fed0bb1b1e34eac70f4ef69162fb96"}},{"ruleId":"D2","level":"warning","message":{"text":"PullUpProjectAliasThroughWindow.apply (cognitive 20): PullUpProjectAliasThroughWindow.apply has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 6 (14 pts), if/else 4 (5 pts), boolean chains 1 (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PullUpProjectAliasThroughWindow.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"61d84e2699b4b955d1e82e4330b9c9929a21c41e6a6491664e358ff971b85e7a"}},{"ruleId":"D2","level":"warning","message":{"text":"UnwrapCastInBinaryComparison.unwrapCast (cognitive 20): UnwrapCastInBinaryComparison.unwrapCast has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (9 pts), boolean chains 6, match/switch 3 (5 pts) (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"b64cc37bdc91314f43966f8930419b13f962b7ff39821a5a19420e3c3635988a"}},{"ruleId":"D2","level":"warning","message":{"text":"LikeSimplification.simplifyMultiLike (cognitive 20): LikeSimplification.simplifyMultiLike has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (18 pts), match/switch 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1103}}}],"partialFingerprints":{"codehealthFindingId/v1":"e90c7195360c28675ef6d590b45fcf1ae0e0771d6c50c6fe37202b4058eaa5b7"}},{"ruleId":"D2","level":"warning","message":{"text":"PartitioningUtils.normalizePartitionSpec (cognitive 20): PartitioningUtils.normalizePartitionSpec has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 4 (11 pts), if/else 6, boolean chains 3 (nesting depth added 7). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/util/PartitioningUtils.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"dda612d009cab7181fd3aa0796e915c226dc495b09b432b40dcc0e8f1e212312"}},{"ruleId":"D2","level":"warning","message":{"text":"DataTypeProtoConverter.toConnectProtoTypeDefault (cognitive 20): DataTypeProtoConverter.toConnectProtoTypeDefault has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (14 pts), match/switch 3 (5 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/DataTypeProtoConverter.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3cd033790732f0c67dd5374d93ad07916026bb2dfa2789d052a5cbf14e2e2d0"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnNodeToExpressionConverter.apply (cognitive 20): ColumnNodeToExpressionConverter.apply has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 7 (14 pts), if/else 5 (6 pts) (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/columnNodeSupport.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"c06361a0d2acfa76ca10a12cda33a071f47a9c767bb525afd4b0336e9c72343f"}},{"ruleId":"D2","level":"warning","message":{"text":"InsertSortForLimitAndOffset.extractOrderingAndPropagateOrderingColumns (cognitive 20): InsertSortForLimitAndOffset.extractOrderingAndPropagateOrderingColumns has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (12 pts), match/switch 4 (7 pts), boolean chains 1 (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/InsertSortForLimitAndOffset.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"437c0567ed0f1426c9bd244138c16c8a4bc6a0f4fe8957b007dc3c7175d4fe2c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitCreateTable (cognitive 20): SparkSqlAstBuilder.visitCreateTable has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (15 pts), match/switch 1 (3 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"af8c0649a027a1a88071b410ef53f18325aca87361bf23003fb06914272fe795"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitDescribeRelation (cognitive 20): SparkSqlAstBuilder.visitDescribeRelation has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (15 pts), match/switch 1 (3 pts), boolean chains 2 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":1491}}}],"partialFingerprints":{"codehealthFindingId/v1":"65fc699ee85d7734819f06ec991cf0585fcf783e652947b19d27924cbfa6ef43"}},{"ruleId":"D2","level":"warning","message":{"text":"ShufflePartitionsUtil.coalescePartitionsWithSkew (cognitive 20): ShufflePartitionsUtil.coalescePartitionsWithSkew has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (12 pts), loops 2 (4 pts), boolean chains 3, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ShufflePartitionsUtil.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ae01bb45ad257898fcee8c1b4e070f9b2c000d51c1109b3f6e83f7092d2b069"}},{"ruleId":"D2","level":"warning","message":{"text":"CommandUtils.analyzeTable (cognitive 20): CommandUtils.analyzeTable has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (18 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dc0a2bdf1f477ef7f9becd9e7b33488fe2fa823c883e97208ba3469b6881f8a"}},{"ruleId":"D2","level":"warning","message":{"text":"ShowCreateTableCommand.run (cognitive 20): ShowCreateTableCommand.run has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (20 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1225}}}],"partialFingerprints":{"codehealthFindingId/v1":"84cb00810b4ce3d5e8ac2ffe6bf4f96d2d2db811cb07a4404e21cffe38d76a7b"}},{"ruleId":"D2","level":"warning","message":{"text":"JDBCRelation.columnPartition (cognitive 20): JDBCRelation.columnPartition has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (15 pts), boolean chains 4, loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRelation.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b7229ef119f57e2a013a416ab4939b3fea74c029d71d1a72849d666602a0576"}},{"ruleId":"D2","level":"warning","message":{"text":"JdbcUtils.getCatalystType (cognitive 20): JdbcUtils.getCatalystType has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 5, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"c11dfd936ba2e9af384a90f7e511ac7d522f84b74046e3138dfa5fb66e795538"}},{"ruleId":"D2","level":"warning","message":{"text":"OrcFileFormat.buildReaderWithPartitionValues (cognitive 20): OrcFileFormat.buildReaderWithPartitionValues has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (17 pts), boolean chains 3 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"981a98041b6eaeb9fea0e8d373d54bf8312580893929ea4f15fe6fabad8e172a"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupPartitionsExec.computeOutputPartitioning (cognitive 20): GroupPartitionsExec.computeOutputPartitioning has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 4 (14 pts), boolean chains 3, if/else 3 (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/GroupPartitionsExec.scala"},"region":{"startLine":641}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c3764efe23d49c19f0bf28e597f6d2c9c3f208714bc48a5b4af0c6fee318ad6"}},{"ruleId":"D2","level":"warning","message":{"text":"EnsureRequirements.resolveKeyedPartitioning (cognitive 20): EnsureRequirements.resolveKeyedPartitioning has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), boolean chains 5, match/switch 3 (5 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":1329}}}],"partialFingerprints":{"codehealthFindingId/v1":"e42adb71ecdd446899a92334354954bf5d300c94a79b54ba6ca2476acd3c4433"}},{"ruleId":"D2","level":"warning","message":{"text":"LongIntervalIndex.apply (cognitive 20): LongIntervalIndex.apply has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (17 pts), loops 2, boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":941}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a8cf1c0b424e1b2f860826dac78c2a3497d427b8d7b57e2cf84c7e487f0b096"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleListStateRequest (cognitive 20): TransformWithStateInPySparkStateServer.handleListStateRequest has cognitive complexity 20 (threshold 15). Drivers by points: if/else 14 (19 pts), match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":504}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2c14e3f79a0612b312e49cdca93a64ac414ae9c8d5f9d1c162f192e84dc351a"}},{"ruleId":"D2","level":"warning","message":{"text":"StateStoreHandler.initializeStateStore (cognitive 20): StateStoreHandler.initializeStateStore has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (20 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":1665}}}],"partialFingerprints":{"codehealthFindingId/v1":"815e2010a722c65c1f577e10cfe24bc9aaf55109eef200fba181d54ba673015f"}},{"ruleId":"D2","level":"warning","message":{"text":"MicroBatchExecution.executeOneBatch (cognitive 20): MicroBatchExecution.executeOneBatch has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (20 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":725}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7fa16256d3bdb60389422d717deb391fcd7d6f898a44cb5d8a5572e809bfcfe"}},{"ruleId":"D2","level":"warning","message":{"text":"HDFSBackedStateStoreProvider.readSnapshotFile (cognitive 20): HDFSBackedStateStoreProvider.readSnapshotFile has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (18 pts), error handling 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":1014}}}],"partialFingerprints":{"codehealthFindingId/v1":"49bfce4a224c0fbc9e7d98d7523261990c863b8d9d313fe75f5ae11dbf59c79d"}},{"ruleId":"D2","level":"warning","message":{"text":"SqlScriptingExecution.getNextStatement (cognitive 20): SqlScriptingExecution.getNextStatement has cognitive complexity 20 (threshold 15). Drivers by points: if/else 6 (13 pts), boolean chains 6, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecution.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"c453b4dfcfdef5c338ddf634f37297873aef534eed2efb157dfce208a5318571"}},{"ruleId":"D2","level":"warning","message":{"text":"RowSetUtils.toTColumnValue (cognitive 20): RowSetUtils.toTColumnValue has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (19 pts), match/switch 1 (nesting depth added 9). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/RowSetUtils.scala"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e5cd1235358d910cf3e972516f75ab57388e1e6dbe742a5516fb7a3ed398c25"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDBIterator.\u003Cinit\u003E (cognitive 20): RocksDBIterator.\u003Cinit\u003E has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (18 pts), boolean chains 1, ternaries 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fe2d27b043ecf20835cf443903a6a7f40f61284bc08f019d92e975aa7a35867"}},{"ruleId":"D2","level":"warning","message":{"text":"SslMessageEncoder.encode (cognitive 20): SslMessageEncoder.encode has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (11 pts), ternaries 2 (5 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/SslMessageEncoder.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0f15acca994d28f3bbb82847875b9dc11cc460de036673c6cc9de6821d19072"}},{"ruleId":"D2","level":"warning","message":{"text":"OneForOneStreamManager.connectionTerminated (cognitive 20): OneForOneStreamManager.connectionTerminated has cognitive complexity 20 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (4 pts), error handling 1 (3 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/server/OneForOneStreamManager.java"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"10f8212d39b7c9c71942e54b415e2acf65497d2a66b8b652ad1591d5f57bd889"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.makeValidBytes (cognitive 20): UTF8String.makeValidBytes has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3 (5 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb3b53d44ddde98ec67e19d684661a3c0b7e140f35a7fb63a8b99d5dd2e1e805"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.subStringIndex (cognitive 20): UTF8String.subStringIndex has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1483}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9bbfdf7d1a74dedd68a28dc2fd185e37ee7ada82eeb14c72a494fac8ceae8f1"}},{"ruleId":"D2","level":"warning","message":{"text":"LateMaterializationParquetRecordReader.initializeLateMaterialization (cognitive 20): LateMaterializationParquetRecordReader.initializeLateMaterialization has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), ternaries 4 (6 pts), boolean chains 2, loops 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f5175e6d07a3bb768eef42ebcc8e8f1df7882f9afd05bdc56699cb9bb65c666"}},{"ruleId":"D2","level":"warning","message":{"text":"MutableColumnarRow.get (cognitive 20): MutableColumnarRow.get has cognitive complexity 20 (threshold 15). Drivers by points: if/else 20. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3849c946249196df2785fc3cc1b3a5392f411278b3dc4cdf6f276754638e62f"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveServer2.startHiveServer2 (cognitive 20): HiveServer2.startHiveServer2 has cognitive complexity 20 (threshold 15). Drivers by points: error handling 4 (12 pts), if/else 3 (7 pts), loops 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/server/HiveServer2.java"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7b27b6d3af62466d2364159107a51f58f8460e3485d5444cdb172b2626db379"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowGroupedAggIncrementalPartialUDFHandler.run (cognitive 20): ArrowGroupedAggIncrementalPartialUDFHandler.run has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 4 (8 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":471}}}],"partialFingerprints":{"codehealthFindingId/v1":"726adad5f548bc40b1cf18e34648eab8756ae9475ef3d7ad5ffcfbc22421548c"}},{"ruleId":"D2","level":"warning","message":{"text":"functions._validate_and_transform_single_input (cognitive 20): functions._validate_and_transform_single_input has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 2, ternaries 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/functions.py"},"region":{"startLine":235}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3ad41a1d38636591901639cf74a86bf06a98589fc9895f5ba28a33078f58014"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.idxmax (cognitive 20): DataFrame.idxmax has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (12 pts), ternaries 2 (6 pts), loops 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (DataFrame.idxmin) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12633}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f249769c5078611282cbeed5099926727a0f79173e761776676564b17ac2b52"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.idxmin (cognitive 20): DataFrame.idxmin has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (12 pts), ternaries 2 (6 pts), loops 1 (2 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (DataFrame.idxmax) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12774}}}],"partialFingerprints":{"codehealthFindingId/v1":"804a991b7024a0f5a5a938a7d011c926e89f23e41b1e5f9ba15ffd5d38d25d30"}},{"ruleId":"D2","level":"warning","message":{"text":"Frame.truncate (cognitive 20): Frame.truncate has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 4, ternaries 2 (3 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":3110}}}],"partialFingerprints":{"codehealthFindingId/v1":"53474b94129d0859332b08026d65f9d4b39886024f55758357788c79758c3b74"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrameGroupBy.__getitem__ (cognitive 20): DataFrameGroupBy.__getitem__ has cognitive complexity 20 (threshold 15). Drivers by points: if/else 6 (11 pts), ternaries 2 (5 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":3954}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cf138244af63b950b9801f6906ede0ba2d6cd5a725279d81d1deb2b0ce88e28"}},{"ruleId":"D2","level":"warning","message":{"text":"Series.__init__ (cognitive 20): Series.__init__ has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (20 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":427}}}],"partialFingerprints":{"codehealthFindingId/v1":"716ef5f3503930c6823d40b7f664169fba928b0f4b4792427832dfd1e870532f"}},{"ruleId":"D2","level":"warning","message":{"text":"Series._interpolate (cognitive 20): Series._interpolate has cognitive complexity 20 (threshold 15). Drivers by points: if/else 12 (15 pts), boolean chains 5 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2327}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6dd983a2241af91c076b61feb348723eab2d76e758d9d0a0ef1ee2153c4a063"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalGroupBy._spill (cognitive 20): ExternalGroupBy._spill has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), loops 4 (10 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":802}}}],"partialFingerprints":{"codehealthFindingId/v1":"02a06dbae3eb6a8968efca3c453d4f589cf789b031fc1c5aa2b29e2729334f3c"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.dropna (cognitive 20): DataFrame.dropna has cognitive complexity 20 (threshold 15). Drivers by points: if/else 10 (17 pts), loops 1 (3 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1443}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e4556722efac41242f3798dd598e745536d8bb6361316b8d4e2294e7e2a4ac4"}},{"ruleId":"D2","level":"warning","message":{"text":"local_server._pid_alive (cognitive 20): local_server._pid_alive has cognitive complexity 20 (threshold 15). Drivers by points: if/else 5 (10 pts), error handling 5 (7 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/local_server.py"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa4bc383cdb8c3a281311d5601ebb5099efb9b9aee7eace79c0dcb2786c95107"}},{"ruleId":"D2","level":"warning","message":{"text":"ServerPool._reap_retired (cognitive 20): ServerPool._reap_retired has cognitive complexity 20 (threshold 15). Drivers by points: if/else 11 (15 pts), boolean chains 4, ternaries 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/local_server_pool.py"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"90f84229270b6e9cc05a12ef6b2af7da1a8489498f9f569930c449d204b40453"}},{"ruleId":"D2","level":"warning","message":{"text":"builtin.lit (cognitive 20): builtin.lit has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (19 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf83ac4151495b43b513af93b46ca942a9f553b992cb04750d3f6ce029a83ada"}},{"ruleId":"D2","level":"warning","message":{"text":"CatalystTranspiler._safe_category (cognitive 20): CatalystTranspiler._safe_category has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), ternaries 3 (6 pts), boolean chains 3, error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"8353f9eea375be703f4c7ceedc0d09e83643f532a62299a24a02b81624ad9d75"}},{"ruleId":"D2","level":"warning","message":{"text":"(anonymous) (cognitive 20): (anonymous) has cognitive complexity 20 (threshold 15). Drivers by points: boolean chains 11, if/else 5 (6 pts), error handling 1 (2 pts), ternaries 1 (nesting depth added 2). Most of this is not in the body itself: 3 of the 20 points are its own statements and the rest belongs to 10 function items inside it that branch (a function literal at line 164, (anonymous)::(anonymous)::createdRow, a function literal at line 186, \u2026). The named helpers are already separate functions; the literals\u0027 work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal\u0027s work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/environmentpage.js"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"5221195b2152ae9652656e6ea6145238a41836cbc5a75af88ef9d0b338058d78"}},{"ruleId":"D2","level":"warning","message":{"text":"FieldAccessFinder.visitMethod (cognitive 19): FieldAccessFinder.visitMethod has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (9 pts), loops 3 (7 pts), boolean chains 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":1164}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5825917e07f760761ec6f4188fc93d4d47ce462e16cd4e9a4ecaf62a95db7c9"}},{"ruleId":"D2","level":"warning","message":{"text":"KafkaDataConsumer.fetchRecord (cognitive 19): KafkaDataConsumer.fetchRecord has cognitive complexity 19 (threshold 15). Drivers by points: if/else 13 (19 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/KafkaDataConsumer.scala"},"region":{"startLine":619}}}],"partialFingerprints":{"codehealthFindingId/v1":"61cb03e679a12a98e952dc90a87d66c29505b1f0af167acb4c2e52da02ca0c65"}},{"ruleId":"D2","level":"warning","message":{"text":"KinesisUtilsPythonHelper.createStream (cognitive 19): KinesisUtilsPythonHelper.createStream has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (10 pts), boolean chains 7, match/switch 2 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtilsPythonHelper.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac5dac44c3c35008a9be5dfdd00c11c41f35ab01ddc40a359be11fb0e8c820c3"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext.createTaskScheduler (cognitive 19): SparkContext.createTaskScheduler has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (12 pts), error handling 2 (4 pts), match/switch 2 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":3665}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c236af16f4ff015ef31c0cd5b85e8c1374d1c6633a04ebffd76b439afc2988a"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskContextImpl.awaitListenerInvocationHandover (cognitive 19): TaskContextImpl.awaitListenerInvocationHandover has cognitive complexity 19 (threshold 15). Drivers by points: error handling 3 (9 pts), if/else 3 (4 pts), loops 2 (3 pts), match/switch 1 (2 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b8839eeb82cf00a986cf151e8664ba941c40b1f83ac0290677dae59f22e8098"}},{"ruleId":"D2","level":"warning","message":{"text":"TorrentBroadcast.readBlocks (cognitive 19): TorrentBroadcast.readBlocks has cognitive complexity 19 (threshold 15). Drivers by points: if/else 3 (13 pts), match/switch 2 (5 pts), loops 1 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c4ccedaf0232b7446177dde96f6f6ab7267c341d04c72ce3046885c3d196e32"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSubmit.submit (cognitive 19): SparkSubmit.submit has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (12 pts), error handling 2 (5 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"78d150bf821b971f700a4f2518628ac505761852cb129b78c7bffb35c8de521a"}},{"ruleId":"D2","level":"warning","message":{"text":"Master.startExecutorsOnWorkers (cognitive 19): Master.startExecutorsOnWorkers has cognitive complexity 19 (threshold 15). Drivers by points: if/else 2 (7 pts), loops 3 (7 pts), match/switch 1 (4 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bfe26823187bb1991a93439b9d1e987f00acec2f86bdc0461be9ecd7df7245e"}},{"ruleId":"D2","level":"warning","message":{"text":"DoubleRDDFunctions.histogram (cognitive 19): DoubleRDDFunctions.histogram has cognitive complexity 19 (threshold 15). Drivers by points: if/else 13 (14 pts), boolean chains 2, match/switch 1 (2 pts), loops 1 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"f64c70642bb140041dfd9a186c4006b7f74b149e1b050f400560a0e20f7d0c6c"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.cancelRunningIndependentStages (cognitive 19): DAGScheduler.cancelRunningIndependentStages has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (13 pts), error handling 1 (4 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":5276}}}],"partialFingerprints":{"codehealthFindingId/v1":"32a5ec3362734eddc5a6aad3bca2e8c74cc18c4dc80b4f00765fd1ac91289402"}},{"ruleId":"D2","level":"warning","message":{"text":"ReplayListenerBus.boundedLines (cognitive 19): ReplayListenerBus.boundedLines has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (14 pts), loops 2 (3 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"0df3f317232bb7c911fac826d9cd5e1c51b9dd444d22434d36947c0a28e6c09e"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockFetcherIterator.sendRequest (cognitive 19): ShuffleBlockFetcherIterator.sendRequest has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 2, boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":264}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c3e53fa6cd23e5d19a34f92b4fadb8fa4377e9bd4bf2b2e4416f82ae0cddf12"}},{"ruleId":"D2","level":"warning","message":{"text":"HttpSecurityFilter.doFilter (cognitive 19): HttpSecurityFilter.doFilter has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/HttpSecurityFilter.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f2baaa8cc971dfc8126f55dc2099d6fc96e06a21152f435cc7ddcb42afc8a73"}},{"ruleId":"D2","level":"warning","message":{"text":"HadoopFSUtils.listLeafFiles (cognitive 19): HadoopFSUtils.listLeafFiles has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (11 pts), error handling 3 (4 pts), match/switch 3, boolean chains 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/HadoopFSUtils.scala"},"region":{"startLine":218}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ac3a69ee9488a175f836c924f911646b70a9f67ad66ca72a24442e182218c0f"}},{"ruleId":"D2","level":"warning","message":{"text":"Vectors.norm (cognitive 19): Vectors.norm has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 2 (6 pts), match/switch 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":336}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bf87d878d19c9a53b8ebf0b5b0c0e4a346c0b88954cc5b6e7f2c1a6fb0e1b85"}},{"ruleId":"D2","level":"warning","message":{"text":"BinaryLogisticBlockAggregator.add (cognitive 19): BinaryLogisticBlockAggregator.add has cognitive complexity 19 (threshold 15). Drivers by points: if/else 13 (17 pts), boolean chains 1, loops 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"afa7cc2245580e6244b0e3c899e95d8c24d479ad2ac87b094736f3e4e2e59f16"}},{"ruleId":"D2","level":"warning","message":{"text":"HuberBlockAggregator.add (cognitive 19): HuberBlockAggregator.add has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 1, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"8eb7faea00bdd5b4fb3a811a290aa535b4d2d1d0b0d63974a35931348607f0ee"}},{"ruleId":"D2","level":"warning","message":{"text":"Vectors.norm (cognitive 19): Vectors.norm has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 2 (6 pts), match/switch 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala"},"region":{"startLine":490}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0cfdb8f2bb1f021253a34a5c92f4e7d612887b1679d7d5c2f0dc59986498c4f"}},{"ruleId":"D2","level":"warning","message":{"text":"MFDataGenerator.main (cognitive 19): MFDataGenerator.main has cognitive complexity 19 (threshold 15). Drivers by points: if/else 19. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"d54cecb852104f48b80474bf69c06a3675ff3bf12fc874c94e53db69a2aa5512"}},{"ruleId":"D2","level":"warning","message":{"text":"DataType.nameToType (cognitive 19): DataType.nameToType has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (10 pts), error handling 2 (4 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"7efea9548b0fa195e0f3479ecfff27eb982b90b7abd262811b4c2903f9829567"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveTranspiledPythonUDFOptions.apply (cognitive 19): ResolveTranspiledPythonUDFOptions.apply has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 3 (10 pts), if/else 4 (7 pts), boolean chains 2 (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTranspiledPythonUDFOptions.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5121f957121ef1532e9c07313e8de7bd513ecaa2a009531a02fab3d28b7bdae"}},{"ruleId":"D2","level":"warning","message":{"text":"ApproxTopKAggregateBuffer.eval (cognitive 19): ApproxTopKAggregateBuffer.eval has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (9 pts), match/switch 2 (7 pts), boolean chains 2, loops 1 (nesting depth added 6). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala"},"region":{"startLine":447}}}],"partialFingerprints":{"codehealthFindingId/v1":"c611a8ae17aaf4a1f9725bc69b653a696d94372c60228547a5ff1d7aea93361d"}},{"ruleId":"D2","level":"warning","message":{"text":"DivModLike.eval (cognitive 19): DivModLike.eval has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (12 pts), match/switch 1 (4 pts), boolean chains 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":704}}}],"partialFingerprints":{"codehealthFindingId/v1":"8517905c408a0cc0bc38ab32b96956b7b23f53830f62100502e5f0c815ba7c41"}},{"ruleId":"D2","level":"warning","message":{"text":"MapZipWith.getKeysWithIndexesBruteForce (cognitive 19): MapZipWith.getKeysWithIndexesBruteForce has cognitive complexity 19 (threshold 15). Drivers by points: if/else 3 (12 pts), loops 3 (6 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1708}}}],"partialFingerprints":{"codehealthFindingId/v1":"3156e3a36e307f1abd55647697a9d19b2e201b998dd6aef92463305cdbd9d429"}},{"ruleId":"D2","level":"warning","message":{"text":"AttributeSeq.matchWithThreeOrLessQualifierParts (cognitive 19): AttributeSeq.matchWithThreeOrLessQualifierParts has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (10 pts), match/switch 5 (7 pts), boolean chains 2 (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"64406d5b55d66a711520d59b75211ee534c84e10923ace2b7ddabc425a5bb7a0"}},{"ruleId":"D2","level":"warning","message":{"text":"PushdownPredicatesAndPruneColumnsForCTEDef.gatherPredicatesAndAttributes (cognitive 19): PushdownPredicatesAndPruneColumnsForCTEDef.gatherPredicatesAndAttributes has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 3 (8 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushdownPredicatesAndPruneColumnsForCTEDef.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"8710c3057dbb67c3e2bbd73e3a39d35e82ff2dfff56e2f4160fbae6e494c2310"}},{"ruleId":"D2","level":"warning","message":{"text":"LikeSimplification.decodeLikePattern (cognitive 19): LikeSimplification.decodeLikePattern has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 2, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1032}}}],"partialFingerprints":{"codehealthFindingId/v1":"01b23d724e2c7753561c78e6a15b0faa1aab283194318369ca07cfeed0c06562"}},{"ruleId":"D2","level":"warning","message":{"text":"NullPropagation.apply (cognitive 19): NullPropagation.apply has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (10 pts), boolean chains 6, match/switch 2 (3 pts) (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1163}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcf53e53bde86f6b96ddd18f707654aa3ddf4bbe14f99dff519f6ad72de9ed0a"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractEquiJoinKeys.unapply (cognitive 19): ExtractEquiJoinKeys.unapply has cognitive complexity 19 (threshold 15). Drivers by points: boolean chains 9, if/else 4 (5 pts), match/switch 3 (5 pts) (nesting depth added 3). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b4286381177877bc0bd3ff07a4cc16a6b2725dafa731b61f06f30e15b1626e1"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinWith.typedJoinWith (cognitive 19): JoinWith.typedJoinWith has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (16 pts), match/switch 1 (2 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":849}}}],"partialFingerprints":{"codehealthFindingId/v1":"6138dd9e2c262ad0949fc23fdaeafc2dc80fe50fb5f1565dd2b191f741cfa013"}},{"ruleId":"D2","level":"warning","message":{"text":"KeyedShuffleSpec.isExpressionCompatible (cognitive 19): KeyedShuffleSpec.isExpressionCompatible has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (10 pts), match/switch 3 (5 pts), boolean chains 4 (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala"},"region":{"startLine":2391}}}],"partialFingerprints":{"codehealthFindingId/v1":"85480500c53fb9a6dd6f199c4d6c8bdc2e6b7f061817729c53030000eb455e0c"}},{"ruleId":"D2","level":"warning","message":{"text":"StaxXmlParser.appendXMLCharacterToVariant (cognitive 19): StaxXmlParser.appendXMLCharacterToVariant has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (14 pts), boolean chains 3, error handling 1, match/switch 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1407}}}],"partialFingerprints":{"codehealthFindingId/v1":"9433b5c8aba23892099322ba154725e24dd5bb231bddee50984964ce2c33e62b"}},{"ruleId":"D2","level":"warning","message":{"text":"Serializer.deserializeMethodArguments (cognitive 19): Serializer.deserializeMethodArguments has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 4 (12 pts), if/else 7 (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/Serializer.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"6de2b8fa063a79fd6fdf985c4cc2cb7c99c1142ef751f3f420471986e329b326"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingQueryManager.createQuery (cognitive 19): StreamingQueryManager.createQuery has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (14 pts), match/switch 3, boolean chains 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/StreamingQueryManager.scala"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c93944ee72c380bcb2a7350fed21beacd61b3f42d762d57a0cfcc3a7f07af86"}},{"ruleId":"D2","level":"warning","message":{"text":"PushDownLocalSort.pushDown (cognitive 19): PushDownLocalSort.pushDown has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 4 (9 pts), if/else 6 (8 pts), boolean chains 2 (nesting depth added 7). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/PushDownLocalSort.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"fef726894e06b9e0c95c318772361f94c6b90aa2af017bb895c77c90b1f627f6"}},{"ruleId":"D2","level":"warning","message":{"text":"ConvertSortMergeJoinToShuffledHashJoin.apply (cognitive 19): ConvertSortMergeJoinToShuffledHashJoin.apply has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (12 pts), boolean chains 4, match/switch 2 (3 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ConvertSortMergeJoinToShuffledHashJoin.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"15b9f2d8757cc4b3680eb35392a1fc168220ff71b99f8b2b18a6737d7e7ff49b"}},{"ruleId":"D2","level":"warning","message":{"text":"UnionExec.prepareOutputPartitioning (cognitive 19): UnionExec.prepareOutputPartitioning has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 5 (12 pts), if/else 6 (7 pts) (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala"},"region":{"startLine":1002}}}],"partialFingerprints":{"codehealthFindingId/v1":"6334e900a1b988065d4ea35c007cd6d82d8f2bf67d1507fa37b167fe56c52010"}},{"ruleId":"D2","level":"warning","message":{"text":"LoadDataCommand.run (cognitive 19): LoadDataCommand.run has cognitive complexity 19 (threshold 15). Drivers by points: if/else 13 (17 pts), boolean chains 1, error handling 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"416d9bedf38a7a4983da416861ef0d8321bed3669c9751e247bebeb9edf3547f"}},{"ruleId":"D2","level":"warning","message":{"text":"JdbcUtils.makeSetter (cognitive 19): JdbcUtils.makeSetter has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (10 pts), match/switch 4 (9 pts) (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":507}}}],"partialFingerprints":{"codehealthFindingId/v1":"0618f1119c65fa7185de0131d5161238a631d9581f3c5d3790405617871e89c9"}},{"ruleId":"D2","level":"warning","message":{"text":"ParquetFileFormat.buildParquetReader (cognitive 19): ParquetFileFormat.buildParquetReader has cognitive complexity 19 (threshold 15). Drivers by points: if/else 15, boolean chains 4. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cfbd27ebfdc6d688d7316863a8f488b927a3bae7a3f6649f2e71eaf04ab07e4"}},{"ruleId":"D2","level":"warning","message":{"text":"MapReader.readFromTyped (cognitive 19): MapReader.readFromTyped has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 4, loops 2 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a558fdf1a73873d6dae2df3aec96711f66c0e98d19d0b939acfbf0dc0038536"}},{"ruleId":"D2","level":"warning","message":{"text":"V2SessionCatalog.createTable0 (cognitive 19): V2SessionCatalog.createTable0 has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (15 pts), boolean chains 2, error handling 1, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2SessionCatalog.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"c216068d6682f00f77fbfea8ebb2415bf8050f62e0e1edc7965dd499cb4c0a06"}},{"ruleId":"D2","level":"warning","message":{"text":"PartitionJoinIterator.readBatch (cognitive 19): PartitionJoinIterator.readBatch has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (11 pts), match/switch 1 (5 pts), boolean chains 2, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ExternalLookupJoinEvaluatorFactory.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"95eb57fce3d49fdbedb20d5c45dc97b8f6ed25d659297fef30236300aff60097"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffledHashJoinExec.buildSideOrFullOuterJoinNonUniqueKey (cognitive 19): ShuffledHashJoinExec.buildSideOrFullOuterJoinNonUniqueKey has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoinExec.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"6258d14d0226be4b985f9dd42aa22d73a383dbb1380e5be614be44c6ff116ecd"}},{"ruleId":"D2","level":"warning","message":{"text":"SQLLastAttemptAccumulator.extractStageRDDScopes (cognitive 19): SQLLastAttemptAccumulator.extractStageRDDScopes has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 6 (10 pts), if/else 9 (nesting depth added 4). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1e149bd1c1dcc90fbb8d0464ae22428a49abe7d478f369c054591358dcf7599"}},{"ruleId":"D2","level":"warning","message":{"text":"InterpreterSession.onInterpreterThread (cognitive 19): InterpreterSession.onInterpreterThread has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (11 pts), error handling 3 (6 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/InProcessPythonRuntime.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"7fe4ba498d4f9a16439765e39d2ec2c8f3c16b08c0efde1d38d326c6c814fea0"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkPythonInitialStateRunner.writeNextBatchToArrowStream (cognitive 19): TransformWithStateInPySparkPythonInitialStateRunner.writeNextBatchToArrowStream has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkPythonRunner.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c316363a0ea1a9dc874ddbe9e8da233f49291c1bdd3c097706b4b7aa7a8ed4c"}},{"ruleId":"D2","level":"warning","message":{"text":"StatefulStreamlineAggregateExec.doExecute (cognitive 19): StatefulStreamlineAggregateExec.doExecute has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (9 pts), loops 3 (6 pts), boolean chains 2, match/switch 2 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcb9368199a76139ee6d12efaafa71c4a417c69835e828298c9608f29b7f9413"}},{"ruleId":"D2","level":"warning","message":{"text":"OneSideHashJoiner.storeAndJoinWithOtherSide (cognitive 19): OneSideHashJoiner.storeAndJoinWithOtherSide has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 4, match/switch 4 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":783}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a6ddb6c9bc3c9527462736d8d85706643fe48683037fb948134ea254528c552"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingV2ScanPushDown.checkPushedFilters (cognitive 19): StreamingV2ScanPushDown.checkPushedFilters has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 5 (12 pts), if/else 5 (7 pts) (nesting depth added 9). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":785}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4e11fc29a29aa1579f441828cb649ee6b2b4ce2d9235b069e25f4a99d847153"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingV2ScanPushDown.impliedBy (cognitive 19): StreamingV2ScanPushDown.impliedBy has cognitive complexity 19 (threshold 15). Drivers by points: boolean chains 10, match/switch 5, if/else 4. To reduce it, name the conditions: bind each compound test to a well-named local or a small predicate function, so the body reads as a sequence of named decisions rather than a chain of operators."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"f27be04d6c161c4131576c2a903236541cf0031c7f282cb836a59a580ed695cb"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDB.handleMetricsUpdate (cognitive 19): RocksDB.handleMetricsUpdate has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (19 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1288}}}],"partialFingerprints":{"codehealthFindingId/v1":"9415f6b63241f013584420b7089b7d189ca728e7c847571619dc45134d02d4ee"}},{"ruleId":"D2","level":"warning","message":{"text":"OracleDialect.getCatalystType (cognitive 19): OracleDialect.getCatalystType has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (14 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"09110352299597ca96f7094ce983cc6f88da99fb1acbee2505246f8e6f597901"}},{"ruleId":"D2","level":"warning","message":{"text":"SqlResource.sqlTable (cognitive 19): SqlResource.sqlTable has cognitive complexity 19 (threshold 15). Drivers by points: if/else 15 (16 pts), boolean chains 3 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/status/api/v1/sql/SqlResource.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"5462a1e32362a528eafc485b8e728ac17360a9acdc56af7f28d69322aa764c71"}},{"ruleId":"D2","level":"warning","message":{"text":"ReceiverInputDStream.createBlockRDD (cognitive 19): ReceiverInputDStream.createBlockRDD has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (19 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/ReceiverInputDStream.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a7157c7a0f59e24f73ddb86d99a2c1c2ccb384b52b821f40f4a2082531d49a2"}},{"ruleId":"D2","level":"warning","message":{"text":"Location.append (cognitive 19): Location.append has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (11 pts), error handling 1 (4 pts), boolean chains 3, ternaries 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":1036}}}],"partialFingerprints":{"codehealthFindingId/v1":"5256c27f670ab01cdc7c01745b325b6f09ed7c9820bf59dccaa924a13e2023fd"}},{"ruleId":"D2","level":"warning","message":{"text":"RemoteBlockPushResolver.reloadFinalizedAppAttemptsShuffleMergeInfo (cognitive 19): RemoteBlockPushResolver.reloadFinalizedAppAttemptsShuffleMergeInfo has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (12 pts), error handling 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":1180}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b468eab7eb67e59345759e24407900eb519416df2e508a0c8cf0b378ea011fd"}},{"ruleId":"D2","level":"warning","message":{"text":"ByteArrayMethods.arrayEquals (cognitive 19): ByteArrayMethods.arrayEquals has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (10 pts), loops 3 (5 pts), boolean chains 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"6743f453db57710b476d76b108fdfa2146e13d8e44b905a137412dcf51848ef2"}},{"ruleId":"D2","level":"warning","message":{"text":"AmIpFilter.doFilter (cognitive 19): AmIpFilter.doFilter has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/java/org/apache/spark/deploy/yarn/AmIpFilter.java"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"05148535f2532eacef53c57d359a74a3a66bb4cde7f8ac1d235c244bb725d257"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorizedRleValuesReader.readBatchInternal (cognitive 19): VectorizedRleValuesReader.readBatchInternal has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (14 pts), match/switch 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c3d1fef75b9aa9fba56c68f786db9c24256a4a208aa849cd8b326defae67136"}},{"ruleId":"D2","level":"warning","message":{"text":"Pipeline._fit (cognitive 19): Pipeline._fit has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3, boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"9449a6e19d992726132f39b47b0682efa5b6d80fe2ecf64a63c8d54665915aeb"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.squared_distance (cognitive 19): SparseVector.squared_distance has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 3 (6 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":719}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a8230a88fbb01b7093d656463fa65bb5018fbf5f961b99bdb61a51dbd52c0b"}},{"ruleId":"D2","level":"warning","message":{"text":"Pipeline._fit (cognitive 19): Pipeline._fit has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3, boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/pipeline.py"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"e21cd77365115a809e1d42dff77e43776ac6ad74e793a0c185a368592c6a4f62"}},{"ruleId":"D2","level":"warning","message":{"text":"_ValidatorSharedReadWrite.meta_estimator_transfer_param_maps_to_java (cognitive 19): _ValidatorSharedReadWrite.meta_estimator_transfer_param_maps_to_java has cognitive complexity 19 (threshold 15). Drivers by points: if/else 4 (11 pts), loops 3 (6 pts), boolean chains 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cdf4e54d6dece20ed930ec7a3e6be845f6368ed568bf14a7d58127319f2e40b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.squared_distance (cognitive 19): SparseVector.squared_distance has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 3 (6 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/__init__.py"},"region":{"startLine":826}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8d62d71b122dfd3fc342d46003a1cb9b1fae889b344873fc297615f6b27045a"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.replace (cognitive 19): DataFrame.replace has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (14 pts), boolean chains 5 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6520}}}],"partialFingerprints":{"codehealthFindingId/v1":"04ad6aa53d9a0f22781663c10e7c8b40fe933bf6762bae70d0202200606701ba"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.cov (cognitive 19): DataFrame.cov has cognitive complexity 19 (threshold 15). Drivers by points: loops 6 (9 pts), if/else 4, ternaries 2 (4 pts), boolean chains 2 (nesting depth added 5). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9549}}}],"partialFingerprints":{"codehealthFindingId/v1":"29f2e2716eddfd04c15c88779d6d878307df8735e71dcb88c29868a382ae368b"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._reindex_columns (cognitive 19): DataFrame._reindex_columns has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (12 pts), loops 3 (4 pts), ternaries 2 (3 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10738}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f927ff9d40a9d9d57cd592f5584f9a46d475cf9a7a1101d68aa1d2771cc2640"}},{"ruleId":"D2","level":"warning","message":{"text":"DatetimeIndex.__new__ (cognitive 19): DatetimeIndex.__new__ has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (19 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/datetimes.py"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e6f74f0047feba2d5ec6f8f5710e5c18e20d7baae74e8924fce698a6d05aba4"}},{"ruleId":"D2","level":"warning","message":{"text":"TimedeltaIndex.__new__ (cognitive 19): TimedeltaIndex.__new__ has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (19 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/timedelta.py"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2537d46b4ae9f755eb3a2d5ae9d58cf70c4cd02d5f92683630031489bfb941d"}},{"ruleId":"D2","level":"warning","message":{"text":"AtIndexer.__getitem__ (cognitive 19): AtIndexer.__getitem__ has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (15 pts), boolean chains 3, ternaries 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"f279070448722100a4ff8a15408b1b34097f893dd76b7b90c10962f1775dc82c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectClient._execute_and_fetch_as_iterator (cognitive 19): SparkConnectClient._execute_and_fetch_as_iterator has cognitive complexity 19 (threshold 15). Drivers by points: loops 4 (8 pts), error handling 3 (6 pts), if/else 4 (5 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1750}}}],"partialFingerprints":{"codehealthFindingId/v1":"825342bd43f8a587e5b4faa403640070a33247a14fd511963d52b18777e7df9b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession.stop (cognitive 19): SparkSession.stop has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (11 pts), error handling 3 (6 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":977}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b97da8ea10cb957a0503fb883a85504f73118e9ee09ef0e5d8a7232553547f0"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession._start_connect_server (cognitive 19): SparkSession._start_connect_server has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (16 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":1270}}}],"partialFingerprints":{"codehealthFindingId/v1":"17ae4bdca61be4af81e161a635dab617af77fe19a3f8ccbce5711457d1752c03"}},{"ruleId":"D2","level":"warning","message":{"text":"LocalDataToArrowConversion._create_converter (cognitive 19): LocalDataToArrowConversion._create_converter has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (15 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (LocalDataToArrowConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":664}}}],"partialFingerprints":{"codehealthFindingId/v1":"96e00f000b8c9a7773653672e9c45bf929742cb5478f1d56c7225df67a275a8e"}},{"ruleId":"D2","level":"warning","message":{"text":"LocalDataToArrowConversion._create_converter (cognitive 19): LocalDataToArrowConversion._create_converter has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (15 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (LocalDataToArrowConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":674}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e650f2b541edcb1b2c25d40d104c83c74cc2f5d8ed181e491abb6e236e0d9f3"}},{"ruleId":"D2","level":"warning","message":{"text":"types._parse_collation_metadata_map (cognitive 19): types._parse_collation_metadata_map has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (10 pts), boolean chains 3, loops 2 (3 pts), ternaries 1 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2800}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9c35400f610a81e4d0cc8e9f03689f135e882e34b6fe777b91fb8daf14d3f4e"}},{"ruleId":"D2","level":"warning","message":{"text":"UserDefinedFunction.__init__ (cognitive 19): UserDefinedFunction.__init__ has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (9 pts), boolean chains 4, ternaries 2 (4 pts), error handling 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"df588efc1d371abcfaf617c083865790741e490794e3761b3aa21ffdd36b3b88"}},{"ruleId":"D2","level":"warning","message":{"text":"getInnerText (cognitive 19): getInnerText has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (9 pts), boolean chains 5, loops 1 (3 pts), match/switch 1 (2 pts) (nesting depth added 5). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"d233856b8de6f13cb11c742c3b8f513a4e9430bfaedee6926f407f0082d5067b"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorAllocationManager.validateSettings (cognitive 18): ExecutorAllocationManager.validateSettings has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (12 pts), boolean chains 6 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"945ae953bf65e5ef5f1035f07b5ac9415c8c98d284fd59422cc3f3f389a63ed4"}},{"ruleId":"D2","level":"warning","message":{"text":"MapOutputTrackerMaster.getLocationsWithLargestOutputs (cognitive 18): MapOutputTrackerMaster.getLocationsWithLargestOutputs has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (15 pts), loops 1 (3 pts) (nesting depth added 12). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1256}}}],"partialFingerprints":{"codehealthFindingId/v1":"45b0f283894c1ea52f2d1313de5df51046cbae896b83fbafd8067d76c0e89fce"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConf.validateSettings (cognitive 18): SparkConf.validateSettings has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (10 pts), boolean chains 5, match/switch 1 (2 pts), loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkConf.scala"},"region":{"startLine":552}}}],"partialFingerprints":{"codehealthFindingId/v1":"998bd4d0c94b4fbdcb1a5235d659992aaa683bf80524a3a004a5f61284f4dfa9"}},{"ruleId":"D2","level":"warning","message":{"text":"ReaderInputStream.writeBufferedInputToPythonWorker (cognitive 18): ReaderInputStream.writeBufferedInputToPythonWorker has cognitive complexity 18 (threshold 15). Drivers by points: boolean chains 6, if/else 3 (6 pts), loops 3 (6 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1577}}}],"partialFingerprints":{"codehealthFindingId/v1":"73afc21a1aabb669f153f192380857a87cfe144b42ac6b6a0d9d97af302220cd"}},{"ruleId":"D2","level":"warning","message":{"text":"PipelinedWriterRunnable.run (cognitive 18): PipelinedWriterRunnable.run has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (10 pts), error handling 4 (5 pts), boolean chains 2, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1649}}}],"partialFingerprints":{"codehealthFindingId/v1":"05b0dc75b82f54b7637d1e0881b8f948c336be63817323bdb3df75db5b2acb90"}},{"ruleId":"D2","level":"warning","message":{"text":"RPackageUtils.extractRFolder (cognitive 18): RPackageUtils.extractRFolder has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (17 pts), loops 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"823ea9e71f3db1e1bdd266b3f01fe6994e806d23829bc11c0b0d7c783fbba0f2"}},{"ruleId":"D2","level":"warning","message":{"text":"Executor.stop (cognitive 18): Executor.stop has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (13 pts), error handling 2 (4 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":651}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcb189526b1f319880ee58b55033ef8f3e0f6b77a577ba55800468fc21bde3e6"}},{"ruleId":"D2","level":"warning","message":{"text":"Executor.updateDependencies (cognitive 18): Executor.updateDependencies has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":1453}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b5540c49eb35f4b3cc604c82b5b0c1d805c17cee6207c4cb2e310039b7f8b1d"}},{"ruleId":"D2","level":"warning","message":{"text":"NettyRpcEnv.askAbortable (cognitive 18): NettyRpcEnv.askAbortable has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (10 pts), match/switch 4 (7 pts), error handling 1 (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/netty/NettyRpcEnv.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"7740c4423f4597f3ccbb8ee53e6805fc3f50945c13646350a4e58d54fae963e2"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.removeExecutorAndUnregisterOutputs (cognitive 18): DAGScheduler.removeExecutorAndUnregisterOutputs has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (11 pts), boolean chains 4, match/switch 1 (3 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4925}}}],"partialFingerprints":{"codehealthFindingId/v1":"2eff1f778172214081881f8391d297231a73be4eb9c3c0a1240859891a0b352d"}},{"ruleId":"D2","level":"warning","message":{"text":"ShuffleBlockPusher.pushUpToMax (cognitive 18): ShuffleBlockPusher.pushUpToMax has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (8 pts), loops 3 (6 pts), boolean chains 4 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/ShuffleBlockPusher.scala"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"82ac989b2583a4da4e081455525c69d6495e755315cad704f7d185dadadd187e"}},{"ruleId":"D2","level":"warning","message":{"text":"AppStatusStore.newStageData (cognitive 18): AppStatusStore.newStageData has cognitive complexity 18 (threshold 15). Drivers by points: if/else 12 (17 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusStore.scala"},"region":{"startLine":630}}}],"partialFingerprints":{"codehealthFindingId/v1":"b239f460ab2d3215584407cb62c09451ca0187018ba41b20306cb6b94048394a"}},{"ruleId":"D2","level":"warning","message":{"text":"MemoryStore.evictBlocksToFreeSpace (cognitive 18): MemoryStore.evictBlocksToFreeSpace has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (13 pts), boolean chains 3, loops 1, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala"},"region":{"startLine":474}}}],"partialFingerprints":{"codehealthFindingId/v1":"77bc60b93484e2ede2bbb74af74c0b166842bd9842a036c1b1c0f7f9ef45c707"}},{"ruleId":"D2","level":"warning","message":{"text":"LastAttemptAccumulator.mergeLastAttempt (cognitive 18): LastAttemptAccumulator.mergeLastAttempt has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (16 pts), error handling 1, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/LastAttemptAccumulator.scala"},"region":{"startLine":706}}}],"partialFingerprints":{"codehealthFindingId/v1":"3aec72f0780dd99f7c8002f2e58b199259c2337e8c0040de0222c64009b56c7c"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkUncaughtExceptionHandler.uncaughtException (cognitive 18): SparkUncaughtExceptionHandler.uncaughtException has cognitive complexity 18 (threshold 15). Drivers by points: error handling 4 (6 pts), if/else 5 (6 pts), match/switch 1 (3 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/SparkUncaughtExceptionHandler.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"860a31151abe305a50dbcf3ba6cc5167ce99f94917fb57151fa38fec67da00d7"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemvImpl (cognitive 18): BLAS.gemvImpl has cognitive complexity 18 (threshold 15). Drivers by points: loops 4 (10 pts), if/else 7 (8 pts) (nesting depth added 7). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":853}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cc276b4b7075f60f8f992aa7d73748109d3758e76ee6c50a5e58e3131bdbe44"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseMatrix.genRandMatrix (cognitive 18): SparseMatrix.genRandMatrix has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 3 (7 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":976}}}],"partialFingerprints":{"codehealthFindingId/v1":"d888954ae94079d2bdbca0629cbc23777b482967ecd1b34f3d57ac21900d2634"}},{"ruleId":"D2","level":"warning","message":{"text":"LogisticRegression.createOptimizer (cognitive 18): LogisticRegression.createOptimizer has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (15 pts), boolean chains 3 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":775}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7ca0881535f43849a31678441ed4618b47842033c81af43e875828878f9dbf8"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneralizedLinearRegressionTrainingSummary.toString (cognitive 18): GeneralizedLinearRegressionTrainingSummary.toString has cognitive complexity 18 (threshold 15). Drivers by points: match/switch 5 (11 pts), if/else 5 (7 pts) (nesting depth added 8). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala"},"region":{"startLine":1621}}}],"partialFingerprints":{"codehealthFindingId/v1":"df3499d1a79c1962bbe54b9ae673fd76c651092a761e9cc9c92e10ebaf89a147"}},{"ruleId":"D2","level":"warning","message":{"text":"BLAS.gemv (cognitive 18): BLAS.gemv has cognitive complexity 18 (threshold 15). Drivers by points: loops 4 (10 pts), if/else 7 (8 pts) (nesting depth added 7). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala"},"region":{"startLine":717}}}],"partialFingerprints":{"codehealthFindingId/v1":"b47d400467cbd0d1d9d606d530bd2a4394a2a2c236fce67930db13ccc93249e1"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseMatrix.genRandMatrix (cognitive 18): SparseMatrix.genRandMatrix has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 3 (7 pts), boolean chains 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala"},"region":{"startLine":837}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b5894fec057e4eedb925671566afa658171da2ee9b28ee57a49a6470f43acbd"}},{"ruleId":"D2","level":"warning","message":{"text":"YarnAllocator.runAllocatedContainers (cognitive 18): YarnAllocator.runAllocatedContainers has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (13 pts), error handling 1 (4 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":755}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bbaa65033cc0ee31786a6a30e86317e4e4573412738d3a00d530407ed48179c"}},{"ruleId":"D2","level":"warning","message":{"text":"HandleNullInputsForUDF.apply (cognitive 18): HandleNullInputsForUDF.apply has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (10 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":3915}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1969a776d5210404af90ac9bf6c27e7daadd63124240a3465b3f02a20784b19"}},{"ruleId":"D2","level":"warning","message":{"text":"RelationResolution.resolveRelation (cognitive 18): RelationResolution.resolveRelation has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 4, match/switch 1 (2 pts), loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"df25e69d6ac361a15b446c5079eb561aa63dc11a3578861957b4cb31c6600f4d"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveCatalogs.apply (cognitive 18): ResolveCatalogs.apply has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (15 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd8380548192e317234c9f2095e6efa70edac46765c0ea47e97c5807ebfe3ffc"}},{"ruleId":"D2","level":"warning","message":{"text":"StreamingJoinHelper.collectTerms (cognitive 18): StreamingJoinHelper.collectTerms has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (13 pts), match/switch 3 (5 pts) (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/StreamingJoinHelper.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"674c90336f5f700cdd0cd2944e441b326b2255993475412fe27fda724ae2b182"}},{"ruleId":"D2","level":"warning","message":{"text":"UnivocityParser.makeConverter (cognitive 18): UnivocityParser.makeConverter has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (9 pts), match/switch 3 (5 pts), error handling 2 (4 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"437f62a08f7391093951452569e4219ad6845344cf8d5659c79f55426bd93df0"}},{"ruleId":"D2","level":"warning","message":{"text":"Cast.castToShort (cognitive 18): Cast.castToShort has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (15 pts), error handling 1 (2 pts), match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1250}}}],"partialFingerprints":{"codehealthFindingId/v1":"e39561fc55040bb70f6db1739191617a77cd90ee0908af20926bf497fb7fd2f8"}},{"ruleId":"D2","level":"warning","message":{"text":"Cast.castToByte (cognitive 18): Cast.castToByte has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (15 pts), error handling 1 (2 pts), match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1314}}}],"partialFingerprints":{"codehealthFindingId/v1":"70c6fc9d4ff0735056f8467bd46bb661f553ffad0360ca6d6c7ee23b26bd0e4a"}},{"ruleId":"D2","level":"warning","message":{"text":"InternalSequenceBase.eval (cognitive 18): InternalSequenceBase.eval has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":4143}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6063b07b764c03deac3e027a0e9be420b1c87e878975ec9bb2723c6fba5f2f8"}},{"ruleId":"D2","level":"warning","message":{"text":"UpdateFields.fieldSources (cognitive 18): UpdateFields.fieldSources has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (11 pts), match/switch 5 (7 pts) (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala"},"region":{"startLine":1085}}}],"partialFingerprints":{"codehealthFindingId/v1":"e15a35e6a14c6060735c8d4ea4e4d58c93ce0afc4ee1ea37fdf9db1a4a3df942"}},{"ruleId":"D2","level":"warning","message":{"text":"ZipWith.eval (cognitive 18): ZipWith.eval has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 1 (3 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1827}}}],"partialFingerprints":{"codehealthFindingId/v1":"b31c7fd5be43977f57295aa4ac09ccae638112a6617f1283dc6993fd8f2f84cb"}},{"ruleId":"D2","level":"warning","message":{"text":"JacksonParser.convertMap (cognitive 18): JacksonParser.convertMap has cognitive complexity 18 (threshold 15). Drivers by points: error handling 3 (9 pts), if/else 4, match/switch 2 (4 pts), loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":656}}}],"partialFingerprints":{"codehealthFindingId/v1":"80df40c1ffa8cad505bd8a1c5c0e068d49193d469e90176946ff847ae3952bf9"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonInferSchema.compatibleType (cognitive 18): JsonInferSchema.compatibleType has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (9 pts), loops 3 (6 pts), boolean chains 2, match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"022aabd6750bab5fc6bcf72d2809cb5135670b31277cddb9fb77a2feff9245d6"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeRand.eliminateRand (cognitive 18): OptimizeRand.eliminateRand has cognitive complexity 18 (threshold 15). Drivers by points: if/else 13 (17 pts), match/switch 1 (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeRand.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"00aa219a0a82b0d94fcb86f4ba0258f3786aae139a4beaccc17f66413116408b"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeSubqueries.optimize (cognitive 18): OptimizeSubqueries.optimize has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"2466afb7d0d056d30e76b5676a12ac37564614e628dbce33857f672a4292ef9f"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitFromClause (cognitive 18): AstBuilder.visitFromClause has cognitive complexity 18 (threshold 15). Drivers by points: if/else 13 (16 pts), match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2096}}}],"partialFingerprints":{"codehealthFindingId/v1":"63293f1203bd64dd5a5f724eeb0574717a87c561d7fda5aedae8ca01ffdafbf8"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitJsonQuery (cognitive 18): AstBuilder.visitJsonQuery has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 3 (6 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":4333}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b0ad2c9780a83361638034a158c4a4833714b143ddae4db579f0dd9bcbde82b"}},{"ruleId":"D2","level":"warning","message":{"text":"Project.reconcileColumnType (cognitive 18): Project.reconcileColumnType has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (16 pts), boolean chains 1, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ea876f8743d02561bcc731cf5e745e66933af8ab7a08373a4bb772c8782cd5a"}},{"ruleId":"D2","level":"warning","message":{"text":"TreeNode.mapChildren (cognitive 18): TreeNode.mapChildren has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":811}}}],"partialFingerprints":{"codehealthFindingId/v1":"90960c8c31f2614ddbcfd688f78b8903b67a502b7882d7e09b5e1b59c185cc0f"}},{"ruleId":"D2","level":"warning","message":{"text":"NumberConverter.encode (cognitive 18): NumberConverter.encode has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (16 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a7069b10d0dfb7dd7e2eb53d807e2461e876612cfaad23da55f7a0c7f2b56a4"}},{"ruleId":"D2","level":"warning","message":{"text":"MLHandler.startHangingHandlerReaper (cognitive 18): MLHandler.startHangingHandlerReaper has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (11 pts), loops 2 (6 pts), error handling 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/MLHandler.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"85359d2a264d2a6774f1597902e41fb9318a1e5c7d6959b348c7fd9a72c837dc"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformWithRelations (cognitive 18): SparkConnectPlanner.transformWithRelations has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 2 (4 pts), boolean chains 3, error handling 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":4677}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c5c8560dac87fa101295787fc68704b102b5c2d46ba5b919aa28e6bc94e1ef4"}},{"ruleId":"D2","level":"warning","message":{"text":"SessionStatsPagedTable.renderMLCacheStatus (cognitive 18): SessionStatsPagedTable.renderMLCacheStatus has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (16 pts), match/switch 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"71f65ffe1fa4d5d35b96cc18a986b25397fcf67518bf6f6c19ae9772bc146cc5"}},{"ruleId":"D2","level":"warning","message":{"text":"AvroFileFormat.buildReader (cognitive 18): AvroFileFormat.buildReader has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (10 pts), error handling 1 (3 pts), match/switch 1 (3 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"57f1ecff643c17a8a3d309327ab716c36b94c3f041753eb78ff9dad6822b0627"}},{"ruleId":"D2","level":"warning","message":{"text":"BroadcastValueProjector.collectExactValueDomain (cognitive 18): BroadcastValueProjector.collectExactValueDomain has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 1, error handling 1, loops 1, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/BroadcastValueProjector.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"22252be4a75c4fe62e5e0b0b5eeac431521bf08ad1ff79790e5f2dbfd61eaf5c"}},{"ruleId":"D2","level":"warning","message":{"text":"SQLExecution.withNewExecutionId0 (cognitive 18): SQLExecution.withNewExecutionId0 has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9, error handling 4 (5 pts), boolean chains 2, match/switch 2 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"816e186f3a542c56eb4191c46b1779a4b4b346b3a7cc7a9eef019ea939bf2e34"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSqlAstBuilder.visitCreateView (cognitive 18): SparkSqlAstBuilder.visitCreateView has cognitive complexity 18 (threshold 15). Drivers by points: if/else 12 (14 pts), boolean chains 4 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":781}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cc16688e0cf4fd84f84d121ba2dd7e24484c80c3815cdab279a6f6f62b3bb11"}},{"ruleId":"D2","level":"warning","message":{"text":"ObjectAggregationIterator.processInputs (cognitive 18): ObjectAggregationIterator.processInputs has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (9 pts), loops 3 (7 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationIterator.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6773e3374814fb665a0b18c2b847c7dd2ef280c9ac184f42c3c475fa4cd22c"}},{"ruleId":"D2","level":"warning","message":{"text":"SortBasedAggregator.destructiveIterator (cognitive 18): SortBasedAggregator.destructiveIterator has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (10 pts), boolean chains 4, loops 2 (4 pts) (nesting depth added 3). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationIterator.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"edea18b6fdd9262c736816ca304af0ea6679eaf6a81c9271ee5319e5a6af0211"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneratePredicateHelper.generatePredicateCode (cognitive 18): GeneratePredicateHelper.generatePredicateCode has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10, boolean chains 5, match/switch 2 (3 pts) (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"c22aed90b9e4225f3aa6a9c91f06360030d7dd26d1fcc5e5fb800369e9247eb3"}},{"ruleId":"D2","level":"warning","message":{"text":"LoadDataCommand.makeQualified (cognitive 18): LoadDataCommand.makeQualified has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"fce55d5a09f3dd7c8376267786c69bd665de0f22af33f75572abc8b9f30b94de"}},{"ruleId":"D2","level":"warning","message":{"text":"CreateViewCommand.run (cognitive 18): CreateViewCommand.run has cognitive complexity 18 (threshold 15). Drivers by points: if/else 15 (18 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"176d08c067c65edf9279cd6987525886c2bbd1cd1e505de984f57835048801ef"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSourceAnalysis.apply (cognitive 18): DataSourceAnalysis.apply has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 5, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd1f3964a1299b7d5dc59c25380bb1c03a26876966cbea3b831c7068f750967a"}},{"ruleId":"D2","level":"warning","message":{"text":"JDBCRDD.compute (cognitive 18): JDBCRDD.compute has cognitive complexity 18 (threshold 15). Drivers by points: error handling 6 (8 pts), if/else 6 (7 pts), boolean chains 2, match/switch 1 (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d0c5dd1a181ef18bc9d506ab4e113e2fad0fcfa7ab31d41574a3dd2777d2b92"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnDomain.toString (cognitive 18): ColumnDomain.toString has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (15 pts), match/switch 2 (3 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b076fb6e7ac8b4cfb1d7f1ef03dd29c4ae510990ab5b31d7cdbf0c96a8a5924"}},{"ruleId":"D2","level":"warning","message":{"text":"PlanExternalUDFs.extractExternalUDFFromAggregate (cognitive 18): PlanExternalUDFs.extractExternalUDFFromAggregate has cognitive complexity 18 (threshold 15). Drivers by points: match/switch 3 (10 pts), if/else 5 (8 pts) (nesting depth added 10). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PlanExternalUDFs.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec5f1cd67436f7f4dc0692891fa9e3136c6e5665a4796590853f33531fc36d92"}},{"ruleId":"D2","level":"warning","message":{"text":"HashJoin.codegenOuter (cognitive 18): HashJoin.codegenOuter has cognitive complexity 18 (threshold 15). Drivers by points: if/else 14 (17 pts), match/switch 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f6f5d28b16e60fe07ae68e1b4d0d814b42859e88ef42dad10aa19fa8ebe6125"}},{"ruleId":"D2","level":"warning","message":{"text":"IntervalIndex.apply (cognitive 18): IntervalIndex.apply has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (13 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":442}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc5cdbf3b1ea36f46b464e1616f7b75e2c74b34f4ac158829fb307e7fc96853"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeAsOfJoinScanner.iterator (cognitive 18): SortMergeAsOfJoinScanner.iterator has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 1, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeAsOfJoinExec.scala"},"region":{"startLine":667}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0e8ed8f8c562884e56b52b10f78da29a22865cd789b9a1ed93e643fc8028b38"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.serveRequests (cognitive 18): TransformWithStateInPySparkStateServer.serveRequests has cognitive complexity 18 (threshold 15). Drivers by points: error handling 5 (12 pts), if/else 3 (4 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"54d760add11ad7c4d0758fbc9c08a0bb80a18e0a015eff1167985b6d7bad6c25"}},{"ruleId":"D2","level":"warning","message":{"text":"TransformWithStateInPySparkStateServer.handleTimerRequest (cognitive 18): TransformWithStateInPySparkStateServer.handleTimerRequest has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (15 pts), match/switch 2 (3 pts) (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"64fe4e3f6e5d0f37f43dce669d35f652836b8284271d4ab68efb314eba0e85a7"}},{"ruleId":"D2","level":"warning","message":{"text":"SymmetricHashJoinStateManagerV4.initializeStateStore (cognitive 18): SymmetricHashJoinStateManagerV4.initializeStateStore has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (18 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"116027099df815b5a8232552179bca787ada153e54b9420ce01e85cd2db7613b"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveExternalCatalog.createTable (cognitive 18): HiveExternalCatalog.createTable has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (10 pts), boolean chains 4, error handling 1 (2 pts), match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec2c996ab85784f052a709993c117ba38f486bbda7c951004a2223cf4b97700c"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveClientImpl.runHive (cognitive 18): HiveClientImpl.runHive has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (12 pts), error handling 3 (5 pts), match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":938}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef4cd95b93a197070e433f701eaa62f53c062f1f62648a5da8a2bcf7063e4310"}},{"ruleId":"D2","level":"warning","message":{"text":"ServerConnection.handle (cognitive 18): ServerConnection.handle has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (15 pts), ternaries 1 (2 pts), error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/LauncherServer.java"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5c16a0e85ddc3f4ab360f98fd423c1143ed1873bf4ecba976ed0426e8dd71ff"}},{"ruleId":"D2","level":"warning","message":{"text":"MessageEncoder.encode (cognitive 18): MessageEncoder.encode has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (10 pts), ternaries 2 (5 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"0114f91ef79a7ad055095fd43c8b5928a7f0f7b6457eca873f437f9c4c2dc031"}},{"ruleId":"D2","level":"warning","message":{"text":"RemoteBlockPushResolver.finalizeShuffleMerge (cognitive 18): RemoteBlockPushResolver.finalizeShuffleMerge has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (11 pts), error handling 1 (3 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":762}}}],"partialFingerprints":{"codehealthFindingId/v1":"87d8414dfe6b351227c895fa8c5a93b219f65a0c787814c3a667472a7ae21a5c"}},{"ruleId":"D2","level":"warning","message":{"text":"PushBlockStreamCallback.onData (cognitive 18): PushBlockStreamCallback.onData has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":1439}}}],"partialFingerprints":{"codehealthFindingId/v1":"8de1701d339dc6219bff0061263316253f0054b0874475155ff777c34d6c8f3f"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationSpecICU.collationNameToId (cognitive 18): CollationSpecICU.collationNameToId has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (14 pts), loops 2, match/switch 1 (2 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java"},"region":{"startLine":889}}}],"partialFingerprints":{"codehealthFindingId/v1":"886fb3c87934d8d4dc429285136910b4039a18fc829d5a53bef3440c24b82965"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.substring (cognitive 18): UTF8String.substring has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (8 pts), loops 2 (5 pts), boolean chains 3, ternaries 1 (2 pts) (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":645}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d2fe468c9ee517828aea123034f1af5b1fa880034f5ac19e3638b9603f8fb09"}},{"ruleId":"D2","level":"warning","message":{"text":"AwsStsCredentialProvider.init (cognitive 18): AwsStsCredentialProvider.init has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (11 pts), boolean chains 5, error handling 1 (2 pts) (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/credential-aws/src/main/java/org/apache/spark/security/aws/AwsStsCredentialProvider.java"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"24f6c464658b659df4ade08bc0b57c69d226776e8e6f3f2b00e030eed688f8e1"}},{"ruleId":"D2","level":"warning","message":{"text":"HadoopLineRecordReader.initialize (cognitive 18): HadoopLineRecordReader.initialize has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 2 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/HadoopLineRecordReader.java"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"28e1638cb9bf4234c1936f5991eab0551d3476a1f9397e244ffc3927eec36db6"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveAuthFactory.\u003Cinit\u003E (cognitive 18): HiveAuthFactory.\u003Cinit\u003E has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 1 (3 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"933f0697f3b22986c6b403a53be173250162a10ac9b4388d7e78c97ec78ab1c4"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowWindowAggIncrementalUDFHandler.run (cognitive 18): ArrowWindowAggIncrementalUDFHandler.run has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (10 pts), loops 3 (7 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":620}}}],"partialFingerprints":{"codehealthFindingId/v1":"eff0a287bbeeeb57b5ef1807c95873ec84d17cc8dbed74e079de3397ff1c64e2"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowUDTFWithPartition._process_arrow_batch_by_partitions (cognitive 18): ArrowUDTFWithPartition._process_arrow_batch_by_partitions has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 3 (5 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_udtf.py"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8f004f531c66dc796a524becffb9a315598482f0dd830bb9496511060e228fa"}},{"ruleId":"D2","level":"warning","message":{"text":"_ValidatorSharedReadWrite.meta_estimator_transfer_param_maps_from_java (cognitive 18): _ValidatorSharedReadWrite.meta_estimator_transfer_param_maps_from_java has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (11 pts), loops 3 (6 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e0cab423e46cb115fb6a0f9a050a66d9f0ee84a7c4e4c390ef66e13f89949d3"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupBy._resolve_grouping_from_diff_dataframes (cognitive 18): GroupBy._resolve_grouping_from_diff_dataframes has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":3798}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e3a79ebc6c01ba9549dc830eae1a699b97f8edd8b3979c86e5687247cc5e91f"}},{"ruleId":"D2","level":"warning","message":{"text":"plotly.plot_pie (cognitive 18): plotly.plot_pie has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (11 pts), loops 1 (3 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a255a9d42b7443e519548ba2707d00cf2ce586f75ebecbd01eb3c353bb67642"}},{"ruleId":"D2","level":"warning","message":{"text":"plotly.plot_box (cognitive 18): plotly.plot_box has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (9 pts), ternaries 2 (5 pts), loops 2 (4 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"24e04dd2b5c99a396df9be0c746b005f5bfce57eaebf6780c8be2b69d0c79501"}},{"ruleId":"D2","level":"warning","message":{"text":"udf._create_py_udf (cognitive 18): udf._create_py_udf has cognitive complexity 18 (threshold 15). Drivers by points: if/else 9 (12 pts), error handling 3 (6 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"2baff37fcd6bb59d75d86902eaa0bf68e52aac07cfa77dcf8d5828205befe463"}},{"ruleId":"D2","level":"warning","message":{"text":"functions.vectorized_udf (cognitive 18): functions.vectorized_udf has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 5 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/functions.py"},"region":{"startLine":783}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d8447cb856a2b3e7377c89518d2c8743206154ca25ad352a83b7eac5f84f2ef"}},{"ruleId":"D2","level":"warning","message":{"text":"transpile._get_function_from_ast (cognitive 18): transpile._get_function_from_ast has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 4 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":1306}}}],"partialFingerprints":{"codehealthFindingId/v1":"96ea59a7f9e235b113dee26491a56e86a288b93d7727058e626d8ed166328543"}},{"ruleId":"D2","level":"warning","message":{"text":"analyze_udtf._main (cognitive 18): analyze_udtf._main has cognitive complexity 18 (threshold 15). Drivers by points: boolean chains 6, if/else 4 (5 pts), loops 3, ternaries 2 (3 pts), error handling 1 (nesting depth added 2). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/analyze_udtf.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"8382c5fe7505b30ae98889f984af5c2b56ff7f53e51b522e2b493bf4d5d2d2ad"}},{"ruleId":"D2","level":"warning","message":{"text":"stagepage.reselectCheckboxesBasedOnTaskTableState (cognitive 18): stagepage.reselectCheckboxesBasedOnTaskTableState has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 2 (4 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e44454aa5b033188e77e1259717bff74dd8497a3927783df287d7e138b48441"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkContext.resumeExecutors (cognitive 17): SparkContext.resumeExecutors has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (8 pts), error handling 1 (4 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2286}}}],"partialFingerprints":{"codehealthFindingId/v1":"3928f9c1e058c5f15cc046971680f30a7a04aca802a0edf244b570f5c0b1bde3"}},{"ruleId":"D2","level":"warning","message":{"text":"RPackageUtils.checkAndBuildRPackage (cognitive 17): RPackageUtils.checkAndBuildRPackage has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (17 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"a50a7ce464f5406bac34e94553d550945aabc681cc56d7c5b6308bb8852eaa60"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.addPendingTask (cognitive 17): TaskSetManager.addPendingTask has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (7 pts), loops 2 (5 pts), match/switch 2 (5 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"a817e7b07f882fdcef419116853a4ab546c5ffda02c91d836aa4a963ea1ff315"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.resourceOffer (cognitive 17): TaskSetManager.resourceOffer has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 5 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc2b37a636594f115c1d78aacba0a35cc396db40bcf1004924b49fe8493aa42"}},{"ruleId":"D2","level":"warning","message":{"text":"ExecutorMonitor.onJobEnd (cognitive 17): ExecutorMonitor.onJobEnd has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (17 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/dynalloc/ExecutorMonitor.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ae11004bb7492bb36ba8279bb41b622cc11da79b55be80e14ae0b2c61d459f6"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManager.getCurrentBlockStatus (cognitive 17): BlockManager.getCurrentBlockStatus has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 3, match/switch 1 (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1090}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fa3b357299cd9873be4d39668a98fc8a1291ddc8d773a9717c077e897db145e"}},{"ruleId":"D2","level":"warning","message":{"text":"SizeEstimator.getClassInfo (cognitive 17): SizeEstimator.getClassInfo has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (11 pts), error handling 1 (4 pts), loops 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/SizeEstimator.scala"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcadeea3ea7aff15d79b9e1a7e01348fd81761aef9acc3a24a19eff67fbdcce5"}},{"ruleId":"D2","level":"warning","message":{"text":"LinearRegression.createOptimizer (cognitive 17): LinearRegression.createOptimizer has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (15 pts), boolean chains 1, match/switch 1 (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":505}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4276c485a3b7e34df932674e21b2e01b9bf461cac1ec9d092a4e8d7eaea9bb0"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnResolutionHelper.resolveLateralColumnAlias (cognitive 17): ColumnResolutionHelper.resolveLateralColumnAlias has cognitive complexity 17 (threshold 15). Drivers by points: match/switch 6 (10 pts), if/else 5 (7 pts) (nesting depth added 6). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ColumnResolutionHelper.scala"},"region":{"startLine":354}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1e371363818440ad3a5907aedd50e6d8f62acda56b2a3dcb2c91f1409477574"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolverGuard.checkUnresolvedFunction (cognitive 17): ResolverGuard.checkUnresolvedFunction has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (11 pts), match/switch 2 (6 pts) (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ResolverGuard.scala"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"1805ba13ceb94fdc8e34c9319ab98b5d5f6a046e14336693b9e1d236a4862f19"}},{"ruleId":"D2","level":"warning","message":{"text":"EquivalentExpressions.alwaysEvaluatedDefinitions (cognitive 17): EquivalentExpressions.alwaysEvaluatedDefinitions has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (11 pts), match/switch 2 (6 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/EquivalentExpressions.scala"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cf3d3f50f53f1a9ade5f772e7558b8dd21defad96429e53c27a164c880cac4c"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaPruning.getArrayReturningHigherOrderFunctionRootFields (cognitive 17): SchemaPruning.getArrayReturningHigherOrderFunctionRootFields has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 3 (7 pts), boolean chains 1 (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SchemaPruning.scala"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"69b666b0039b876380b6403167d2552fbc000041d4c82a2ac251f59d20fb0b91"}},{"ruleId":"D2","level":"warning","message":{"text":"Sequence.eval (cognitive 17): Sequence.eval has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (14 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":3738}}}],"partialFingerprints":{"codehealthFindingId/v1":"22b8e2581b820d833055c5a99d2054bec91032722470e99692437698f56b952f"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonTableEvaluator.descendInto (cognitive 17): JsonTableEvaluator.descendInto has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (9 pts), loops 2 (4 pts), boolean chains 3, match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1123}}}],"partialFingerprints":{"codehealthFindingId/v1":"b11aca14eb61cd0e7d0955b4110af19dfaff9eda101af7fe31dd9585e0ffdd56"}},{"ruleId":"D2","level":"warning","message":{"text":"ConvertToCatalyst.convertOperator (cognitive 17): ConvertToCatalyst.convertOperator has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 3, match/switch 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1126}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a54e9c40fbfb28c13f7207d47eb2aecabc9b85001cc5bada79caf7e2fd92fb7"}},{"ruleId":"D2","level":"warning","message":{"text":"CollapseProject.mergeProjectExpressions (cognitive 17): CollapseProject.mergeProjectExpressions has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (10 pts), match/switch 3 (4 pts), boolean chains 3 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1810}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a904f1d5e31ec6a060f017d554e237459dbae434426717bbf48fa64eddd3d65"}},{"ruleId":"D2","level":"warning","message":{"text":"PushdownPredicatesAndPruneColumnsForCTEDef.pushdownPredicatesAndAttributes (cognitive 17): PushdownPredicatesAndPruneColumnsForCTEDef.pushdownPredicatesAndAttributes has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (12 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushdownPredicatesAndPruneColumnsForCTEDef.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"d44150a72cf9ddf6f7bb2468ef814bae8ae814997e266507b57ec7e40628eb2f"}},{"ruleId":"D2","level":"warning","message":{"text":"RewriteCorrelatedScalarSubquery.evalSubqueryOnZeroTups (cognitive 17): RewriteCorrelatedScalarSubquery.evalSubqueryOnZeroTups has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (11 pts), match/switch 3 (6 pts) (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":793}}}],"partialFingerprints":{"codehealthFindingId/v1":"e86bae0889b6555414a7b05989cb0d2a04abe68d80bdb6d9bc6d0843161cc229"}},{"ruleId":"D2","level":"warning","message":{"text":"HyperLogLogPlusPlusHelper.query (cognitive 17): HyperLogLogPlusPlusHelper.query has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (9 pts), boolean chains 4, loops 2 (3 pts), match/switch 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/HyperLogLogPlusPlusHelper.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"50ab28f462b7e5b2375d30bc8f0564b14a4594112804977bb1bb6494abee820e"}},{"ruleId":"D2","level":"warning","message":{"text":"SQLConf.get (cognitive 17): SQLConf.get has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (17 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"52f0715dcc7155eb915236b5b4ab9212f4c755071bc9177766e1b05b8d7e00b3"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.handleWriteStreamOperationStart (cognitive 17): SparkConnectPlanner.handleWriteStreamOperationStart has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (12 pts), match/switch 3 (4 pts), error handling 1 (nesting depth added 2). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":3704}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ba5cfd09d938905d3570be9ba9df2b7d9e8c96e57520f2edf41053c08c53873"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.handleStreamingQueryCommand (cognitive 17): SparkConnectPlanner.handleStreamingQueryCommand has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (13 pts), match/switch 3 (4 pts) (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":3880}}}],"partialFingerprints":{"codehealthFindingId/v1":"8616ef8180b9f837b317c59cf3a9618b7276300f2e8a28bc361b9c4d5292633b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectAnalyzeHandler.process (cognitive 17): SparkConnectAnalyzeHandler.process has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (13 pts), match/switch 2 (3 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectAnalyzeHandler.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"476d3f1ab6af52a4b532591afc530996d795e816be90fc624f5e759dee2d772a"}},{"ruleId":"D2","level":"warning","message":{"text":"ResolveTranspose.apply (cognitive 17): ResolveTranspose.apply has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), match/switch 2 (3 pts), boolean chains 2 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTranspose.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"50595153cd14230a7cff6fd77fed3468b0c5b58ed506d358bc01e0e944959aa1"}},{"ruleId":"D2","level":"warning","message":{"text":"OptimizeMetadataOnlyQuery.apply (cognitive 17): OptimizeMetadataOnlyQuery.apply has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 3 (7 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/OptimizeMetadataOnlyQuery.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0787cbb33d84fd83be5f6cc1a1ddc4e0fe91a2e15c38d5399fcb730034645e9"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinSelection.checkHintBuildSide (cognitive 17): JoinSelection.checkHintBuildSide has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (16 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dea9b87ba14bc23ac24aa0ee99ef944bdac786d299bb1349ee32f83a6c4f2a8"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtractJoinWithBuckets.unapply (cognitive 17): ExtractJoinWithBuckets.unapply has cognitive complexity 17 (threshold 15). Drivers by points: loops 4 (14 pts), boolean chains 1, if/else 1, match/switch 1 (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/bucketing/CoalesceBucketsInJoin.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"862816e86d8e5d22390737b8f542682fa7bc07a9f24f40493375c13d7a2808d4"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowCachedBatchSerializer.calculateMinMaxFloat (cognitive 17): ArrowCachedBatchSerializer.calculateMinMaxFloat has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (17 pts) (nesting depth added 9). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function. This shape REPEATS in the file: one other method here (ArrowCachedBatchSerializer.calculateMinMaxDouble) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":790}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e46b5ca5fdd9f811f8d5b08a1912e6b772b1dd6bfd3e0e60adebc4d3222e0fa"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowCachedBatchSerializer.calculateMinMaxDouble (cognitive 17): ArrowCachedBatchSerializer.calculateMinMaxDouble has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (17 pts) (nesting depth added 9). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function. This shape REPEATS in the file: one other method here (ArrowCachedBatchSerializer.calculateMinMaxFloat) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":818}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e2ece5e2fbcb579456e8403261668454ff9bd190972b813f02716b6a9ee18ce"}},{"ruleId":"D2","level":"warning","message":{"text":"ObjectColumnStats.gatherStats (cognitive 17): ObjectColumnStats.gatherStats has cognitive complexity 17 (threshold 15). Drivers by points: match/switch 4 (11 pts), if/else 6 (nesting depth added 7). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnStats.scala"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"e67e05024d14e4603992e3ecbca3e1425c91ef7f7ee759438d74d9280981dd63"}},{"ruleId":"D2","level":"warning","message":{"text":"CreateDataSourceTableAsSelectCommand.run (cognitive 17): CreateDataSourceTableAsSelectCommand.run has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b4a6da087072286df9d81d934935d001eb981736d4196084e4b876954e81fcb"}},{"ruleId":"D2","level":"warning","message":{"text":"DescribeFunctionCommand.describeSQLFunction (cognitive 17): DescribeFunctionCommand.describeSQLFunction has cognitive complexity 17 (threshold 15). Drivers by points: if/else 12 (15 pts), match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/functions.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"29ffc0644c1ea224dc6663e70ed64cf008ad55339256aae42be8be9014395dec"}},{"ruleId":"D2","level":"warning","message":{"text":"AggregatePushDownUtils.getSchemaForPushedAggregation (cognitive 17): AggregatePushDownUtils.getSchemaForPushedAggregation has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 3, match/switch 3 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/AggregatePushDownUtils.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"537c6bddc65bd843c161a2f41811681f315b75aa7b03803c7831efbe06af50f7"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSource.sourceSchema (cognitive 17): DataSource.sourceSchema has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (11 pts), boolean chains 5, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"274ec479a76f8271fc93ef257d01e8191da84e0c439158c4e593d7943f26eabc"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSourceV2Utils.loadV2Source (cognitive 17): DataSourceV2Utils.loadV2Source has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (13 pts), match/switch 3 (4 pts) (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Utils.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4c65f5fc3423226df3bf91b9ae2f575e148cf2e69d95a5cc2e69e6802c97b11"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnDomains.compare (cognitive 17): ColumnDomains.compare has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (12 pts), match/switch 2 (4 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"d697f51adda6b3d14f848be9ce5c55e854dd52d8eba0b398a431a0bf95197cdd"}},{"ruleId":"D2","level":"warning","message":{"text":"SortMergeFullOuterJoinScanner.advanceNext (cognitive 17): SortMergeFullOuterJoinScanner.advanceNext has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 6 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":1590}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e8c34bdda4481d4060dc3e3e40a249ebd2b9c65b37c090cb19454f30764002d"}},{"ruleId":"D2","level":"warning","message":{"text":"CollectLimitExec.doExecute (cognitive 17): CollectLimitExec.doExecute has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"25c54f7f67c62ed6481e08cba4acc4bdb98bd91826a9ce742f8eb50627d213f4"}},{"ruleId":"D2","level":"warning","message":{"text":"CoGroupedArrowPythonRunner.newWriter (cognitive 17): CoGroupedArrowPythonRunner.newWriter has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (15 pts), boolean chains 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/CoGroupedArrowPythonRunner.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"d35bb7bf61fe92aa8d24970001871553cdb1129e3b0755cebc41e0b47320a1c0"}},{"ruleId":"D2","level":"warning","message":{"text":"HDFSMetadataLog.verifyBatchIds (cognitive 17): HDFSMetadataLog.verifyBatchIds has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (16 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/HDFSMetadataLog.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"776ee8f6d33c7f4bfcceed5071f98e4511ed6ba739b17cad971b3c278a0085b1"}},{"ruleId":"D2","level":"warning","message":{"text":"SymmetricHashJoinStateManagerV4.getJoinedRowsAndRemoveMatched (cognitive 17): SymmetricHashJoinStateManagerV4.getJoinedRowsAndRemoveMatched has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 1, loops 1, match/switch 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2d292545b98df42715bba152e443f40eb69842d0f21d6f481e274daffc7f968"}},{"ruleId":"D2","level":"warning","message":{"text":"KeyWithTsToValuesStore.getValuesInRange (cognitive 17): KeyWithTsToValuesStore.getValuesInRange has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 4 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":755}}}],"partialFingerprints":{"codehealthFindingId/v1":"53add840112f099fdffadc6e752d09fa5e0c3b57b9a8bf65155d18a809deda08"}},{"ruleId":"D2","level":"warning","message":{"text":"SymmetricHashJoinStateManagerBase.evictAndReturnByValueCondition (cognitive 17): SymmetricHashJoinStateManagerBase.evictAndReturnByValueCondition has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 2, loops 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":1415}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7ca2db40ff4024843d23da506f28fbc54c4dcd66e3717011dc5fb77b2ad9a66"}},{"ruleId":"D2","level":"warning","message":{"text":"AutoSnapshotLoader.loadSnapshot (cognitive 17): AutoSnapshotLoader.loadSnapshot has cognitive complexity 17 (threshold 15). Drivers by points: error handling 3 (7 pts), if/else 5 (6 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/AutoSnapshotLoader.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee48e54b790846266edbf645da6b8bcb95ae0c79ac21d1b36560907cda3f87cd"}},{"ruleId":"D2","level":"warning","message":{"text":"RocksDB.loadWithoutCheckpointId (cognitive 17): RocksDB.loadWithoutCheckpointId has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 2, error handling 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":608}}}],"partialFingerprints":{"codehealthFindingId/v1":"caadce0bf130ac5a8c6e644ae80287325945024f259239e76fed786de6940226"}},{"ruleId":"D2","level":"warning","message":{"text":"SQLAppStatusListener.aggregateMetrics (cognitive 17): SQLAppStatusListener.aggregateMetrics has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (14 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f9e22f190d41d761a0b1051e74087f50f32188b4c1b0d7e5fa24f4dea6a1e89"}},{"ruleId":"D2","level":"warning","message":{"text":"WindowPartitionEvaluator.eval (cognitive 17): WindowPartitionEvaluator.eval has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8, boolean chains 5, loops 3 (4 pts) (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"8784d5c3ab7f5a48963ecdb4e3dafb4c20dca49a3bdb884bf5dd5220e710e4e6"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkExecuteStatementOperation.execute (cognitive 17): SparkExecuteStatementOperation.execute has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (12 pts), match/switch 1 (3 pts), boolean chains 1, error handling 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkExecuteStatementOperation.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f7aa5a307f230baf0fd03aac8132a44a509bbf91c317da59cf0431e6e53fc1e"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveScriptTransformationExec.createOutputIteratorWithSerde (cognitive 17): HiveScriptTransformationExec.createOutputIteratorWithSerde has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (12 pts), error handling 2 (4 pts), loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveScriptTransformationExec.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef62098dd1b00d181538d89304e377a8ace3d1b277d1b7852626e2f803136e99"}},{"ruleId":"D2","level":"warning","message":{"text":"CheckpointWriteHandler.run (cognitive 17): CheckpointWriteHandler.run has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (12 pts), boolean chains 2, error handling 1 (2 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbe0f444f93615967484eca1913777f5950278a3a2aa611f60b5f79cee947f5c"}},{"ruleId":"D2","level":"warning","message":{"text":"BytesToBytesMap.safeLookup (cognitive 17): BytesToBytesMap.safeLookup has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (16 pts), loops 1 (nesting depth added 10). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":743}}}],"partialFingerprints":{"codehealthFindingId/v1":"faffacdf3c83480a7e4bbcfbd3d915cb5555f198bc4cd97987a89e56c4631484"}},{"ruleId":"D2","level":"warning","message":{"text":"InstanceList.countingRemoveAllByIndexValues (cognitive 17): InstanceList.countingRemoveAllByIndexValues has cognitive complexity 17 (threshold 15). Drivers by points: loops 3 (7 pts), if/else 4 (6 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/InMemoryStore.java"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c1c541e2d9dd2883d1c373d864e4db4c674c37760f10367e340f694acad519b"}},{"ruleId":"D2","level":"warning","message":{"text":"GcmEncryptedMessage.transferTo (cognitive 17): GcmEncryptedMessage.transferTo has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (14 pts), error handling 1 (2 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/GcmTransportCipher.java"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"aaba913877659fdb00d990e6a370136d943dca572aee1817f0f2da1e020020cd"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalShuffleBlockResolver.applicationRemoved (cognitive 17): ExternalShuffleBlockResolver.applicationRemoved has cognitive complexity 17 (threshold 15). Drivers by points: if/else 4 (11 pts), error handling 1 (4 pts), boolean chains 1, loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4f84e3f9d3f01ddc685d7b174f75e4a8a1de254ff8c401bf3d13ed995f6427b"}},{"ruleId":"D2","level":"warning","message":{"text":"RemoteBlockPushResolver.registerExecutor (cognitive 17): RemoteBlockPushResolver.registerExecutor has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (14 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":876}}}],"partialFingerprints":{"codehealthFindingId/v1":"8993ddc9683e989b09d8c68ef0b98a71bfaed744c06b8c4542ff89eed69e444b"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseMatchLengthFrom (cognitive 17): CollationAwareUTF8String.lowercaseMatchLengthFrom has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 3, loops 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (CollationAwareUTF8String.lowercaseMatchLengthUntil) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fe299414706a699d64863c745de64b9e40b4cc11ed14612992d72a33b55df85"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseMatchLengthUntil (cognitive 17): CollationAwareUTF8String.lowercaseMatchLengthUntil has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 3, loops 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (CollationAwareUTF8String.lowercaseMatchLengthFrom) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"191ff3f1958083f9027c0f8b59d880998a76dee00b6feafd768278f87696da92"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseTrimLeft (cognitive 17): CollationAwareUTF8String.lowercaseTrimLeft has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (13 pts), loops 2, boolean chains 1, ternaries 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1289}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d2ca4963b6f90dbb1ca21d4aeda7283c57b80a725d7b2c27ca92fed4ea44c38"}},{"ruleId":"D2","level":"warning","message":{"text":"UTF8String.levenshteinDistance (cognitive 17): UTF8String.levenshteinDistance has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (8 pts), loops 3 (4 pts), ternaries 1 (4 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":2165}}}],"partialFingerprints":{"codehealthFindingId/v1":"37501bbc3e3da3a4507f22798e3c3d555d033983aa350c9e9a75df8786815f5e"}},{"ruleId":"D2","level":"warning","message":{"text":"JavaUtils.deleteRecursivelyUsingJavaIO (cognitive 17): JavaUtils.deleteRecursivelyUsingJavaIO has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (7 pts), boolean chains 5, error handling 1 (3 pts), loops 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ae7ee2b0e5589a6f945fe9f4efa765cfc8ca6112e54d88d9865a5d2c94f5117"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantBuilder.appendWithArrayAppendImpl (cognitive 17): VariantBuilder.appendWithArrayAppendImpl has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (12 pts), loops 3, boolean chains 2 (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"14af83be8ef6b36f44dd13a7bf894a41b57e8462710b72a2767598c9aebed369"}},{"ruleId":"D2","level":"warning","message":{"text":"ExpressionInfo.\u003Cinit\u003E (cognitive 17): ExpressionInfo.\u003Cinit\u003E has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (12 pts), boolean chains 5 (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionInfo.java"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"04dd10a7d9f393ccde1f3d558e3f4544b0358d3a260e1b10237e6f6adb680b5c"}},{"ruleId":"D2","level":"warning","message":{"text":"WkbWriter.calculateSize (cognitive 17): WkbWriter.calculateSize has cognitive complexity 17 (threshold 15). Drivers by points: loops 5 (10 pts), if/else 7 (nesting depth added 5). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbWriter.java"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dffcd87daf733c065297edfb06f8875e1baeb68e3a4e89181d44744e7e6b2ec"}},{"ruleId":"D2","level":"warning","message":{"text":"cloudpickle._find_imported_submodules (cognitive 17): cloudpickle._find_imported_submodules has cognitive complexity 17 (threshold 15). Drivers by points: if/else 3 (11 pts), loops 2 (4 pts), boolean chains 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fa89cfed560fa558d8d09a703508ab7f8272b69590cc93fae71aba3954b1a12"}},{"ruleId":"D2","level":"warning","message":{"text":"Traceback.from_string (cognitive 17): Traceback.from_string has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (11 pts), loops 3 (5 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/tblib.py"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"567aa44c0f3da978033ccc365c6d361e7829388c079fd0418135d94e981f2152"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowBatchedUDFLegacyPandasHandler.run (cognitive 17): ArrowBatchedUDFLegacyPandasHandler.run has cognitive complexity 17 (threshold 15). Drivers by points: ternaries 3 (9 pts), if/else 2 (5 pts), loops 2 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":782}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dab07ec315ad611a83f3d840267e39698e3e65688f209bb72e65020362ef20b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.__init__ (cognitive 17): SparseVector.__init__ has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SparseVector.__init__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"59e4f13f4a63967fe928812c1d4413eb79137542fc9d7e9cf51453b3b322314d"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.__init__ (cognitive 17): SparseVector.__init__ has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SparseVector.__init__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":556}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1c368d8a0176f9732b2ee1fb96ac87ba38c420d2d05736ff1804bb8e96b8a6e"}},{"ruleId":"D2","level":"warning","message":{"text":"utils.combine_frames (cognitive 17): utils.combine_frames has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 2, loops 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/utils.py"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"a35326e660ab649a3e027bbe75fd6775ad4c67d98f0b4d31bda23496b498b506"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame.explain (cognitive 17): DataFrame.explain has cognitive complexity 17 (threshold 15). Drivers by points: boolean chains 8, if/else 5 (7 pts), ternaries 1 (2 pts) (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"eba2220e93e63e482977217fe8d918c9daa6d2425c1e11a669ee07a4a973aa07"}},{"ruleId":"D2","level":"warning","message":{"text":"WriteOperation.command (cognitive 17): WriteOperation.command has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (16 pts), loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":2200}}}],"partialFingerprints":{"codehealthFindingId/v1":"d01be8470bc32bcb44c6ab53083eec835d141105ed20298f28e9ffdcac9344c6"}},{"ruleId":"D2","level":"warning","message":{"text":"WriteOperationV2.command (cognitive 17): WriteOperationV2.command has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (15 pts), loops 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":2304}}}],"partialFingerprints":{"codehealthFindingId/v1":"098c21a8400d3f4604559a7c1b50059908e27f16459a760e7a0cd88528e856d5"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowTableToRowsConversion._create_converter (cognitive 17): ArrowTableToRowsConversion._create_converter has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (16 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (ArrowTableToRowsConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1290}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb9e42e8be6bdcc29a4bcb2d10cadf3ce178d76296acf28b8e73af53b1282c7b"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowTableToRowsConversion._create_converter (cognitive 17): ArrowTableToRowsConversion._create_converter has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (16 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (ArrowTableToRowsConversion._create_converter) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1296}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac8832fb74addf610d65cfad9f16b0ab86886542549e8eedb8bd82ce4de5b05c"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowToPandasConversion._convert_array_numpy (cognitive 17): ArrowToPandasConversion._convert_array_numpy has cognitive complexity 17 (threshold 15). Drivers by points: if/else 12 (16 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":2075}}}],"partialFingerprints":{"codehealthFindingId/v1":"aac9d313893b45cbdcbf1742667e2b145fceb07f1c1de6d07035f36ec9cf2225"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowStreamSerializer.dump_stream (cognitive 17): ArrowStreamSerializer.dump_stream has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (15 pts), loops 1, ternaries 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/serializers.py"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"12abfc186cd34ea7c9a79b527d6f03eda19a0669628ada5c9d83e4cd1da355c6"}},{"ruleId":"D2","level":"warning","message":{"text":"data_source_pushdown_filters._main (cognitive 17): data_source_pushdown_filters._main has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (13 pts), loops 2, boolean chains 1, ternaries 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/data_source_pushdown_filters.py"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"9032ce9371277ab53c2b3c6f2debddc1398c911f3ca0ab535135257146df1563"}},{"ruleId":"D2","level":"warning","message":{"text":"utils.worker_run (cognitive 17): utils.worker_run has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (10 pts), error handling 2 (4 pts), ternaries 1 (3 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/utils.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"921102c675aa2a18d36bf1e4436a41474fd1bf023bea20cc538f479a7af8800f"}},{"ruleId":"D2","level":"warning","message":{"text":"mlutils.check_params (cognitive 17): mlutils.check_params has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (11 pts), ternaries 1 (4 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/mlutils.py"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8bf65134e554d3b3ff575d07945b55cb4596d347a3ca0d7b25fa26f88212899"}},{"ruleId":"D2","level":"warning","message":{"text":"pandasutils._assert_pandas_equal (cognitive 17): pandasutils._assert_pandas_equal has cognitive complexity 17 (threshold 15). Drivers by points: error handling 3 (6 pts), ternaries 3 (6 pts), boolean chains 3, if/else 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ae6d41f8ce5e9d98f3faef5d22bfe9b97fc32cb268626b0e6e9d2678e08cb07"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkStringUtils.truncatedString (cognitive 16): SparkStringUtils.truncatedString has cognitive complexity 16 (threshold 15). Drivers by points: if/else 11 (16 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bb1bba2589080f4988736e337b0e9b2d5d1dbad97b930699daf0fdbf5175519"}},{"ruleId":"D2","level":"warning","message":{"text":"PipelinedWriterTask.awaitExit (cognitive 16): PipelinedWriterTask.awaitExit has cognitive complexity 16 (threshold 15). Drivers by points: error handling 3 (8 pts), if/else 3 (4 pts), match/switch 1 (3 pts), loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"14ad11941a8bb74657b085caea59a77d677666664dfd4becd0ef633021f1a93e"}},{"ruleId":"D2","level":"warning","message":{"text":"Master.scheduleExecutorsOnWorkers (cognitive 16): Master.scheduleExecutorsOnWorkers has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (9 pts), boolean chains 4, loops 2 (3 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e3163a497567c8da27cb846eda80077bc0f13fb43000941bb649504c67d3d60"}},{"ruleId":"D2","level":"warning","message":{"text":"RestSubmissionClient.readResponse (cognitive 16): RestSubmissionClient.readResponse has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (9 pts), error handling 4, match/switch 1 (2 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"26a3f19910efd9a3d79aad2475f624a01e5cc621f2d20528355094687ccca919"}},{"ruleId":"D2","level":"warning","message":{"text":"Worker.syncExecutorStateWithMaster (cognitive 16): Worker.syncExecutorStateWithMaster has cognitive complexity 16 (threshold 15). Drivers by points: if/else 3 (8 pts), error handling 1 (5 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":811}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f82d50e735c26b0859b050a38242fd201693887b58ea6c71556cabd956091d4"}},{"ruleId":"D2","level":"warning","message":{"text":"DAGScheduler.checkPipelinedStageCreation (cognitive 16): DAGScheduler.checkPipelinedStageCreation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), match/switch 2 (5 pts), loops 2, boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":1593}}}],"partialFingerprints":{"codehealthFindingId/v1":"db049dbd91ed4c711354225f525055e0d2eccdd577f8ce0398be798754a5c896"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.getAllowedLocalityLevel (cognitive 16): TaskSetManager.getAllowedLocalityLevel has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 2 (3 pts), loops 2, boolean chains 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":641}}}],"partialFingerprints":{"codehealthFindingId/v1":"58085ea5a98b0908f3c982fdd4099328c2610c2287c2016ee7e26e670d4afc1e"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskSetManager.checkAndSubmitSpeculatableTasks (cognitive 16): TaskSetManager.checkAndSubmitSpeculatableTasks has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (9 pts), boolean chains 6, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1310}}}],"partialFingerprints":{"codehealthFindingId/v1":"12ca7ffd0e7cc4bb3190f48a35190876ec019f326c00d64270dbf7945db986e9"}},{"ruleId":"D2","level":"warning","message":{"text":"AppStatusListener.onJobEnd (cognitive 16): AppStatusListener.onJobEnd has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 4 (7 pts), match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":519}}}],"partialFingerprints":{"codehealthFindingId/v1":"660ea6a26be8c4be91732ffaeaf9c570fa23e8c3a3f33b703104a461b7da623b"}},{"ruleId":"D2","level":"warning","message":{"text":"BlockManager.fetchRemoteManagedBuffer (cognitive 16): BlockManager.fetchRemoteManagedBuffer has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (12 pts), error handling 1 (2 pts), boolean chains 1, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1395}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e32cef7c00d9950fbe80d9df30d50c44df9896fc8d28341d47d6bdf15a1a56f"}},{"ruleId":"D2","level":"warning","message":{"text":"ListenerBus.postToAll (cognitive 16): ListenerBus.postToAll has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (10 pts), error handling 2 (4 pts), boolean chains 1, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/ListenerBus.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e4b305bd0ebeda2aed60add4c68242f371ac22670cff056c3fbd622eb285bc8"}},{"ruleId":"D2","level":"warning","message":{"text":"MetricUtils.stringValue (cognitive 16): MetricUtils.stringValue has cognitive complexity 16 (threshold 15). Drivers by points: if/else 13 (16 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/MetricUtils.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"28e4e494ff915afddd5ee8ca9bed9d3f11ada1174f7a2104e03f57071a2fa635"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.fetchFile (cognitive 16): Utils.fetchFile has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 2 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"2150cdb17e98f94154f2980e4821117422a21acc8fa25b77ae1cdafe1492a454"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.findLocalInetAddress (cognitive 16): Utils.findLocalInetAddress has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":902}}}],"partialFingerprints":{"codehealthFindingId/v1":"10123db303911b9a904047eb95a71f0226379f929049c1331b54da213db869b5"}},{"ruleId":"D2","level":"warning","message":{"text":"EdgePartition.innerJoin (cognitive 16): EdgePartition.innerJoin has cognitive complexity 16 (threshold 15). Drivers by points: loops 3 (6 pts), boolean chains 5, if/else 2 (5 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d05855ae2b2c4cc9dc6d7584eb05d637020aad63a9899699229aae0f7ce5331"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseMatrix.fromCOO (cognitive 16): SparseMatrix.fromCOO has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 2 (5 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":918}}}],"partialFingerprints":{"codehealthFindingId/v1":"6705f12551f21dc4175a22439000388f48b3d2032b3122a5320115b534aee47b"}},{"ruleId":"D2","level":"warning","message":{"text":"Vectors.sqdist (cognitive 16): Vectors.sqdist has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (6 pts), boolean chains 5, loops 2 (4 pts), match/switch 1 (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"c28d1bac74abb8c02994a09f8054679d9b78fd121ae89739626b90a50acaec00"}},{"ruleId":"D2","level":"warning","message":{"text":"LinearSVC.train (cognitive 16): LinearSVC.train has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12 (13 pts), match/switch 2, boolean chains 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"02c3c5931eea244ffd0e43f9a3d8fedb7620fa6dea0ae9376360cbf6f8eabb97"}},{"ruleId":"D2","level":"warning","message":{"text":"GaussianMixture.trainImpl (cognitive 16): GaussianMixture.trainImpl has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala"},"region":{"startLine":499}}}],"partialFingerprints":{"codehealthFindingId/v1":"50cf8843dbdf6de43021cf9895b059f5e049eb0412473f73524f0f6e4f9730cf"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomForest.mixedBinSeqOp (cognitive 16): RandomForest.mixedBinSeqOp has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 2 (4 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3fea96ef62a533cafd3288b600bb80867cc7f5e2b14e41ff1b958ac0d6b5ee4"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomForest.findSplitsForContinuousFeature (cognitive 16): RandomForest.findSplitsForContinuousFeature has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 1 (3 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":1293}}}],"partialFingerprints":{"codehealthFindingId/v1":"54dbbd2af54c1c36bc4864937e782432d73ebcec21fcdfa3a8f8c6dcd4d9cd7d"}},{"ruleId":"D2","level":"warning","message":{"text":"GaussianMixture.run (cognitive 16): GaussianMixture.run has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), loops 2 (4 pts), boolean chains 1, match/switch 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"410881644e8c5834b3ab0f6cbc84db3f2fb8137efcc15404119958a25f0199d8"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseMatrix.fromCOO (cognitive 16): SparseMatrix.fromCOO has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 2 (5 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala"},"region":{"startLine":779}}}],"partialFingerprints":{"codehealthFindingId/v1":"44d298092f8bab9251f334fc64d4de548e88b393f926b3cbf2a90d07832c96be"}},{"ruleId":"D2","level":"warning","message":{"text":"Vectors.sqdist (cognitive 16): Vectors.sqdist has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (6 pts), boolean chains 5, loops 2 (4 pts), match/switch 1 (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala"},"region":{"startLine":534}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e29e58cc223b6babc9cd583fe53958a3068025606c119f0546bc2f0f9fb91ca"}},{"ruleId":"D2","level":"warning","message":{"text":"KubernetesClusterManager.createSchedulerBackend (cognitive 16): KubernetesClusterManager.createSchedulerBackend has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10 (14 pts), match/switch 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterManager.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c0a636d115e8c1b65c225f7a1c9098c2e050afa9d7417e629534bee8dd5bfb2"}},{"ruleId":"D2","level":"warning","message":{"text":"Client.createConfArchive (cognitive 16): Client.createConfArchive has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (11 pts), loops 2 (3 pts), boolean chains 2 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":861}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d04fea33d42d60b2b618e15cc09d1eab9c28f720314bdc986b26a0c05297c17"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowUtils.fromArrowField (cognitive 16): ArrowUtils.fromArrowField has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), boolean chains 3, match/switch 2 (3 pts) (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8a664ab69bd4d14496c6a9d6736a4e67c8a011e5af24832421072e2e02f6bfd"}},{"ruleId":"D2","level":"warning","message":{"text":"LookupFunctions.apply (cognitive 16): LookupFunctions.apply has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (10 pts), match/switch 2 (5 pts), boolean chains 1 (nesting depth added 7). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2344}}}],"partialFingerprints":{"codehealthFindingId/v1":"d10f13f13b1925b0ac0d12fd1e5cfcd5c442b53ae80c87972ac796626a6bc4ad"}},{"ruleId":"D2","level":"warning","message":{"text":"AsOfJoinMatchConditionResolution.coerceNearestKeys (cognitive 16): AsOfJoinMatchConditionResolution.coerceNearestKeys has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (11 pts), boolean chains 3, match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AsOfJoinMatchConditionResolution.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e33c2c4a6ac13ca31f3227a92e93fc3989f93e3361b29532850e988fd9e106a"}},{"ruleId":"D2","level":"warning","message":{"text":"ColumnResolutionHelper.resolveExprsAndAddMissingAttrs (cognitive 16): ColumnResolutionHelper.resolveExprsAndAddMissingAttrs has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 2 (5 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ColumnResolutionHelper.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"d87659f97ff82ac0685296266cb3383c703b71c9b83486cd348d3cd1cb184455"}},{"ruleId":"D2","level":"warning","message":{"text":"FunctionResolution.resolveFunctionCandidate (cognitive 16): FunctionResolution.resolveFunctionCandidate has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), error handling 3 (6 pts), match/switch 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"27f57b333bdae905667e67caed81797102a1935a5f16edd919e2d7e33346ea97"}},{"ruleId":"D2","level":"warning","message":{"text":"InMemoryCatalog.dropTable (cognitive 16): InMemoryCatalog.dropTable has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), error handling 2 (6 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"e55392952c93b7f64092b7a4aedd00d61eb36a622ecbda43cb90addeee0830f4"}},{"ruleId":"D2","level":"warning","message":{"text":"SelectedField.selectField (cognitive 16): SelectedField.selectField has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 6 (11 pts), if/else 4, boolean chains 1 (nesting depth added 5). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SelectedField.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"f17f4996999d50415f048ee9ff87f1aabffc4e7e1f3efba80d80d530cc7f262b"}},{"ruleId":"D2","level":"warning","message":{"text":"ApproxCountDistinctForIntervals.findHllppIndex (cognitive 16): ApproxCountDistinctForIntervals.findHllppIndex has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (12 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxCountDistinctForIntervals.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"455619d0248ca95d215087c936740e4b8bad9d188f691b23d9e3361bf8acd25f"}},{"ruleId":"D2","level":"warning","message":{"text":"ClassLoaderFileManager.resolveReferencedClasses (cognitive 16): ClassLoaderFileManager.resolveReferencedClasses has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (11 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1691}}}],"partialFingerprints":{"codehealthFindingId/v1":"73130b34815134c400f37215435708ab27405e2cc7c17a043c6249c9b3d99c3d"}},{"ruleId":"D2","level":"warning","message":{"text":"GenerateUnsafeRowJoiner.create (cognitive 16): GenerateUnsafeRowJoiner.create has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12 (15 pts), boolean chains 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateUnsafeRowJoiner.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"402ec76368d89105dfae4ce8c208ec075ecc44337c01707c4f684948008b978f"}},{"ruleId":"D2","level":"warning","message":{"text":"UpdateFieldsExpression.eval (cognitive 16): UpdateFieldsExpression.eval has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala"},"region":{"startLine":818}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6a46f576c473bbfed111d2d1e372daf7141215fdae88282b21fdee071856e27"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonTupleEvaluator.parseRow (cognitive 16): JsonTupleEvaluator.parseRow has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (10 pts), loops 2 (6 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":430}}}],"partialFingerprints":{"codehealthFindingId/v1":"7104a368912766d74bb0184e294500ed612a37770b979afc921fee43f94ac2de"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonArray.checkInputDataTypes (cognitive 16): JsonArray.checkInputDataTypes has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":1479}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b98ac10531c79edf7496a0b3aefdb059f4506474fa5e5ac390144db09a7a4b4"}},{"ruleId":"D2","level":"warning","message":{"text":"JsonArray.sqlString (cognitive 16): JsonArray.sqlString has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10, boolean chains 4, match/switch 2. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":1676}}}],"partialFingerprints":{"codehealthFindingId/v1":"847a020c2863e2419eac9dc42ae9a8b041f601a58eef8232163bde8e478e02cb"}},{"ruleId":"D2","level":"warning","message":{"text":"AtLeastNNonNulls.eval (cognitive 16): AtLeastNNonNulls.eval has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (11 pts), match/switch 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/nullExpressions.scala"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"28d00e923f08bb1a2b5956c25bacceb6330b360571ecc8db28b73909779da2c5"}},{"ruleId":"D2","level":"warning","message":{"text":"ToCharacterBuilder.build (cognitive 16): ToCharacterBuilder.build has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (10 pts), match/switch 2 (5 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2cd7cfb6ee5b4041fa4440f5825cb28db86c3beda4fa0550297a13b27f4c650"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaOfVariant.schemaOf (cognitive 16): SchemaOfVariant.schemaOf has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 3 (6 pts), boolean chains 1, match/switch 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":2249}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c96f6f9708670b7b3780309f3c5bee29d616917f9512f13c2cbe976fbb3017d"}},{"ruleId":"D2","level":"warning","message":{"text":"FoldablePropagation.propagateFoldables (cognitive 16): FoldablePropagation.propagateFoldables has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 3 (6 pts), boolean chains 1 (nesting depth added 6). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1280}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c619eb295d668c94931d0bac5d43033260133fc2774c848418a2381e9698dfc"}},{"ruleId":"D2","level":"warning","message":{"text":"AstBuilder.visitAlterTableAlterColumn (cognitive 16): AstBuilder.visitAlterTableAlterColumn has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12, boolean chains 2, match/switch 1 (2 pts) (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6974}}}],"partialFingerprints":{"codehealthFindingId/v1":"90badc41721c3fcdb110dba9307ec3a33c22b70cc41a9bd32f9290ee7df5a2aa"}},{"ruleId":"D2","level":"warning","message":{"text":"OperationHelper.collectProjectsAndFilters (cognitive 16): OperationHelper.collectProjectsAndFilters has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (11 pts), boolean chains 4, match/switch 1 (nesting depth added 4). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6f7f81713ddc0552151567c707f36c66c1784bb2592608b04b60a1df84cc780"}},{"ruleId":"D2","level":"warning","message":{"text":"FilterEstimation.evaluateInSet (cognitive 16): FilterEstimation.evaluateInSet has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (13 pts), boolean chains 2, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"2059d07363148787e57ffb065d55a88131f90536db2ce7aa3d1bd106f373c450"}},{"ruleId":"D2","level":"warning","message":{"text":"JoinEstimation.computeCardinalityAndStats (cognitive 16): JoinEstimation.computeCardinalityAndStats has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), match/switch 2 (4 pts), boolean chains 3, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"f83b8eb72f5efd5d9055c7384bee29390de0802bb8857867f067508a4db9d112"}},{"ruleId":"D2","level":"warning","message":{"text":"TreeNode.generateTreeString (cognitive 16): TreeNode.generateTreeString has cognitive complexity 16 (threshold 15). Drivers by points: if/else 13 (16 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1194}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4674ab9476712f62b4dfa71da43cfa15a49902f8ad36ffd0ad8e1e372b350b5"}},{"ruleId":"D2","level":"warning","message":{"text":"NumberConverter.convert (cognitive 16): NumberConverter.convert has cognitive complexity 16 (threshold 15). Drivers by points: if/else 11 (12 pts), boolean chains 4 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"39d3155198ff6ffe6e38425cacc4fc1821326f7d719537822747d75ee0a63902"}},{"ruleId":"D2","level":"warning","message":{"text":"GrpcExceptionConverter.errorsToThrowable (cognitive 16): GrpcExceptionConverter.errorsToThrowable has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12 (13 pts), boolean chains 2, match/switch 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/GrpcExceptionConverter.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b29d6c29e1f6aa433ec952870c828815281bfeef4d49a5f3b72aa5206608bc8"}},{"ruleId":"D2","level":"warning","message":{"text":"ResponseValidator.verifyResponse (cognitive 16): ResponseValidator.verifyResponse has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (9 pts), boolean chains 3, match/switch 1 (3 pts), error handling 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ResponseValidator.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"357537a54be89eb2ef4a9e8405f0df11277d441ea28e6ff47e919cbeba77b893"}},{"ruleId":"D2","level":"warning","message":{"text":"LiteralValueProtoConverter.getProtoDataTypeDefault (cognitive 16): LiteralValueProtoConverter.getProtoDataTypeDefault has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (14 pts), boolean chains 1, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/LiteralValueProtoConverter.scala"},"region":{"startLine":544}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cce687a99d16ab49f8440d04a5f87caecfb9d0b3f6b76192a589a8e7fa10804"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformJvmOrigin (cognitive 16): SparkConnectPlanner.transformJvmOrigin has cognitive complexity 16 (threshold 15). Drivers by points: if/else 16. To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":2047}}}],"partialFingerprints":{"codehealthFindingId/v1":"69afd7052f6b94ecc0b43e4c2b233430ceb583b451e1b2c961ce9e8b81a30ed5"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformWindowExpression (cognitive 16): SparkConnectPlanner.transformWindowExpression has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (10 pts), match/switch 3 (6 pts) (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":2543}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0409a045ded788388c1292fc47a3547f1e62d475ba4387056ecebf7d226a5f3"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectPlanner.transformSetOperation (cognitive 16): SparkConnectPlanner.transformSetOperation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 2, match/switch 1 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":2614}}}],"partialFingerprints":{"codehealthFindingId/v1":"e90ec57ec3379aa124145a678b3289429b5d1879d2750558d93f157134bce8bb"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectAddArtifactsHandler.onNext (cognitive 16): SparkConnectAddArtifactsHandler.onNext has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (10 pts), match/switch 2 (4 pts), boolean chains 2 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectAddArtifactsHandler.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"024d89824a8bc57e6e85de7c7a5a65b675e4d726e170336743b2f32242533c22"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.showString (cognitive 16): Dataset.showString has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (10 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":368}}}],"partialFingerprints":{"codehealthFindingId/v1":"818e4962d3b0de6000f1b86ddeaa1a7e050c1e7a07ca3529d993eb7ada04da37"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSession.parseParameterizedPlan (cognitive 16): SparkSession.parseParameterizedPlan has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (12 pts), boolean chains 2, match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":658}}}],"partialFingerprints":{"codehealthFindingId/v1":"c12eaa9c32e71665c6404f7ada40b65701bddcc02cada0c8796400f39e8551c4"}},{"ruleId":"D2","level":"warning","message":{"text":"CombineAdjacentAggregation.detachAggregate (cognitive 16): CombineAdjacentAggregation.detachAggregate has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 4 (8 pts), if/else 6 (7 pts), boolean chains 1 (nesting depth added 5). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/CombineAdjacentAggregation.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6e6ef079ccd27f9ae71820b76844e867f75ee1d0aff4089da44016e73c79f6e"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowCachedBatchSerializer.drainAndClosePrefetch (cognitive 16): ArrowCachedBatchSerializer.drainAndClosePrefetch has cognitive complexity 16 (threshold 15). Drivers by points: error handling 4 (9 pts), if/else 4 (5 pts), loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"5918ca95aeb25bcb57fdc7a248a01e36ae1578df82348c2f2781f36bf5fdfbd7"}},{"ruleId":"D2","level":"warning","message":{"text":"CachedRDDBuilder.buildBuffers (cognitive 16): CachedRDDBuilder.buildBuffers has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7, boolean chains 4, match/switch 2 (4 pts), error handling 1 (nesting depth added 2). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"7dba16ec7a6aa7a336cd1c2febea7b1bb249a5585712ec14c32461ea06ec747c"}},{"ruleId":"D2","level":"warning","message":{"text":"DataSource.resolveRelation (cognitive 16): DataSource.resolveRelation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), match/switch 2, boolean chains 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":382}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7f442a2d0cb229f33dd4c5dac60a40865204050486daf18320223bedeff4e9f"}},{"ruleId":"D2","level":"warning","message":{"text":"VariantInRelation.rewriteType (cognitive 16): VariantInRelation.rewriteType has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (9 pts), match/switch 3 (7 pts) (nesting depth added 8). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PushVariantIntoScan.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fa624cb41fb35609452115450e2e29afed0de601a949f231e6d02c0708f32a8"}},{"ruleId":"D2","level":"warning","message":{"text":"SupportsArchiveFormat.readLocalizedEntries (cognitive 16): SupportsArchiveFormat.readLocalizedEntries has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (7 pts), error handling 3 (5 pts), match/switch 2, boolean chains 1, loops 1 (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"c49e10dd4a0a11dd5a0057268a9077da4ab67af0256d7fcfe76087dcdbda9403"}},{"ruleId":"D2","level":"warning","message":{"text":"InferVariantShreddingSchema.mergeSchema (cognitive 16): InferVariantShreddingSchema.mergeSchema has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (6 pts), loops 3 (6 pts), boolean chains 3, match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/InferVariantShreddingSchema.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"25947715f338b588285a0f843085fda7bac50e7a127935454ce3e66ecb0aacd2"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkToParquetSchemaConverter.convertFieldDefault (cognitive 16): SparkToParquetSchemaConverter.convertFieldDefault has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), match/switch 2 (4 pts), boolean chains 2 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":673}}}],"partialFingerprints":{"codehealthFindingId/v1":"316a57c0832ac7d26bb30bf8209924dd05737512a41ec217b27c37a5dcc8ec8f"}},{"ruleId":"D2","level":"warning","message":{"text":"EnsureRequirements.resolveChild (cognitive 16): EnsureRequirements.resolveChild has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), match/switch 3 (8 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d61775b2b8e2fe212b263381bff55b59abf9524217c705c77348d82a6ff0b1a"}},{"ruleId":"D2","level":"warning","message":{"text":"PythonArrowOutput.newReaderIterator (cognitive 16): PythonArrowOutput.newReaderIterator has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10 (13 pts), match/switch 1 (2 pts), boolean chains 1 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonArrowOutput.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bfede7ebca55b80efebc739d08196580e70e23e68a987fee540051e3aacd4c5"}},{"ruleId":"D2","level":"warning","message":{"text":"UserDefinedPythonTableFunctionAnalyzeRunner.receiveFromPython (cognitive 16): UserDefinedPythonTableFunctionAnalyzeRunner.receiveFromPython has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (9 pts), match/switch 2 (4 pts), loops 3 (nesting depth added 4). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef896317f3ddd099947a33b13dd44e1462bf1afa4b1518e3656dd08eb10b8156"}},{"ruleId":"D2","level":"warning","message":{"text":"FlatMapGroupsInPandasWithStateExec.createInputProcessor (cognitive 16): FlatMapGroupsInPandasWithStateExec.createInputProcessor has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (11 pts), boolean chains 3, match/switch 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/FlatMapGroupsInPandasWithStateExec.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dc5a57a93a6e10e0c85ed67f20a8d1ae250d57fc0095a9f11b660d16d89af40"}},{"ruleId":"D2","level":"warning","message":{"text":"StatFunctions.summary (cognitive 16): StatFunctions.summary has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 2, match/switch 1 (2 pts), error handling 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab0af70a2097149fd8123811b468a3a515c0ccab9033f550f1528e0593d07a5d"}},{"ruleId":"D2","level":"warning","message":{"text":"SqlScriptingInterpreter.transformBodyIntoExec (cognitive 16): SqlScriptingInterpreter.transformBodyIntoExec has cognitive complexity 16 (threshold 15). Drivers by points: if/else 13 (15 pts), match/switch 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreter.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"62995ccebbb474407bdb622855801753bf5a3af136459a558afd28a9dcacf88a"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkSQLCLIDriver.processLine (cognitive 16): SparkSQLCLIDriver.processLine has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (14 pts), boolean chains 1, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala"},"region":{"startLine":586}}}],"partialFingerprints":{"codehealthFindingId/v1":"20522f73a9361ba73370e1cc114d4440a19c024fe431e62625856ebcabf67b2d"}},{"ruleId":"D2","level":"warning","message":{"text":"HiveMetastoreCatalog.convertToLogicalRelation (cognitive 16): HiveMetastoreCatalog.convertToLogicalRelation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12 (16 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e40133222c92b37cda88ec3d12c87c511c0d529eeffb1ab9882f4ba7383cb17"}},{"ruleId":"D2","level":"warning","message":{"text":"FlowResolver.attemptResolveFlow (cognitive 16): FlowResolver.attemptResolveFlow has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 5 (9 pts), if/else 6 (7 pts) (nesting depth added 5). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/CoreDataflowNodeProcessor.scala"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ede94b550b077bafaba8960059789c7f7e4018fe2bc90a1a3a10f3752a63f75"}},{"ruleId":"D2","level":"warning","message":{"text":"TaskMemoryManager.spillConsumersForPageAllocation (cognitive 16): TaskMemoryManager.spillConsumersForPageAllocation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (9 pts), ternaries 1 (3 pts), boolean chains 2, loops 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1e78bdc38ce0cbbbdc03da56ad4eee3fea05efebcae24bf6f73a09a6b44b760"}},{"ruleId":"D2","level":"warning","message":{"text":"BytesToBytesMap.safeLookupWithKeyOperations (cognitive 16): BytesToBytesMap.safeLookupWithKeyOperations has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (14 pts), boolean chains 1, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":785}}}],"partialFingerprints":{"codehealthFindingId/v1":"4800982bb60b83134401edc4505cef28e797927a519abe5c10dd650050293263"}},{"ruleId":"D2","level":"warning","message":{"text":"TransportClientFactory.createClient (cognitive 16): TransportClientFactory.createClient has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (12 pts), boolean chains 2, error handling 1, ternaries 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportClientFactory.java"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"f42336f244aa913e34be82a9428e81b7ff3c2fb35e89ea8460a2dfc24748dc4d"}},{"ruleId":"D2","level":"warning","message":{"text":"TransportClientFactory.createClient (cognitive 16): TransportClientFactory.createClient has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10 (13 pts), error handling 2, loops 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportClientFactory.java"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"111e25f8429aa1cea9165aa6386c45d71a08c7f9a977984834b8244474d6e764"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.binaryTrimRight (cognitive 16): CollationAwareUTF8String.binaryTrimRight has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (9 pts), loops 4 (5 pts), boolean chains 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1410}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fa91a0912ac449d16bdebcdfb631e63850bcb223624e2165d22cf6c7c0c2aad"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.lowercaseSubStringIndex (cognitive 16): CollationAwareUTF8String.lowercaseSubStringIndex has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1041}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff01a3eda1e6a067973f67c3fb44588b928e7d3ee65bde7a258af8b612852e2e"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.translate (cognitive 16): CollationAwareUTF8String.translate has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (13 pts), loops 2 (3 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1167}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6abae9385fd32fe7aa3c7f7f86afa356ddb5549e4eb42dc6117342ec3f68bf0"}},{"ruleId":"D2","level":"warning","message":{"text":"CollationAwareUTF8String.trimLeft (cognitive 16): CollationAwareUTF8String.trimLeft has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 3 (4 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1355}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dabc12ce3ea604c8532b8372675bdf29ed76d7155f8ac5d3519918e4c5fa945"}},{"ruleId":"D2","level":"warning","message":{"text":"HeapMemoryAllocator.allocate (cognitive 16): HeapMemoryAllocator.allocate has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (13 pts), loops 1 (3 pts) (nesting depth added 10). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/memory/HeapMemoryAllocator.java"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ed3302c6f0db7fe12c6b726eb5b97ed039263facb36902ce18dd293495bb4d4"}},{"ruleId":"D2","level":"warning","message":{"text":"ValueCopier.forTypeOrNull (cognitive 16): ValueCopier.forTypeOrNull has cognitive complexity 16 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 3 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ValueCopier.java"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5730c685db9ea55c3f09f15e06126ccd965db74342c6f1ac64ce4f1e68821e9"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorizedRleValuesReader.initFromPage (cognitive 16): VectorizedRleValuesReader.initFromPage has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (15 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"a78287d49b048dc231ebdcab0539eec681ab141f7b0242e9f3b79222c5f57623"}},{"ruleId":"D2","level":"warning","message":{"text":"VectorizedRleValuesReader.readPackedBatch (cognitive 16): VectorizedRleValuesReader.readPackedBatch has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (7 pts), loops 3 (7 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":293}}}],"partialFingerprints":{"codehealthFindingId/v1":"939bd86d704264eee10bc19df5ce62bc3e2490cbb68108e8fb070484157ddb20"}},{"ruleId":"D2","level":"warning","message":{"text":"PlainSaslServer.evaluateResponse (cognitive 16): PlainSaslServer.evaluateResponse has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (9 pts), boolean chains 3, error handling 3, loops 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/PlainSaslServer.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ac78c4f943aeff2f2037ed1fd3eb63666642fd4bb58eddf6fd111a2b584c942"}},{"ruleId":"D2","level":"warning","message":{"text":"4.run (cognitive 16): 4.run has cognitive complexity 16 (threshold 15). Drivers by points: if/else 3 (7 pts), error handling 1 (4 pts), loops 2 (3 pts), boolean chains 2 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/SessionManager.java"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"e61c9718ec0cb230788e68ebee8130c6223f127d14030f016877426d0317ee5b"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkDefaultUDAFEvaluatorResolver.getEvaluatorClass (cognitive 16): SparkDefaultUDAFEvaluatorResolver.getEvaluatorClass has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (11 pts), loops 4 (5 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/SparkDefaultUDAFEvaluatorResolver.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"1840bca8a16bc558c28e349313b01c31aac7d9e9f405b3759a70a717a4cd8f19"}},{"ruleId":"D2","level":"warning","message":{"text":"merge_spark_pr.cherry_pick (cognitive 16): merge_spark_pr.cherry_pick has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), error handling 3 (7 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":1358}}}],"partialFingerprints":{"codehealthFindingId/v1":"94c541be18f75d80db5416c18a2e71a07cc90fc629d6151078570c47ed980995"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowElementwiseUDFHandler.run (cognitive 16): ArrowElementwiseUDFHandler.run has cognitive complexity 16 (threshold 15). Drivers by points: loops 3 (6 pts), if/else 1 (4 pts), error handling 1 (3 pts), ternaries 1 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_elementwise.py"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"b66e2b8d072e3df9dbad7847b580c4f6ee5d44dede49e1265ace11b3dda621f2"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowTableUDTFArrowHandler._check_return_value (cognitive 16): ArrowTableUDTFArrowHandler._check_return_value has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (13 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_udtf.py"},"region":{"startLine":1187}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf6978ff18a55cbcc3c0293a7854fddc5e217b84039041fa7e3283929c55bfd4"}},{"ruleId":"D2","level":"warning","message":{"text":"SummarizerAggState.to_result (cognitive 16): SummarizerAggState.to_result has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/summarizer.py"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"db87a3cd247057839e1084a415b95bcb8b20385afae45aeceacc8d6e3a63e1d4"}},{"ruleId":"D2","level":"warning","message":{"text":"JavaParams._transfer_params_from_java (cognitive 16): JavaParams._transfer_params_from_java has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (13 pts), boolean chains 2, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/wrapper.py"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"47140c746d61b2447cef29954c3ea9587038f8212e83c1615b4a719be0d01ddb"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.__init__ (cognitive 16): SparseVector.__init__ has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SparseVector.__init__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/__init__.py"},"region":{"startLine":612}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4e11b9cfbd91235d7cc06eee64c721bafb96d1f0ce7fe5243b52c636f8422ac"}},{"ruleId":"D2","level":"warning","message":{"text":"SparseVector.__init__ (cognitive 16): SparseVector.__init__ has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (SparseVector.__init__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/__init__.py"},"region":{"startLine":623}}}],"partialFingerprints":{"codehealthFindingId/v1":"f53534f8ce8071717340140c8d506c5abf1b682ee671d3e54de7a89beed72e6e"}},{"ruleId":"D2","level":"warning","message":{"text":"FractionalExtensionOps.astype (cognitive 16): FractionalExtensionOps.astype has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (14 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":694}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2d762ac14c5afef8bdba570c30e3148357d4bb2f21d8d84ca2b8f9ffdb4e119"}},{"ruleId":"D2","level":"warning","message":{"text":"DataFrame._mark_duplicates (cognitive 16): DataFrame._mark_duplicates has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (12 pts), ternaries 1 (3 pts), boolean chains 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5259}}}],"partialFingerprints":{"codehealthFindingId/v1":"448b438490cca8a7a16ad1336eb6723d43624c3c574fe64426d355165e235925"}},{"ruleId":"D2","level":"warning","message":{"text":"GroupBy._spark_groupby (cognitive 16): GroupBy._spark_groupby has cognitive complexity 16 (threshold 15). Drivers by points: ternaries 3 (7 pts), if/else 3 (6 pts), loops 2 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"764bb21b3d3cad9c666910cf3103a2f3c17f5dec10be61c4ba42db1a13924335"}},{"ruleId":"D2","level":"warning","message":{"text":"MultiIndex.drop (cognitive 16): MultiIndex.drop has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (14 pts), loops 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":837}}}],"partialFingerprints":{"codehealthFindingId/v1":"17673bcd197e2395af7213f3202b613356b854b89c0db14a212b9f72f6fcb781"}},{"ruleId":"D2","level":"warning","message":{"text":"InternalFrame.restore_index (cognitive 16): InternalFrame.restore_index has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (6 pts), boolean chains 4, ternaries 3 (4 pts), loops 2 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":1123}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a7798a4fbc1d8955ed08db7d07276d206bd4f074fe9a1bba830ead9ff363843"}},{"ruleId":"D2","level":"warning","message":{"text":"ExternalMerger.mergeCombiners (cognitive 16): ExternalMerger.mergeCombiners has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (10 pts), ternaries 2 (4 pts), boolean chains 1, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":326}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ac1b5385f822456380ed8fda229d5cb6255fcd3476341ff873642ce31ca44cb"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectClient._analyze (cognitive 16): SparkConnectClient._analyze has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), boolean chains 1, error handling 1, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1592}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d90ae71481175630dcaf8afa96bb33e648ab8a5aa53b68b332f42c5bd9e135d"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkConnectClient._handle_rpc_error (cognitive 16): SparkConnectClient._handle_rpc_error has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (14 pts), loops 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2405}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9fadf33f15f71fb627a150e6f6de5d4ed795a45850092147db48c86f3b8e857"}},{"ruleId":"D2","level":"warning","message":{"text":"LiteralExpression.__repr__ (cognitive 16): LiteralExpression.__repr__ has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), boolean chains 5 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad87d4c90715852b06fb4b5d85af0e88b3bfa40c9ae57574c7ddcc7bce7f6acf"}},{"ruleId":"D2","level":"warning","message":{"text":"DataStreamWriter.trigger (cognitive 16): DataStreamWriter.trigger has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), boolean chains 3 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":571}}}],"partialFingerprints":{"codehealthFindingId/v1":"6baa987b5af1c04a0b51798b36c335c12968b13c25604ec8d368b04cafc10262"}},{"ruleId":"D2","level":"warning","message":{"text":"PandasToArrowConversion.from_pandas (cognitive 16): PandasToArrowConversion.from_pandas has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (9 pts), boolean chains 3, ternaries 2 (3 pts), loops 1 (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ba517ed992905ef528d73605084fa6cbee42d3bc40b2fba7b76c092a96ac95c"}},{"ruleId":"D2","level":"warning","message":{"text":"types.from_arrow_type (cognitive 16): types.from_arrow_type has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (15 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ae66a011774680ea0717f899a5e637eb438cad250525896014bc7f019574dd9"}},{"ruleId":"D2","level":"warning","message":{"text":"DataStreamWriter.trigger (cognitive 16): DataStreamWriter.trigger has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (13 pts), boolean chains 3 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":1358}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d67affe2e805e1c49b767074d3ad429eda9a6524b0dd9177b3a5a5778153927"}},{"ruleId":"D2","level":"warning","message":{"text":"StructType.toInternal (cognitive 16): StructType.toInternal has cognitive complexity 16 (threshold 15). Drivers by points: ternaries 3 (9 pts), if/else 6 (7 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2000}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfd0f114655a35d0fc4f1e1eb1cf423e95401c19d38f3e3498c027a90d91564f"}},{"ruleId":"D2","level":"warning","message":{"text":"types._merge_type (cognitive 16): types._merge_type has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (8 pts), boolean chains 6, loops 1 (2 pts) (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":3297}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f1342db4527252997a29414655690f391cf2962b2864550fd4b0aac7ee55d1e"}},{"ruleId":"D2","level":"warning","message":{"text":"spark-sql-viz.formatMetricValue (cognitive 16): spark-sql-viz.formatMetricValue has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (10 pts), boolean chains 5, loops 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":344}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fdb5f753e30b27632b9811af0dc956177dcd3955ecc8eea6bdcf4b552b7cfae"}},{"ruleId":"D2","level":"warning","message":{"text":"spark-sql-viz.setupPlanVizSearch (cognitive 16): spark-sql-viz.setupPlanVizSearch has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9, boolean chains 5, ternaries 1 (2 pts) (nesting depth added 1). Most of this is not in the body itself: 3 of the 16 points are its own statements and the rest belongs to 3 function literals inside it that branch (lines 888, 875, 868). The decisions are inside those literals, which nothing outside this body can call, review or test on its own, so splitting the enclosing body is not the move available here. To reduce it, lift the literals\u0027 work into a named function or method at the enclosing scope and have each literal call it, then reduce whichever part then reads as the largest."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":850}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdcce4346c0960e9526beecf55159c4d34ca8b0c61823ee98732da21069f8d33"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: functions: TooManyMethods \u2014 1051 methods. The bar is 30 methods; this is 1021 over it, 35.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"3278977733d507e74d166ba5a64f6d6f3599b0d4670f84ea4fe2f3b4f5512453"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryCompilationErrors: TooManyMethods \u2014 659 methods. The bar is 30 methods; this is 629 over it, 21.97\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fa9454e3a55daa841a1677eb7a4771348bfa1c40e26e85144f45529adef8c43"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: internal/SQLConf.scala: FileTooLong \u2014 9327 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 8827 over it, 18.65\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fae6eca803b0eb44ccbfd3a2794c3e34e6bb0dc7c76cc989ba08a841e57d177"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryExecutionErrors: TooManyMethods \u2014 450 methods. The bar is 30 methods; this is 420 over it, 15.00\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"723cb0975f363b50b26b256260f0b65775c0e57eef6cb9f90d6bbc58e6359371"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: AstBuilder: ClassTooLong \u2014 5021 significant lines (blank, comment-only and punctuation-only lines excluded), 148 methods. The bar is 400 significant lines; this is 4621 over it, 12.55\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"57fb9143ac8ce3840477aa00e17bd223444eed6082e2e3ed4afc24728e5f70da"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/frame.py: FileTooLong \u2014 5883 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 5383 over it, 11.77\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"abe1ff5d74594d077849fedbbb3009ebe7eb3490e5cced1b7854ec13f82a3ec5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parser/AstBuilder.scala: FileTooLong \u2014 5075 significant lines (blank, comment-only and punctuation-only lines excluded), about 99% of them inside a single declaration: AstBuilder (68-8665). The bar is 500 significant lines; this is 4575 over it, 10.15\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d9936b073e221e56bac276877ac51aa173dfac5ba40139fb9d1cb1af7fbf2ac"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/collectionOperations.scala: FileTooLong \u2014 4466 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 3966 over it, 8.93\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e941dc54ace883eb1ae3d997ff8ae28bf66bc8bae1bf5ceb5ffc637b19ed8810"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SparkConnectPlanner: ClassTooLong \u2014 3336 significant lines (blank, comment-only and punctuation-only lines excluded), 208 methods. The bar is 400 significant lines; this is 2936 over it, 8.34\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"7812368c27691c8d5d8e393f0e0d746e1c18fc614ecfdf775a6b338b572f77df"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/datetimeExpressions.scala: FileTooLong \u2014 4083 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 3583 over it, 8.17\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"00e72ae2066efbdad12ff67fc71fe133adeb513322725f1ba1bd2e4040f75643"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: errors/QueryCompilationErrors.scala: FileTooLong \u2014 3824 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 3324 over it, 7.65\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"40c9730043783dccc375a4f12ecf5c9edd880905e3797027c2f17c5c53186221"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkConnectPlanner: TooManyMethods \u2014 208 methods. The bar is 30 methods; this is 178 over it, 6.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"20e6fd7cdcfb95c425ef533e6bd1cd8bf6a7c673bf712b0269cdcd2f4cdfc353"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Dataset: TooManyMethods \u2014 205 methods. The bar is 30 methods; this is 175 over it, 6.83\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Dataset.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f8252ece0e72ddaf398881bd4e1d9f9c667f8180ebba419792900f218ca5f0e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: planner/SparkConnectPlanner.scala: FileTooLong \u2014 3404 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: SparkConnectPlanner (91-4747). The bar is 500 significant lines; this is 2904 over it, 6.81\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad3c2f9f6d9aec33c4a22a84e8d6b15c1de775975c83aad831c310626d6c36ea"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: functions/builtin.py: FileTooLong \u2014 3320 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2820 over it, 6.64\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"50eae0500a2eb2b38edbb47d95e5791a5aa917bce880881befd68c0c796d1022"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataFrame: TooManyMethods \u2014 197 methods. The bar is 30 methods; this is 167 over it, 6.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dd4f31d2f4a9ba99ae08f38c1cddae04322652129781511e81c10f2fe50a92f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/stringExpressions.scala: FileTooLong \u2014 3103 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2603 over it, 6.21\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e346c0636b5b759579682e63d1ca239ba454fd044268cb11597ced400b89d2c4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkContext: TooManyMethods \u2014 181 methods. The bar is 30 methods; this is 151 over it, 6.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"6555c1fc5609089982137a61ef85e276f9968ef9189608fa51d9c745df4f74e8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: config/package.scala: FileTooLong \u2014 2963 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2463 over it, 5.93\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/config/package.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e220697077ff95e5f9e2b745a77ce87a26d22479db06b63fe248c60a1f249647"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Utils: TooManyMethods \u2014 175 methods. The bar is 30 methods; this is 145 over it, 5.83\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"c74d5975ad42e9b0058216fd9e98a108a755025110614075a28efc1539fe0f2e"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SessionCatalog: TooManyMethods \u2014 174 methods. The bar is 30 methods; this is 144 over it, 5.80\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9e23cfc37d6375cbf62e9e69055acc1b385fd57d846b09257e7c0901fd00e6e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: errors/QueryExecutionErrors.scala: FileTooLong \u2014 2848 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2348 over it, 5.70\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bee92ca61ce1d1b400ae7cd3bdb3062cb08cbd2d501b23290492684ef1a06789"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: scheduler/DAGScheduler.scala: FileTooLong \u2014 2747 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2247 over it, 5.49\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"43939bd49ca02d7d1dcd542cef9d713667ead0fcc47c1bc14943b9370267e96c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/Analyzer.scala: FileTooLong \u2014 2616 significant lines (blank, comment-only and punctuation-only lines excluded), about 87% of them inside a single declaration: Analyzer (429-4447). The bar is 500 significant lines; this is 2116 over it, 5.23\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9225d33b359ea45031de141d5dfae8d4be15d27c3aa357110d613abf9c815242"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DAGScheduler: TooManyMethods \u2014 154 methods. The bar is 30 methods; this is 124 over it, 5.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa6e6cb70a83203182a121b9be3b484feaa61c5fb024be6fc94fe42bffd13f71"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: dev/merge_spark_pr.py: FileTooLong \u2014 2528 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2028 over it, 5.06\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"53df2d6eb453befcdfbdb5d2cfab84f2a1f358c6f89685774f5e8aa527d39a1d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Dataset: TooManyMethods \u2014 151 methods. The bar is 30 methods; this is 121 over it, 5.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd4f9ca49a8abed2648760c6e6aa0d36f97665a1ddfb5b4579123da3983f4bf0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/feature.py: FileTooLong \u2014 2505 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2005 over it, 5.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/feature.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0495449109f565aeb7fb79eed523c446e32730eb59b978b545498cd37cdf107a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: AstBuilder: TooManyMethods \u2014 148 methods. The bar is 30 methods; this is 118 over it, 4.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5de33a91a274bb8189b1809c702ab5e0bdf85388553f5c06e2233fe992d2d6e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/series.py: FileTooLong \u2014 2411 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1911 over it, 4.82\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6326ccc75869161c22f02da8ec6fcd306ee8a205a3ac390c72ffc1234fdbd8ed"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryParsingErrors: TooManyMethods \u2014 143 methods. The bar is 30 methods; this is 113 over it, 4.77\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c1148e584bdb2f4bcea9cb4d48b26b1a56e8dbc2a407f8ab3e96720e916507b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/types.py: FileTooLong \u2014 2328 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1828 over it, 4.66\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4af38bbde6fb4a54e1c10cc264491a5855a84b9233fcade4c30646700ce93bd"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RDD: TooManyMethods \u2014 135 methods. The bar is 30 methods; this is 105 over it, 4.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6c752d98af537799f90676c3dbdf2d38db392b3b65ca4e787280254a2024d93"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataFrame: TooManyMethods \u2014 135 methods. The bar is 30 methods; this is 105 over it, 4.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6a239ba5c8ba33a2dc92969d9088bdca48d524ca547b7357bc718559dc45e83"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Series: TooManyMethods \u2014 132 methods. The bar is 30 methods; this is 102 over it, 4.40\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":393}}}],"partialFingerprints":{"codehealthFindingId/v1":"08e4e3831ed584d1ae87e61fed854cf0a8fce6941e1ec6291ea6dac8fe584f71"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataFrame: TooManyMethods \u2014 131 methods. The bar is 30 methods; this is 101 over it, 4.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4143797d8dfbfcd578542c5e843a493afdf8b2bfdc0c3821af2d01130165660"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/Cast.scala: FileTooLong \u2014 2168 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1668 over it, 4.34\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"76f0619deb2191144c44fba3cec7a1fa2a68eac15bd5e6e0fbb6c7663af04473"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/plan.py: FileTooLong \u2014 2148 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1648 over it, 4.30\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c69da92d7292d182398c2b47ecca32488413932dda45f954398debc597704d4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RDD: TooManyMethods \u2014 127 methods. The bar is 30 methods; this is 97 over it, 4.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc6379f31e4691c6e026eca1256805bcc58764e8592817d626bd33f24f945b5f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/classification.py: FileTooLong \u2014 2116 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1616 over it, 4.23\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a385b2e1ae87c41ef740ec0a982aac3cbaf4726f864829913a1656683a2b7061"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Dataset: TooManyMethods \u2014 126 methods. The bar is 30 methods; this is 96 over it, 4.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"30e204fa4926f69d27901bb5ea56e3b506cc612791dc6d8687e7da88a2a87d64"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/functions.scala: FileTooLong \u2014 2060 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1560 over it, 4.12\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a641c748a3057f012aa826c2444a6ece0ed1037f8919a215621477f55cd098f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: optimizer/Optimizer.scala: FileTooLong \u2014 2047 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1547 over it, 4.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"998b211b0a780e61a4da164d63caaa001eb5a158c811affa2f99b0ddf2944df2"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/dataframe.py: FileTooLong \u2014 1976 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1476 over it, 3.95\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e232581a62e18410dd8796f26d74515e6bfbe3fb0a29dc5c591dde9049ce79f4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: UTF8String: TooManyMethods \u2014 118 methods. The bar is 30 methods; this is 88 over it, 3.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"923a9b6f51ccc5935d9c6be35db4b49b77a48d85a8b4bc05dc4d9c297384e085"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/namespace.py: FileTooLong \u2014 1913 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1413 over it, 3.83\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"67a0f090fc0bc4a02006bff4942026399555f1ef64e8922c84c111a035bc7741"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: client/core.py: FileTooLong \u2014 1870 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1370 over it, 3.74\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"16fe9218ddf19512d5c9793303c9f0efba15eb98791fcb0cb9fcfb81da920904"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/generic.py: FileTooLong \u2014 1857 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1357 over it, 3.71\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b61fc67ae489207c47d4aa3d1f8600b747ad13a8c3b139ddb3d8b4bfaefd1f1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/Utils.scala: FileTooLong \u2014 1851 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1351 over it, 3.70\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d83cd606faef15802e34d902d3d8000852acfeba500df1a73a2500b7393bed2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: WritableColumnVector: TooManyMethods \u2014 111 methods. The bar is 30 methods; this is 81 over it, 3.70\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"b67947d5bdb2e3c21852f37688beec69b9f8c570e29457478b5e9de481b7cdba"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/groupby.py: FileTooLong \u2014 1849 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1349 over it, 3.70\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb193880e13fbe1faf8e000e37af5e3f04606e34b88fdf513b4480271f667162"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: variant/variantExpressions.scala: FileTooLong \u2014 1833 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1333 over it, 3.67\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7eb15e2a2910cbd83f5521be7b1a04737b2e1927a6f366360fb0689c86b88f72"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ParquetVectorUpdaterFactory: ClassTooLong \u2014 1448 significant lines (blank, comment-only and punctuation-only lines excluded), 20 methods. The bar is 400 significant lines; this is 1048 over it, 3.62\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1f6166a801a276a52ae6d418ad72ff5637e2d2bedff121cea35ee7a2a0e0ee2"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/SparkContext.scala: FileTooLong \u2014 1770 significant lines (blank, comment-only and punctuation-only lines excluded), about 79% of them inside a single declaration: SparkContext (88-3341). The bar is 500 significant lines; this is 1270 over it, 3.54\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d1e0a0642486e812dce9c62d804733b9bc9817f713710ea70116dd2084f99da"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/RocksDB.scala: FileTooLong \u2014 1762 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1262 over it, 3.52\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6d8f9b2c40294e53be9f57a4b7cccff73c042b98fd46f63325ec54112ecee1c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: logical/basicLogicalOperators.scala: FileTooLong \u2014 1690 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1190 over it, 3.38\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3fc87d54d64ee9bae63266834c14d3833b3630cce7145ac9a3ae8b889f70dd4"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: RemoteBlockPushResolver: ClassTooLong \u2014 1330 significant lines (blank, comment-only and punctuation-only lines excluded), 39 methods. The bar is 400 significant lines; this is 930 over it, 3.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbf8c9cfe7ba679d519d96ff352ca65ab1c103950831d7d27966e1d4db277c25"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/jsonExpressions.scala: FileTooLong \u2014 1657 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1157 over it, 3.31\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddb75d9a964a9f9f14fc8d342115c2ba29e1d74365632b69b8637537a019874e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classic/dataframe.py: FileTooLong \u2014 1634 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1134 over it, 3.27\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdd6cf94ba3d9ef3d8b1a8b66379975ebbe0a5eb0d26385c2d9720ea93da383d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/mathExpressions.scala: FileTooLong \u2014 1634 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1134 over it, 3.27\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"40e5817c028e6fc822a92b8cb21dfb981d7e2ce9515df843b1a2167de8a61938"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaPairRDD: TooManyMethods \u2014 96 methods. The bar is 30 methods; this is 66 over it, 3.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"54665ac293514a217dd1181ea88bfa11b71869b65c7f58f439926c92cf8ad7fb"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DateTimeUtils: TooManyMethods \u2014 96 methods. The bar is 30 methods; this is 66 over it, 3.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8fa630d7065726c2800ad538a56d5186ad8400d6da44eb56efb97d01d3a223b"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JsonProtocol: TooManyMethods \u2014 94 methods. The bar is 30 methods; this is 64 over it, 3.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/JsonProtocol.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbb497010cf854eb41ee4ec4aa146336c84dc0438d79ec292f0ab74b00b362a7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: core/context.py: FileTooLong \u2014 1535 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1035 over it, 3.07\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/context.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad9c03c52d59fa93b101fac4c48f62d2eb5d509ba6dbcf0b6cf9c990f4d3fdb4"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: catalog/SessionCatalog.scala: FileTooLong \u2014 1533 significant lines (blank, comment-only and punctuation-only lines excluded), about 97% of them inside a single declaration: SessionCatalog (91-3058). The bar is 500 significant lines; this is 1033 over it, 3.07\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"33acf07217bf7118c85172a9ae6adb9247f85cee09f540aab0978690aa391f63"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Column: TooManyMethods \u2014 89 methods. The bar is 30 methods; this is 59 over it, 2.97\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Column.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"57125edd52df140324a11a7f02813c6f5958c68ed4205a514483e940521ea835"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: UTF8String: ClassTooLong \u2014 1182 significant lines (blank, comment-only and punctuation-only lines excluded), 118 methods. The bar is 400 significant lines; this is 782 over it, 2.96\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5b442971142c19272e7a5a9c1a86ce4dd1d324ce973b26fea4e11301f7826ec"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/ParquetVectorUpdaterFactory.java: FileTooLong \u2014 1475 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: ParquetVectorUpdaterFactory (49-2082). The bar is 500 significant lines; this is 975 over it, 2.95\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d74721276a06d109935963b83888ed62b33cc7ec0a971fa5165c84bf11eb82f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/regression.py: FileTooLong \u2014 1453 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 953 over it, 2.91\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/regression.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b684b544ba74c27cf18b55f0cc19bbb24bbf90470585ec25b9bd6966ba457d3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/conversion.py: FileTooLong \u2014 1410 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 910 over it, 2.82\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab73c924bddac31752bd48513a62e8104d4f0f5f1676c616809f86a779dca762"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: storage/BlockManager.scala: FileTooLong \u2014 1406 significant lines (blank, comment-only and punctuation-only lines excluded), about 86% of them inside a single declaration: executorId (184-2454). The bar is 500 significant lines; this is 906 over it, 2.81\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"61e18e2944d548309dd5919bdc4a76e2c399bf78140e70970a26ce4aaad4d9ef"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: core/rdd.py: FileTooLong \u2014 1399 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 899 over it, 2.80\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5fff737ee70ef13a518b129c1ae8aac0d93922c971d76466c939c7483674fef"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: join/SymmetricHashJoinStateManager.scala: FileTooLong \u2014 1398 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 898 over it, 2.80\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9db90687fdb06dc4b67c3d9a33c423acd588f22a16d9417c80ccd4c761f2942c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/RemoteBlockPushResolver.java: FileTooLong \u2014 1397 significant lines (blank, comment-only and punctuation-only lines excluded), about 95% of them inside a single declaration: RemoteBlockPushResolver (97-2297). The bar is 500 significant lines; this is 897 over it, 2.79\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"86b993e3a5195e83c5c34cb3a364b5c14c352e8b8562491f8ff121cc8878d828"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classic/Dataset.scala: FileTooLong \u2014 1395 significant lines (blank, comment-only and punctuation-only lines excluded), about 93% of them inside a single declaration: Dataset (231-2514). The bar is 500 significant lines; this is 895 over it, 2.79\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e2a029a825635199f7532900518dc1241be5a1afe9c2c4625e7a6591eef61d6"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: logical/v2Commands.scala: FileTooLong \u2014 1355 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 855 over it, 2.71\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/v2Commands.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"04dc64780a7f5b82fc5ca11f06739bf0a0aa649d313ddb460f78eb5c332a30c6"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaSparkContext: TooManyMethods \u2014 79 methods. The bar is 30 methods; this is 49 over it, 2.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d1572586fc346fed0d83c7de64fd8321e1b26cf073412b5292ff82c1851c03d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkConnectClient: TooManyMethods \u2014 79 methods. The bar is 30 methods; this is 49 over it, 2.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":816}}}],"partialFingerprints":{"codehealthFindingId/v1":"f70331dfc3d9310b9484b324169725acf361b4413033dddea7972c103f4beaea"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: objects/objects.scala: FileTooLong \u2014 1314 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 814 over it, 2.63\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a98464bff8f93c57b891a99b9bcd0cfca68040bc99aedf485959afd86ecb9352"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaRDDLike: TooManyMethods \u2014 78 methods. The bar is 30 methods; this is 48 over it, 2.60\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"416cc2e89f8fa3838854a17586eb0367b2bda3ef5df8da8ef7e0f0a6130dc52c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TreeNode: TooManyMethods \u2014 78 methods. The bar is 30 methods; this is 48 over it, 2.60\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1aa0cc8731fc1222476569c053a9648d02e15c425ec822bb2573ad20876ad14"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: NativeLibrary: ClassTooLong \u2014 1027 significant lines (blank, comment-only and punctuation-only lines excluded), 59 methods. The bar is 400 significant lines; this is 627 over it, 2.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c6aec9ce3264e43bcd4771ae55bc67cfffa7f0b9a5cb9758b33daf93880e415"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/higherOrderFunctions.scala: FileTooLong \u2014 1280 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 780 over it, 2.56\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4718672d740a182b6d34cfbc25da82b7ee8ee6f8578fd374d0bb3103d60d797a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/JsonProtocol.scala: FileTooLong \u2014 1269 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 769 over it, 2.54\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/JsonProtocol.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7d2979ce30bb76ade2009b88312273737e651c01bf08a4dbebaf9538d19cb2a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: history/FsHistoryProvider.scala: FileTooLong \u2014 1252 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 752 over it, 2.50\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1e05be25d8d2a6993f5c518b55aa9ff3996e3c825ce095c82006be39fa08d4e"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: PythonMLLibAPI: TooManyMethods \u2014 75 methods. The bar is 30 methods; this is 45 over it, 2.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"904bac41b307186a8e5d010f825f104992ef179c239e35c0d28e1947f9d77fbf"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RocksDB: TooManyMethods \u2014 75 methods. The bar is 30 methods; this is 45 over it, 2.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b73cc214e4d654ebd4cf6d9199e3bcfb9d4d05da3398c72cfdc81340b5e65cf"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: PairRDDFunctions: TooManyMethods \u2014 73 methods. The bar is 30 methods; this is 43 over it, 2.43\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f4bda5749e7fbcf2f9692ff4a2f56d1efdce9582197c33420693e1cabdddb78"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: AvroDeserializer.deserialize: MethodTooLong \u2014 deserialize runs 242 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 142 over it, 2.42\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d6e2f97a49ba734b6fa7721c1c3a1576a134f588e8cd7a8334fe62aac9692bf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: types/UTF8String.java: FileTooLong \u2014 1205 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: UTF8String (55-2423). The bar is 500 significant lines; this is 705 over it, 2.41\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec4e175ac846b495988326433f18d9c74dfb6a5ce3ad919ca915819a12492464"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: AvroDeserializer.newWriter: MethodTooLong \u2014 newWriter runs 241 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 141 over it, 2.41\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"02d07c301b37f971216856aa55f348bbb3fd6064787ff7f108f864319608e64b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/RocksDBStateStoreProvider.scala: FileTooLong \u2014 1186 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 686 over it, 2.37\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"42e746e47240d369c779b7feb841153ab980b51cd029d626309e424366126db9"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Column: TooManyMethods \u2014 71 methods. The bar is 30 methods; this is 41 over it, 2.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"f36fc1f8987aecc3cb40783d0f4dcd50bcac209f39e7473ed72e6e5b01bbde66"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SQLContext: TooManyMethods \u2014 71 methods. The bar is 30 methods; this is 41 over it, 2.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/SQLContext.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"efdc86dca38465f90d940196d5d0148726558ec7f16ff5374dab126bbb957e32"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: HiveInspectors.unwrapperFor: MethodTooLong \u2014 unwrapperFor runs 236 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 136 over it, 2.36\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"f02a764a1b09f2a634cf3029c493f746a0b280f74fc6304643da0ba43999f94d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkCoreErrors: TooManyMethods \u2014 70 methods. The bar is 30 methods; this is 40 over it, 2.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/errors/SparkCoreErrors.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6baaa239a133edc266c3c024647c038f976523eaaa82730c44bef9eef3a6da1"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: BlockManager: TooManyMethods \u2014 70 methods. The bar is 30 methods; this is 40 over it, 2.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"5946c08e1ec88a1a07b035658c87fc7e76399e9db8877a6a1f6d48f5a05c380f"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Column: TooManyMethods \u2014 70 methods. The bar is 30 methods; this is 40 over it, 2.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/column.py"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fdfca9976f2aa2108086f2e7babe0ab8a969a7f326910de95f0b903975f41f3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: client/HiveShim.scala: FileTooLong \u2014 1164 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 664 over it, 2.33\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"40ea0c51ccf9136c0ca13926cf43bd3136abb3dd88b804416f0658d119cd6188"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/indexing.py: FileTooLong \u2014 1161 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 661 over it, 2.32\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"505f00caa8a27a203d3e9fba135fefa5003fd1f04e74cb97e5fb5fcf4aab1c79"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/arithmetic.scala: FileTooLong \u2014 1139 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 639 over it, 2.28\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c9a9f9401c3d61b0d1401af743beda729029dcb6c06a754adebc6c50284294f"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SparkSqlAstBuilder: ClassTooLong \u2014 903 significant lines (blank, comment-only and punctuation-only lines excluded), 11 methods. The bar is 400 significant lines; this is 503 over it, 2.26\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa5a3e37c73c2d52e85ae42280d9ec9361275003175b1fd719f56bd5fd7fe512"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ResolverGuard: TooManyMethods \u2014 67 methods. The bar is 30 methods; this is 37 over it, 2.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ResolverGuard.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b60bfdae0db765c7204ec757d99aef55c5af3dad43b04b680faca0f2f432ee4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JdbcDialect: TooManyMethods \u2014 67 methods. The bar is 30 methods; this is 37 over it, 2.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b0ae42a37195fec44e3a7ee912eb6a6c44e420802044e4afaa481b14a768c9f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/readwriter.py: FileTooLong \u2014 1111 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 611 over it, 2.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a6962c9ace83560cf55a9ba9ed39f9bcec383373d9b13a84162dd16b9f827cf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/RocksDBStateEncoder.scala: FileTooLong \u2014 1111 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 611 over it, 2.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"34fbc5f829488bf9fd7c4179f2eef7dc8e18ecfb16924fdd193e547ce9017de9"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/FunctionRegistry.scala: FileTooLong \u2014 1100 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 600 over it, 2.20\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"031fdf1704f6657a05aba08a7eab688fe4f820253e938e383fa895c6b26f1898"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: joins/SortMergeJoinExec.scala: FileTooLong \u2014 1098 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 598 over it, 2.20\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ea9273efde485abff739b7ba6039f465ba94106f8c8b129123a216a987fa42c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: UnsafeRow: TooManyMethods \u2014 65 methods. The bar is 30 methods; this is 35 over it, 2.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"76a3960b0e307e7435ec6155a4814bdc15bc30cb3e7261a07f4fec20f66332c0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/regexpExpressions.scala: FileTooLong \u2014 1070 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 570 over it, 2.14\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf53e0be8311736ed3433d44c1ac6cc13e55e7cbdbc0b3e74a2cc9828f66d68c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: python/PythonRunner.scala: FileTooLong \u2014 1069 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 569 over it, 2.14\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"84320e418be1448b7851686814177d855d46326bbb43b8dd13d2b16795bf846e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/StateStore.scala: FileTooLong \u2014 1052 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 552 over it, 2.10\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"28e3068e5d82fcbd957e69e3af7c1dca2d18f8dc1484fab26cf93edffd95d9f5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: IntervalUtils: TooManyMethods \u2014 63 methods. The bar is 30 methods; this is 33 over it, 2.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"62efac2dbefbfe1df8f5e99e0304cdb8a2979830095cdf95fab7863f7d5886d8"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: OffHeapColumnVector: TooManyMethods \u2014 63 methods. The bar is 30 methods; this is 33 over it, 2.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b613104981443e869b5578afdb6f984102a3cc35a465223799029a349e2f920"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/types.py: FileTooLong \u2014 1047 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 547 over it, 2.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6cba6e44fffdf7c1e124712e4ade373a4dfcdf442327c99a5555249eb47b559"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ffi/NativeLibrary.java: FileTooLong \u2014 1047 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: NativeLibrary (58-1670). The bar is 500 significant lines; this is 547 over it, 2.09\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"905e034c8ff4f97f62abcc2e5c9bfd347d7caa8e52b2d6420f672c2826e6c278"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: runtime/MicroBatchExecution.scala: FileTooLong \u2014 1046 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 546 over it, 2.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f379ce496683b7a1d262135bcb143e9da59ff9ad7a10cacbdb2dd6fbb11a6fb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: yarn/Client.scala: FileTooLong \u2014 1045 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 545 over it, 2.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2eebc21bfe432ee909f4d036a724937ee939a7716cddc5e36be786c7926559c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/expressions.py: FileTooLong \u2014 1041 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 541 over it, 2.08\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fc1f86c23838f7ef3eac993039d818dcfd213718cb27d11623f4c8b4b6f3cbf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: columnar/ArrowCachedBatchSerializer.scala: FileTooLong \u2014 1039 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 539 over it, 2.08\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a37f6dec8339619ed890fe3618c9b76b5c85885ccda982857ec0204b07df5661"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: stateful/statefulOperators.scala: FileTooLong \u2014 1034 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 534 over it, 2.07\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea0535bd85818444ab7f1208492b44c7c07079955ecbe254b4d80b861012362c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: hive/HiveInspectors.scala: FileTooLong \u2014 1034 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 534 over it, 2.07\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8140efa31be17a6ebb1cd9b538936f4d7679cacdb4636a6056b7301465e4d95"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: VariantBuilder: ClassTooLong \u2014 827 significant lines (blank, comment-only and punctuation-only lines excluded), 50 methods. The bar is 400 significant lines; this is 427 over it, 2.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4d7971277c5da9f4accf1646128823c9ca06a9d1b75e19e9bda35009ea3a040"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TransportConf: TooManyMethods \u2014 62 methods. The bar is 30 methods; this is 32 over it, 2.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"805d65b240041ca362a5d7e9ccdb758df080e1eac194a8a121548b5ec7fd019a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Index: TooManyMethods \u2014 62 methods. The bar is 30 methods; this is 32 over it, 2.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"81436de0a26bd5f37f880acb133d0cf10cc5401dcc1e1345dd952bd14a080179"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ExpressionResolver: TooManyMethods \u2014 62 methods. The bar is 30 methods; this is 32 over it, 2.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ExpressionResolver.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6bb222ed97fdc58bb13ec03f1719f914d7bd50a29f4d5b73fcbf5adf082dcc7"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: OnHeapColumnVector: TooManyMethods \u2014 62 methods. The bar is 30 methods; this is 32 over it, 2.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e73cddccd5338e53f257b298819ebf3c93e7627cfae3c416aa9dab80263ebd6"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: json/JsonExpressionEvalUtils.scala: FileTooLong \u2014 1017 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 517 over it, 2.03\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c27affaafb814cdf3d0cc17e06d12d06347940e3ab36ff9eb327e1115d717a3"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkDateTimeUtils: TooManyMethods \u2014 61 methods. The bar is 30 methods; this is 31 over it, 2.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ad117bcc23529c3bd84e4b1e9ca09a3c0fbc71253f14187ceb873bcc750c418"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/ScalaUDF.scala: FileTooLong \u2014 1015 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 515 over it, 2.03\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7fd6a4012867eb4e3cdb3fac7af4789884c8922816dfa2b192b5af36c2100f80"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/MapOutputTracker.scala: FileTooLong \u2014 1006 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 506 over it, 2.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e52fda562eb848ab1225cabc4ab6882d9642ecbe41d12eabe6715cad47bca679"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/Dataset.scala: FileTooLong \u2014 1003 significant lines (blank, comment-only and punctuation-only lines excluded), about 93% of them inside a single declaration: Dataset (140-1701). The bar is 500 significant lines; this is 503 over it, 2.01\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c953d8123b688a068a487bdc6b3746d0746b1dec4231c40222c8ea33681e3d1"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkContext: TooManyMethods \u2014 60 methods. The bar is 30 methods; this is 30 over it, 2.00\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/context.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1de63a48daa687e7706eb2f062ee97d2d3bff7db29062fcce608e7496ccc32a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Catalog: TooManyMethods \u2014 60 methods. The bar is 30 methods; this is 30 over it, 2.00\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalog/Catalog.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"75c9e717c7f7348b44c7c6f45721e7819112a9bc275095a1a193f89cc5fad045"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: UnsafeArrayData: TooManyMethods \u2014 60 methods. The bar is 30 methods; this is 30 over it, 2.00\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ecc7d082507a5d865f7dbbf16b3f38fcee809aa97f8a6b581325acc7f68e38e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/SparkSqlParser.scala: FileTooLong \u2014 999 significant lines (blank, comment-only and punctuation-only lines excluded), about 90% of them inside a single declaration: SparkSqlAstBuilder (238-1785). The bar is 500 significant lines; this is 499 over it, 2.00\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7fbaa6e867936406692e82fde0a8a969162b93c8f8f8bf1c2045388988be8264"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ParquetFilters: ClassTooLong \u2014 798 significant lines (blank, comment-only and punctuation-only lines excluded), 27 methods. The bar is 400 significant lines; this is 398 over it, 2.00\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6ed2835168161df40ee1cb859628a690429788cd57a01fb62dd37fb6ae0aac2"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SparkStrategies: ClassTooLong \u2014 796 significant lines (blank, comment-only and punctuation-only lines excluded), 2 methods. The bar is 400 significant lines; this is 396 over it, 1.99\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"13f0743e2a081779346b8884823ac08470fcd2690466acd3d1ae7dfe00efa820"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: CollationFactory: ClassTooLong \u2014 792 significant lines (blank, comment-only and punctuation-only lines excluded), 21 methods. The bar is 400 significant lines; this is 392 over it, 1.98\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e7341728bf98994464d26481020ff7c5302497a24ef86378d8327ccc65315fd"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: master/Master.scala: FileTooLong \u2014 986 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: securityMgr (54-1465). The bar is 500 significant lines; this is 486 over it, 1.97\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f46df7d64af959aafc9b0e16443206db0141f2633e9750ecd2ac09e4d5fb5ca2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CollationAwareUTF8String: TooManyMethods \u2014 59 methods. The bar is 30 methods; this is 29 over it, 1.97\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"581b446c698fab747e928ebd5e15180cc4c1b67a662203c36f98de065b884036"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: NativeLibrary: TooManyMethods \u2014 59 methods. The bar is 30 methods; this is 29 over it, 1.97\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2e55ef42ed6f88ed8a8a43e554c4ddb0aec53084713b43038c9acd0115e2c0f"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: CollationAwareUTF8String: ClassTooLong \u2014 783 significant lines (blank, comment-only and punctuation-only lines excluded), 59 methods. The bar is 400 significant lines; this is 383 over it, 1.96\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f205972d04e8764286eff045969d70a06e385d7109be263bbea58bc166a8cf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: python/PythonMLLibAPI.scala: FileTooLong \u2014 974 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 474 over it, 1.95\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a0d20f93ff18790dace485c8716679f1c1e5e2c88742564be9cbcfed62a9ebb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: client/HiveClientImpl.scala: FileTooLong \u2014 971 significant lines (blank, comment-only and punctuation-only lines excluded), about 68% of them inside a single declaration: clientLoader (107-1148). The bar is 500 significant lines; this is 471 over it, 1.94\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"634f106da7f0e3a14b298d1af61456079e494c6f9f1bc7bd0270e70e3bd0a20c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ffi/NativeDataSource.scala: FileTooLong \u2014 967 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 467 over it, 1.93\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ce89e43a75702a7d6f9a694d7cc5015b70b5d03a7e5ea239785108335fff7e1"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: HiveSessionImpl: TooManyMethods \u2014 58 methods. The bar is 30 methods; this is 28 over it, 1.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"1201092443fac56eb08a1295f554fe6e1958ce3933d48745a5d7780cd663dffc"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaPairDStream: TooManyMethods \u2014 58 methods. The bar is 30 methods; this is 28 over it, 1.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8183b736d6d18da6c0ee7b8cf00998f1387ac0228368772cfdbb6cdf5961c3d"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: HiveInspectors.wrapperFor: MethodTooLong \u2014 wrapperFor runs 193 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 93 over it, 1.93\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"345c97c07eda365357363ca454c47e32dbc14cfd24b02198fe7866fe7685020b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: physical/partitioning.scala: FileTooLong \u2014 953 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 453 over it, 1.91\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"69f1d7b5237339e9df1aa99e1cb9816357243e305dce1547bf3aa544974336f2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RandomRDDs: TooManyMethods \u2014 57 methods. The bar is 30 methods; this is 27 over it, 1.90\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDs.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ab88abace9597acb3b39eb9a46c32e836bea9aa7259155c0caa99b9b9cfa97e"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: GroupBy: TooManyMethods \u2014 57 methods. The bar is 30 methods; this is 27 over it, 1.90\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6f30c23dd2a6d3d07fbf93e19c77280a274ddd0a43c4a47d19b14e5b09bd39c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/predicates.scala: FileTooLong \u2014 950 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 450 over it, 1.90\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f1cc5c9ccc722fc94ab125cac25f57d28e3acef47728f29719041feee1592a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: recommendation/ALS.scala: FileTooLong \u2014 948 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 448 over it, 1.90\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8840ab80f28ab97224678f89e3c9938952d58532fcb8ef5039e4078815286d5d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/clustering.py: FileTooLong \u2014 948 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 448 over it, 1.90\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/clustering.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f27c0ff4fdd76961d7e9281d06c140f9f491f0112ef694598af81a6b9475efb9"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/hash.scala: FileTooLong \u2014 947 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 447 over it, 1.89\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"12f2777beec431c3477eb936674617d408baea110928246b80b4357e921970ca"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: storage/ShuffleBlockFetcherIterator.scala: FileTooLong \u2014 943 significant lines (blank, comment-only and punctuation-only lines excluded), about 81% of them inside a single declaration: ShuffleBlockFetcherIterator (86-1344). The bar is 500 significant lines; this is 443 over it, 1.89\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b76fbe47db11dfdaaa2d70ef45f9ba0e578009694c508b7f2e51f5e12a8641c5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/session.py: FileTooLong \u2014 941 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 441 over it, 1.88\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bebc80b7503080f143a251db1a57681515860a8642e4030407782606eae3ca0f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classification/LogisticRegression.scala: FileTooLong \u2014 934 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 434 over it, 1.87\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"911333fbc1b5d0e61b7934ed5b71b567cbf710e55da0efc938d48b0ffc0e3ab2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DStream: TooManyMethods \u2014 56 methods. The bar is 30 methods; this is 26 over it, 1.87\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f9e679275087f0f0b477f5a60eeaa297c9a7e0a63a19d8a6c99260e90efec7c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: executor/Executor.scala: FileTooLong \u2014 930 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 430 over it, 1.86\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b67077547a4e0af6facc4ac5a712849b3221c7cf3939e5effcbb04fcc2b5dafc"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/session.py: FileTooLong \u2014 928 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 428 over it, 1.86\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"42e07be44a180457caad798660bc6adaffc1b987294156dd64aa59bd52d7141a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: xml/StaxXmlParser.scala: FileTooLong \u2014 925 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 425 over it, 1.85\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4d339b6dd524dbee1fb3f16e056ad11a99f89d7451ad3c3ecadcdb80f88c2e2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSession: TooManyMethods \u2014 55 methods. The bar is 30 methods; this is 25 over it, 1.83\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/SparkSession.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"286bdebb12e21c91da74854a5524a15da2c00ba3542f492e0c65098c3300140d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/basicPhysicalOperators.scala: FileTooLong \u2014 910 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 410 over it, 1.82\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd118069e3ea83584bb03c5c5343bec06a5cf4db181c5d7587a45a1fb5475287"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: hive/HiveExternalCatalog.scala: FileTooLong \u2014 909 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 409 over it, 1.82\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab103580e6bb95b36dbe9314dd13539fb7a6630221167eefe617ecbad96382be"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: status/AppStatusListener.scala: FileTooLong \u2014 905 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 405 over it, 1.81\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f3429d262106289f8a81c6492c1522fe09518e271c60522f9c5b43ec4f77e87"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: indexes/base.py: FileTooLong \u2014 904 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 404 over it, 1.81\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"41f1fef1276c5bd7813f0306d554a89b135df459ef25dbf41606fad83c8db31d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ShuffleReadMetrics: TooManyMethods \u2014 54 methods. The bar is 30 methods; this is 24 over it, 1.80\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ShuffleReadMetrics.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"acfdd2f82a8d49c175242816bb069ebed5c7f6137392abbc15dfac79ae19798f"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: HiveInspectors: TooManyMethods \u2014 54 methods. The bar is 30 methods; this is 24 over it, 1.80\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"e85ffb2db355e52df0b1822eab75427fb1375ecc6a3fdc8d55a88823f9e27a54"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: StagePage.makeTimeline: MethodTooLong \u2014 makeTimeline runs 180 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 80 over it, 1.80\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a305be8b9006051c5888cbc54df2d3ce2a7f4126978770bd526d954778fd7a3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: optimizer/expressions.scala: FileTooLong \u2014 899 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 399 over it, 1.80\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf7385b37bc6c88b9d8426f5cad9fd83721040d90534a3ca876fc8f6be9709fa"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: rdd/RDD.scala: FileTooLong \u2014 894 significant lines (blank, comment-only and punctuation-only lines excluded), about 93% of them inside a single declaration: RDD (84-2223). The bar is 500 significant lines; this is 394 over it, 1.79\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"78237b98b145f4a27bf7c1f4f56a2403b8a05d27675df349c437af99f20611ba"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/HDFSBackedStateStoreProvider.scala: FileTooLong \u2014 891 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 391 over it, 1.78\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5bbdedcecdd0946656c81bb4c8b293150a400e941bc56149bbb738fe7021204b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: aggregate/HashAggregateExec.scala: FileTooLong \u2014 890 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 390 over it, 1.78\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2da9d2c13ae88d7624a32c2ee55b5c423d99cf5a51474bc4f31c30d6699de36"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: StringMethods: TooManyMethods \u2014 53 methods. The bar is 30 methods; this is 23 over it, 1.77\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/strings.py"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"0578558d1688d66d8bac39617bb6791fa3f5f25a2aae5b113426147c01aa9e43"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VectorizedRleValuesReader: TooManyMethods \u2014 53 methods. The bar is 30 methods; this is 23 over it, 1.77\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"916b0def8711f1afdff61f8f6524ff57abd1d35a94d2eea71b8d5691dd82e09c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/readwriter.py: FileTooLong \u2014 880 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 380 over it, 1.76\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2067f427b52f943b39d290de52eb9d52591109b150f5cd3f00268d004ac59f3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: autocdc/Scd2BatchProcessor.scala: FileTooLong \u2014 879 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 379 over it, 1.76\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7bd870be97bf368fd8c00915c0806f6f0a3f1c2e4d1c1efb3d8a7f49646ea0a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: scheduler/TaskSetManager.scala: FileTooLong \u2014 874 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: taskSet (59-1536). The bar is 500 significant lines; this is 374 over it, 1.75\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d21cfa7951934a0223692e6fcc5312c9be8f7dc8e61afc8403e1cc6f9512e29c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Frame: TooManyMethods \u2014 52 methods. The bar is 30 methods; this is 22 over it, 1.73\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f95a896374c05c96cc923c717e318b8665eef12224437ec5db0c7c888867200"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSession: TooManyMethods \u2014 52 methods. The bar is 30 methods; this is 22 over it, 1.73\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5dcdbd1e718b6af80d7d36a4f2569ef46a668bdf4d9ef18f981e4d5fe028252"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/__init__.py: FileTooLong \u2014 865 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 365 over it, 1.73\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/__init__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"efb1489add0ece9692259fd6a9300be03e8fc70160b8b64cc6804556314231de"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/CheckAnalysis.scala: FileTooLong \u2014 864 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 364 over it, 1.73\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"13e76df574143c700efdf3de4383efad769b40c18449f4deb595fb96cde353e6"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: v2/V2ScanRelationPushDown.scala: FileTooLong \u2014 862 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 362 over it, 1.72\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a89cd7ccac66741bfd5d149bab244b584d5c5f8b19232d62af603aa9689a9a1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: k8s/Config.scala: FileTooLong \u2014 857 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 357 over it, 1.71\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/Config.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c63b019c779854a5de1dbcb93bfc269b266ebb53092f24610fcdb2be59a49232"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: command/tables.scala: FileTooLong \u2014 857 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 357 over it, 1.71\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d4a575c910df11926f8275724b0a84aaab6cd61506581a4b075a79bb98e6c84"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ExpressionConversions: TooManyMethods \u2014 51 methods. The bar is 30 methods; this is 21 over it, 1.70\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"806f73ff994e8dfd90d7e4611c71c010d65dfa47991e6b4285e55c5960cc4cda"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: PairDStreamFunctions: TooManyMethods \u2014 51 methods. The bar is 30 methods; this is 21 over it, 1.70\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"44fdcf78b1627ba4c47cb615925c2f6544bb503a571d3ebe54d92ace0d3de260"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: regression/GeneralizedLinearRegression.scala: FileTooLong \u2014 849 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 349 over it, 1.70\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c75b374a698c20ef55c79e81d065974bb4e3e3543b4cdc3c952399d524e5cadf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: variant/VariantBuilder.java: FileTooLong \u2014 844 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: VariantBuilder (43-1304). The bar is 500 significant lines; this is 344 over it, 1.69\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac1e5a70caa942de1383a88da616d664f8e09233eca5305354d5371812e10387"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: streaming/readwriter.py: FileTooLong \u2014 841 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 341 over it, 1.68\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0d2f78625a0b8030e2110bcb5f9634bc00883de2f829783883241ae104381df"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/SparkStrategies.scala: FileTooLong \u2014 838 significant lines (blank, comment-only and punctuation-only lines excluded), about 95% of them inside a single declaration: SparkStrategies (77-1293). The bar is 500 significant lines; this is 338 over it, 1.68\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f56937ac11fb7a5ab577ef83fa918fc72b7e52eabf729aa7d7980900ccd16560"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaUtils: TooManyMethods \u2014 50 methods. The bar is 30 methods; this is 20 over it, 1.67\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"e396de5d6d3f5b1e037056f207e3306e4632bfd73ec60538fc2b129078c77375"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VariantBuilder: TooManyMethods \u2014 50 methods. The bar is 30 methods; this is 20 over it, 1.67\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c9a970a692fc6280ca366858fddcbf5779b6926773d067ae7b8aac63f984d52"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Builder: TooManyMethods \u2014 50 methods. The bar is 30 methods; this is 20 over it, 1.67\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala"},"region":{"startLine":840}}}],"partialFingerprints":{"codehealthFindingId/v1":"0087a72e06e4d311009ff27a7eaf3f02948120329e2644cc1e6d9209e7be32b0"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: InvalidInputErrors: TooManyMethods \u2014 50 methods. The bar is 30 methods; this is 20 over it, 1.67\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/InvalidInputErrors.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"639adcc27e0e152d69478e6d91d65614ac5ee67e353832dafde50606a8d8ef24"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: TransformWithStateInPySparkStateServer: ClassTooLong \u2014 664 significant lines (blank, comment-only and punctuation-only lines excluded), 13 methods. The bar is 400 significant lines; this is 264 over it, 1.66\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"6eb4a976b9c3b83f6caf3a0d22addb550c4fe9d26ef7c40091f071b65e746982"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: impl/RandomForest.scala: FileTooLong \u2014 829 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 329 over it, 1.66\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7917d8f4bb39673e86170ee6286e5f8cdf769c6c92f3b64728a2855f29222e8d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: jdbc/JdbcUtils.scala: FileTooLong \u2014 829 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 329 over it, 1.66\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d56c175caff85c4e0f1e56fd04d4f70994d5e05c079bf21bb218c4253092b87a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/ParquetFilters.scala: FileTooLong \u2014 827 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: ParquetFilters (55-1320). The bar is 500 significant lines; this is 327 over it, 1.65\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0ba2121eeaf3ded5fe1de86b65ebdd2e0f13b111fb6f4901e9712752edff51d"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: VectorizedRleValuesReader: ClassTooLong \u2014 657 significant lines (blank, comment-only and punctuation-only lines excluded), 53 methods. The bar is 400 significant lines; this is 257 over it, 1.64\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"72eb895bfcd621de63c6624af57fe01d4d25f7f8d05d85f0da03ba16a9488c62"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: trees/TreeNode.scala: FileTooLong \u2014 820 significant lines (blank, comment-only and punctuation-only lines excluded), about 82% of them inside a single declaration: TreeNode (89-1402). The bar is 500 significant lines; this is 320 over it, 1.64\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b70a558a454d32d4ad9561aa30053be1bc468cd3ff02f5b449582f518213146"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: FsHistoryProvider: TooManyMethods \u2014 49 methods. The bar is 30 methods; this is 19 over it, 1.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"0af7626d28283292f88ead3231379c64aa743812d40bc3d2a256a369462825e8"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ResourceImpl: TooManyMethods \u2014 49 methods. The bar is 30 methods; this is 19 over it, 1.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"22fa283034db788a1ea8403aa8db8f1a087900b48ae2ec0cbdbc9910ff46a09d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryPlan: TooManyMethods \u2014 49 methods. The bar is 30 methods; this is 19 over it, 1.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"57840fe81a2ba8a10f13ad564daca9fdc11c281205d649ecb9b6920a1602d1b4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ParseSqlResult: TooManyMethods \u2014 49 methods. The bar is 30 methods; this is 19 over it, 1.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb045ba63e22e174df5b58ef233f37139f77f51083993a72d01aa5e98f68d612"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: StateStoreErrors: TooManyMethods \u2014 49 methods. The bar is 30 methods; this is 19 over it, 1.63\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreErrors.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"730a427b2ca8e0a770de72380b7f45901f112f5d991d6da183642017ade6faa1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/CollationFactory.java: FileTooLong \u2014 811 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: CollationFactory (44-1515). The bar is 500 significant lines; this is 311 over it, 1.62\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d8d66276f9739af484c5c016fbfea6ab5a408bcb57fdb51ad15c60ed7897089"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/CollationAwareUTF8String.java: FileTooLong \u2014 802 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: CollationAwareUTF8String (44-1746). The bar is 500 significant lines; this is 302 over it, 1.60\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a9e8d95c9dfa792a3c05c9001ce20e6c389523cbe25aeb3cab96052761c9dac"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: IndexOpsMixin: TooManyMethods \u2014 48 methods. The bar is 30 methods; this is 18 over it, 1.60\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"e54e34fbbd8d4e6f4183ef1d6fc07961bb3a645812e42d4f284f9a50e04b4e1a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DStream: TooManyMethods \u2014 48 methods. The bar is 30 methods; this is 18 over it, 1.60\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/dstream.py"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"c29507d5119f64f479c299c530259c02c84fdfd413a3e9410a2e54b2a86ca9a6"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: ProtobufDeserializer.newWriter: MethodTooLong \u2014 newWriter runs 159 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 59 over it, 1.59\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a25cc12886d98ce70c65ca1477ae9fc3e8845b7f037f68d769d7fb33854a267"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/transpile.py: FileTooLong \u2014 794 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 294 over it, 1.59\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cdd7d722a6b9f4124657f12ca31452f86ffecbd0803739a0757be52b1d408df"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: BytesToBytesMap: ClassTooLong \u2014 633 significant lines (blank, comment-only and punctuation-only lines excluded), 32 methods. The bar is 400 significant lines; this is 233 over it, 1.58\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"f816b0afdbd54eb82efe213dcdba48f6bea340807546e52d0ccea49ddd28bf51"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: deploy/SparkSubmit.scala: FileTooLong \u2014 788 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 288 over it, 1.58\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbdcbbc41edc08176e331e0b3dd87b980d3de58a0cad6269ab9afae5fc989ade"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: client/SparkConnectClient.scala: FileTooLong \u2014 786 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 286 over it, 1.57\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c773370219b15d8029a3a3a224b380edb0c84c23494210294bddc442927b30f4"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: adaptive/AdaptiveSparkPlanExec.scala: FileTooLong \u2014 786 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 286 over it, 1.57\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"845c99dc00b53ed554f1c2f18928ff94dd4e1f96c7b2075eeca565a5d15be1d5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSession: TooManyMethods \u2014 47 methods. The bar is 30 methods; this is 17 over it, 1.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a09a004707c57662231c8765ca86976b1e8854c6b9604a010fbce8263a93d4c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Decimal: TooManyMethods \u2014 47 methods. The bar is 30 methods; this is 17 over it, 1.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"d91ce1b1b6522cdb8317941629ab4dc34835e96b32d3010f97e1590a95e7acbd"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: UdfUtils: TooManyMethods \u2014 47 methods. The bar is 30 methods; this is 17 over it, 1.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a5aadcf52fa144c89cc040a6e5fb3ab4e7c5f3dae1307c4a2196f9ebddb536a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JdbcUtils: TooManyMethods \u2014 47 methods. The bar is 30 methods; this is 17 over it, 1.57\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"158fc1821707a2315ad2f0c2a7e623260b5d2ef43ca18a8d88a5356933f18dda"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/RocksDBFileManager.scala: FileTooLong \u2014 783 significant lines (blank, comment-only and punctuation-only lines excluded), about 77% of them inside a single declaration: RocksDBFileManager (130-1154). The bar is 500 significant lines; this is 283 over it, 1.57\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"61bdd752a7a1fa70faf48c6eb2bc58151bada7b4199b0defc81e83f467c00dea"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: static/stagepage.js: FileTooLong \u2014 779 significant lines (blank, comment-only and punctuation-only lines excluded; the length bar is tripled for a single-responsibility module of 4 or fewer top-level units), about 73% of them inside a single declaration: executorSummaryTableSelector (341-1161). The bar is 500 significant lines; this is 279 over it, 1.56\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5b003d45eef9092bfc9e23349915bfcb22f7eab8ee49f879ccd9a78ea57df50"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: BlockManagerMasterEndpoint: ClassTooLong \u2014 619 significant lines (blank, comment-only and punctuation-only lines excluded), 31 methods. The bar is 400 significant lines; this is 219 over it, 1.55\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"7642b34cbc8dd2ed0af8eba2ae8cf4e50e0920f0756e928cce1e001726600012"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/complexTypeCreator.scala: FileTooLong \u2014 770 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 270 over it, 1.54\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fddf160266ce9c990b83f5f468a568fd68375e391df6a7e0699e4b1da38b769"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/timeExpressions.scala: FileTooLong \u2014 770 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 270 over it, 1.54\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7146a0c9707b99b8536ba474936e077ce0616ece00e936e81f8e3800577557d1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: v2/DataSourceV2Strategy.scala: FileTooLong \u2014 769 significant lines (blank, comment-only and punctuation-only lines excluded), about 79% of them inside a single declaration: DataSourceV2Strategy (62-964). The bar is 500 significant lines; this is 269 over it, 1.54\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"126b7b32992c8cf839282f7972734d12c50e57703e84c85bd7d1fd47f5e56629"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: cloudpickle/cloudpickle.py: FileTooLong \u2014 768 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 268 over it, 1.54\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c5030d0c90d5986fe84da8478a0a4b36a0f4ebfedc540104cae5dd21228acd5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ImplicitOperators: TooManyMethods \u2014 46 methods. The bar is 30 methods; this is 16 over it, 1.53\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaf47b078a1277a39a5b54cde559dce0cc1a4c44399d44298124bab2394ccc09"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSession: TooManyMethods \u2014 46 methods. The bar is 30 methods; this is 16 over it, 1.53\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SparkSession.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"7aa2571283cbc78cc00e6fb03418cb4f713b510e1a4943e68c4465ecc12297eb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: errors/QueryParsingErrors.scala: FileTooLong \u2014 765 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 265 over it, 1.53\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cb5996322155561461d3ce05e7844d3ed78f5cd2b4b3f8c8750adc1ce06c4f5"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: RocksDBFileManager: ClassTooLong \u2014 604 significant lines (blank, comment-only and punctuation-only lines excluded), 38 methods. The bar is 400 significant lines; this is 204 over it, 1.51\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"83d353d28dcfe1d213e9dd2b2941796645b1369bfc3c3bbdfbbf7055a7716b14"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: joins/RangeRelation.scala: FileTooLong \u2014 755 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 255 over it, 1.51\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"68fc4d00097b152ebda8a8a8c5b3b37a4bf31cfc15530fb63c7d83dc615c9e43"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: status/LiveEntity.scala: FileTooLong \u2014 754 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 254 over it, 1.51\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/LiveEntity.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba396df60a6d9df419c14173796e6ee93da1f6cb2cdc74f9331b77724c194793"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ExpressionResolver: ClassTooLong \u2014 600 significant lines (blank, comment-only and punctuation-only lines excluded), 62 methods. The bar is 400 significant lines; this is 200 over it, 1.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ExpressionResolver.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"10180ab07ec047051257e52973d851f58938e276ab725b7d42598d929758377d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TaskSchedulerImpl: TooManyMethods \u2014 45 methods. The bar is 30 methods; this is 15 over it, 1.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"f39601f3b17a6559b92586333f3efda47cd949c44c82c0c7d921b26a1cad9c11"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Encoders: TooManyMethods \u2014 45 methods. The bar is 30 methods; this is 15 over it, 1.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Encoders.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7a67f56f00d660a1be65bb911b4b8718b87a754212e0bc01785ba643e15483c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: XXH3: TooManyMethods \u2014 45 methods. The bar is 30 methods; this is 15 over it, 1.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"857c3fe2d27af90d37b643313458c75b99b86f3e220d476180faa5c5a21ef6fa"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkConnectClient: TooManyMethods \u2014 45 methods. The bar is 30 methods; this is 15 over it, 1.50\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"18b0f8b3b81e986c64badc3d9edc5e741929f7296f585c840d80990626b045ba"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VectorizedPlainValuesReader: TooManyMethods \u2014 45 methods. The bar is 30 methods; this is 15 over it, 1.50\u00D7 the bar. Most of these members implement parquet.VectorizedValuesReader (35 of 44 members), so moving them onto a smaller type would remove them from that contract rather than reduce it. To reduce it, split the contract instead: give each cohesive group of operations its own smaller interface and its own implementing type. Where the contract has to stay whole, move the work behind these members into collaborator types, so what is left here is a forward per member rather than a responsibility per member."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"be33339721cc00cad52737e639c3bac219b696b3021c60fb26b534e4699ca42e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: storage/BlockManagerMasterEndpoint.scala: FileTooLong \u2014 750 significant lines (blank, comment-only and punctuation-only lines excluded), about 83% of them inside a single declaration: BlockManagerMasterEndpoint (50-1136). The bar is 500 significant lines; this is 250 over it, 1.50\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed96a66ff343a40ea96d19feac10e65c4380b04fbc81424bc88913ada914a44c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/internal.py: FileTooLong \u2014 750 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 250 over it, 1.50\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9df6e6820da3123c7c91963645184a51a58e5554baf81a5af2f28ffa5d4c51d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: scheduler/TaskSchedulerImpl.scala: FileTooLong \u2014 748 significant lines (blank, comment-only and punctuation-only lines excluded), about 88% of them inside a single declaration: sc (84-1288). The bar is 500 significant lines; this is 248 over it, 1.50\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f39bdf27066db4380f47fe899b33cceba9aba0389353a805d7f2456826473cdc"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: HiveSessionImpl: ClassTooLong \u2014 596 significant lines (blank, comment-only and punctuation-only lines excluded), 58 methods. The bar is 400 significant lines; this is 196 over it, 1.49\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ce4a7a1684551e2b879897cecf35c77a5ded702b2266767e49ad7eac62b14f3"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: ParquetVectorUpdaterFactory.getUpdater: MethodTooLong \u2014 getUpdater runs 149 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 49 over it, 1.49\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd9c0456e45e4f01461c84bed9b1b01186d994f36b866f55a24db220229a7106"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/__init__.py: FileTooLong \u2014 742 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 242 over it, 1.48\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a26c87a83b7eeadd6a5dda47fe490f35f3a485a9760467542c4ffa922026ae2f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: v2/WriteToDataSourceV2Exec.scala: FileTooLong \u2014 739 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 239 over it, 1.48\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"005b791ce5e24db04d65d8b5c908f3525ae1cce831226d2bbff6147c829f369f"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: JacksonParser: ClassTooLong \u2014 590 significant lines (blank, comment-only and punctuation-only lines excluded), 20 methods. The bar is 400 significant lines; this is 190 over it, 1.48\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"07209169c4c35224038b1b6c68f5a010113017162888155796f78668dadfdaab"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: static/spark-sql-viz.js: FileTooLong \u2014 734 significant lines (blank, comment-only and punctuation-only lines excluded; the length bar is tripled for a single-responsibility module of 4 or fewer top-level units). The bar is 500 significant lines; this is 234 over it, 1.47\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"818bec359307bdf9c28892a6ad675d9f0d7a0a4b2fb34d7a2c890a3b9131f858"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: KeyValueGroupedDataset: TooManyMethods \u2014 44 methods. The bar is 30 methods; this is 14 over it, 1.47\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9d61a371a8a678c8db4bd17e2072ab76fd88c971632b64e0d6b1e373d37ceb3"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CatalogV2Util: TooManyMethods \u2014 44 methods. The bar is 30 methods; this is 14 over it, 1.47\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"31d1fa88d96976ed7a085cb01d48a4ad504f10221503cd7b218c8d9b1e03c210"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryExecution: TooManyMethods \u2014 44 methods. The bar is 30 methods; this is 14 over it, 1.47\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/QueryExecution.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"88f1c160a1cdcbb5a4327e4310085f9ed29fbc5933252640d99676b73ee47383"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/util.py: FileTooLong \u2014 730 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 230 over it, 1.46\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e39bb9303b82a7c587710d3a320dc2befe5578df6b61e2bc1fe31c022e65328"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/utils.py: FileTooLong \u2014 729 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 229 over it, 1.46\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eefac6aadeb223a7e7314d6a191b16cc5b6cf699c2b648dfc5c9350c208307ff"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parser/ParseSqlResult.scala: FileTooLong \u2014 725 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 225 over it, 1.45\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"efacb3a6dc180518351ce7eed77487418c492ee5e475c335252ad9fe7cfbb5b1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: joins/SortMergeAsOfJoinExec.scala: FileTooLong \u2014 725 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 225 over it, 1.45\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeAsOfJoinExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"50632b37b2ff2e649a2e40518f32072daa7068b6a63267cc2eb24ea40ccca8f8"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: ColumnNodeToProtoConverter.apply: MethodTooLong \u2014 apply runs 145 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 45 over it, 1.45\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b397b094c4a40f92f36105d77b077421402354afbd1ce11ddb16586751e642f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: eval_handlers/_udtf.py: FileTooLong \u2014 718 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 218 over it, 1.44\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_udtf.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"faa89738a27d4cea39e2a87ecc418beb3d64d8a6ebe8fb2fc3c8df1f0766bd17"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: V2ExpressionSQLBuilder: TooManyMethods \u2014 43 methods. The bar is 30 methods; this is 13 over it, 1.43\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"324184086a595dcfa7a9ca430f07f216f2bba74ba2e280d9c2214fc9bef1eac4"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ThriftCLIService: TooManyMethods \u2014 43 methods. The bar is 30 methods; this is 13 over it, 1.43\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"c44d388a0534010ff672598e344b1a79208404da92bbbee54b19d0f02d24c712"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: catalog/interface.scala: FileTooLong \u2014 715 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 215 over it, 1.43\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9595e60b2f173d74c59d93a28dbf045afabc9e2f71cb81ea38de4e2012bd86a3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/conversion.py: FileTooLong \u2014 710 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 210 over it, 1.42\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b1d89b2f0c60c7edb05626954a916fcb7bc2ddd304a68bd744b679b6aaefff4"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: streaming/TransformWithStateInPySparkStateServer.scala: FileTooLong \u2014 709 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: TransformWithStateInPySparkStateServer (62-980). The bar is 500 significant lines; this is 209 over it, 1.42\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"edce17baabe57b785ca2ba6996a4655ca436751d2129809840ffc25217c16476"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: command/ddl.scala: FileTooLong \u2014 701 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 201 over it, 1.40\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"231501cdcda8794d142a6ab6312b85c616043f2aeb7a42252c9ade2145fcb1ed"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CLIService: TooManyMethods \u2014 42 methods. The bar is 30 methods; this is 12 over it, 1.40\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/CLIService.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"605202a4e5e62c090bef2fb0918e482f861f8730d14fd99e9ec643df26f16d4c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Operation: TooManyMethods \u2014 42 methods. The bar is 30 methods; this is 12 over it, 1.40\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/Operation.java"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"460e386d988cb0e7a6a72a6aa59499ad4a370e90625428c28e85e62ff12f9fc0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: worker/Worker.scala: FileTooLong \u2014 699 significant lines (blank, comment-only and punctuation-only lines excluded), about 86% of them inside a single declaration: conf (60-982). The bar is 500 significant lines; this is 199 over it, 1.40\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c6eeddb96828a37221dd4c177bec694423275c43c6927acd9f9ae3f66956c01"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/Matrices.scala: FileTooLong \u2014 698 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 198 over it, 1.40\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"84a5da179e2ca189bc7c1c5ebd9bacd22f580b57ff44878b4233673c543c4865"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/windowExpressions.scala: FileTooLong \u2014 695 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 195 over it, 1.39\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ea01ed86228fddac270de904247065f95a685fe18f95dc911d16314bd219e56"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sparktestsupport/modules.py: FileTooLong \u2014 694 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 194 over it, 1.39\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/sparktestsupport/modules.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c8dd8e9e6aec3605123c554506dbaf1849b911bd2f5c9d36750f2693a134ac8"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: LateMaterializationParquetRecordReader: ClassTooLong \u2014 551 significant lines (blank, comment-only and punctuation-only lines excluded), 35 methods. The bar is 400 significant lines; this is 151 over it, 1.38\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fdacb415ab2da046a680056f0b8e95ddd287a4199f8e1361595faebaa8446ce"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: CollationSupport: ClassTooLong \u2014 550 significant lines (blank, comment-only and punctuation-only lines excluded), 5 methods. The bar is 400 significant lines; this is 150 over it, 1.38\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"c065f8c2544e697fab05140c3b6e9212c18e8f81d200f80a55d27adb8fc77e9c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: AppStatusStore: TooManyMethods \u2014 41 methods. The bar is 30 methods; this is 11 over it, 1.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusStore.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc5d32e95147a5e9588c16b6f7f3ad4b9991c4cac14b7443cc1e8cf53798c13d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataTypeErrors: TooManyMethods \u2014 41 methods. The bar is 30 methods; this is 11 over it, 1.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrors.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"19a6b7a615ee12389304e2c74ee978f870737926daa68277b79e993e908940f5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DslLogicalPlan: TooManyMethods \u2014 41 methods. The bar is 30 methods; this is 11 over it, 1.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"4279267138a1ed840c4fe73c28662c82b8a41fdd77e86422dfb52948e0eb665b"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ConstantColumnVector: TooManyMethods \u2014 41 methods. The bar is 30 methods; this is 11 over it, 1.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ConstantColumnVector.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"64e1f7bd3a1f1087f06920ce0c7a0b01ac8bf85fb381a633e8269b693afb239b"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: StreamingContext: TooManyMethods \u2014 41 methods. The bar is 30 methods; this is 11 over it, 1.37\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"770808ba9f4823c0b8d00736d6a8e11093359933ae24c77c212d6099960e334e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: static/executorspage.js: FileTooLong \u2014 683 significant lines (blank, comment-only and punctuation-only lines excluded; the length bar is tripled for a single-responsibility module of 4 or fewer top-level units). The bar is 500 significant lines; this is 183 over it, 1.37\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9faf72031c919217b73a0d2b343691b4492a8f40380272bb4a2efcd8d24dc17b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/Expression.scala: FileTooLong \u2014 680 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 180 over it, 1.36\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a906b752cfd1606ef95b7cf8ac6919beef93cd0946e295b17c75b6a98d13979"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/DateTimeUtils.scala: FileTooLong \u2014 675 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 175 over it, 1.35\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f6fa16d842be99a285deae8e09c34d22c1d7f5b9b36407253168d0b13e93589"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: WritableColumnVector: ClassTooLong \u2014 538 significant lines (blank, comment-only and punctuation-only lines excluded), 111 methods. The bar is 400 significant lines; this is 138 over it, 1.35\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca5a58060eb2210ba716c9aecf069775043933df72639abfb4fff31f01c0d4c9"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/VectorizedRleValuesReader.java: FileTooLong \u2014 670 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: VectorizedRleValuesReader (46-1085). The bar is 500 significant lines; this is 170 over it, 1.34\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8b98d63758f05b434dd23e65958e4d81445a3a25bf0a6dc5b4f18291187dfb3"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SQLExecution.withNewExecutionId0: MethodTooLong \u2014 withNewExecutionId0 runs 134 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 34 over it, 1.34\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"912c2890feb6d7fda065e0c911d90186e2decd393d410591e553516b3ba155f1"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: DataflowGraphTransformer.transformDownNodes: MethodTooLong \u2014 transformDownNodes runs 134 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 34 over it, 1.34\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/DataflowGraphTransformer.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"58c6b0243b76ea6a105299f76c15340b03f781589769e07735119e9bced5a325"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: scripting/SqlScriptingExecutionNode.scala: FileTooLong \u2014 669 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 169 over it, 1.34\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"959bb4d9e9581e3430b723bfa10e7d8bc9c13c79dbb0a2e95e8659fc9fef4d7a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TaskContext: TooManyMethods \u2014 40 methods. The bar is 30 methods; this is 10 over it, 1.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContext.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbfe870634db277081104cf1754a003b1182ad904e15a4d5926a4aa4758d785e"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: UIUtils: TooManyMethods \u2014 40 methods. The bar is 30 methods; this is 10 over it, 1.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ba24b4ca41c37eb1bc11ecba842a0f994be20f019e3748bcf3498e72f7313db"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SerializerBuildHelper: TooManyMethods \u2014 40 methods. The bar is 30 methods; this is 10 over it, 1.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bdad8d65e7dab6c7f40d05aa09fee704b6bc91afe51b985470ff1958ca4ebcd"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CacheManager: TooManyMethods \u2014 40 methods. The bar is 30 methods; this is 10 over it, 1.33\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"efd23be37ea62e3553741ee87c3dd32164c3b0e2c7d0d7486dac4d08054b0adb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/TableOutputResolver.scala: FileTooLong \u2014 666 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 166 over it, 1.33\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d421c49c304334af96fce968f5a31bec4ce6a34211e1a0a38a8e1b5a51f108e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: joins/HashJoin.scala: FileTooLong \u2014 666 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 166 over it, 1.33\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad716e3829a351f4749f1f332a47e1ee9a614536dbcc5a7594e3ae8b76a30348"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: map/BytesToBytesMap.java: FileTooLong \u2014 662 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: BytesToBytesMap (71-1330). The bar is 500 significant lines; this is 162 over it, 1.32\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"84eef176f6dea5e93add00445b0c11cda0c17718d165de92569adfd082c851cc"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: cluster/CoarseGrainedSchedulerBackend.scala: FileTooLong \u2014 659 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: CoarseGrainedSchedulerBackend (56-1299). The bar is 500 significant lines; this is 159 over it, 1.32\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"93166b0260edbf8453d0f4742773dcb945e3a5640a7860fbb69f170e2734014e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: joins/HashedRelation.scala: FileTooLong \u2014 658 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 158 over it, 1.32\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"536d9ae12a5964f985eb754e2be958a96dcd99c58ecbe78ded2d191f6d0333ec"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: session/HiveSessionImpl.java: FileTooLong \u2014 658 significant lines (blank, comment-only and punctuation-only lines excluded), about 91% of them inside a single declaration: HiveSessionImpl (89-943). The bar is 500 significant lines; this is 158 over it, 1.32\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf95e95b15b5d57788fe08b7438c4f243fb638b8031049dd17a5972fa74f70ba"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: jdbc/SparkConnectDatabaseMetaData.scala: FileTooLong \u2014 652 significant lines (blank, comment-only and punctuation-only lines excluded), about 80% of them inside a single declaration: SparkConnectDatabaseMetaData (33-827). The bar is 500 significant lines; this is 152 over it, 1.30\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbc975f7e451a469af3aad05ca6f29ba34b7845da45c7d368a4a083fe6dcbd2d"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: UnsafeExternalSorter: ClassTooLong \u2014 521 significant lines (blank, comment-only and punctuation-only lines excluded), 30 methods. The bar is 400 significant lines; this is 121 over it, 1.30\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc551417d9dbd337091fb61f7dee4aa8f32bcd2e1750fe38623db5022254bd1b"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RemoteBlockPushResolver: TooManyMethods \u2014 39 methods. The bar is 30 methods; this is 9 over it, 1.30\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"017f5b8941fa162052615b91d1f4278ca5cb06b0febb26122cf87a5f18ce9868"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Catalog: TooManyMethods \u2014 39 methods. The bar is 30 methods; this is 9 over it, 1.30\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/catalog.py"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"162a40cdb2e69be762d39eca6fd41ab0b8826b79edd7a3d144b71ef88cfa7160"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: FunctionRegistry: TooManyMethods \u2014 39 methods. The bar is 30 methods; this is 9 over it, 1.30\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"08bd18cd6053e56dfd5a0c5e500e29fdb89162d74dad0d2bca03c86c6f6eef3b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/IntervalUtils.scala: FileTooLong \u2014 650 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 150 over it, 1.30\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"95ca02254f107a0659607206862cbc2d6e3864083c76ef6ae950b5d992e66e3c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: status/AppStatusStore.scala: FileTooLong \u2014 644 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: store (43-848). The bar is 500 significant lines; this is 144 over it, 1.29\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusStore.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b7cda44de656fecbcf526cd12f252b6283ade3458b30d63778bb86785663d78"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/Matrices.scala: FileTooLong \u2014 644 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 144 over it, 1.29\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"098cce747c4bf6ce0ff3e050a79a25c6ddef172595b8eb4ced2847b246282c8f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: streaming/listener.py: FileTooLong \u2014 643 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 143 over it, 1.29\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/listener.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9031baa45540425c3dc40feb31acd374067335af1416ee3edc1e74554dd0b896"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/vectorExpressions.scala: FileTooLong \u2014 640 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 140 over it, 1.28\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"41ff113a3a6153ef324617eb3039cca3e25b9716518fec55fd07103a98323664"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: optimizer/subquery.scala: FileTooLong \u2014 640 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 140 over it, 1.28\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"08b796cc0c8cf5b0576a3b6e73bbe7d80431915e1ce601db31d8331be4e211e0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: exchange/EnsureRequirements.scala: FileTooLong \u2014 640 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 140 over it, 1.28\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"14105533eb317e0f0d85536e23de6cdfd751a90bd0e376f1287ac1cf50d79a04"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/base.py: FileTooLong \u2014 638 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 138 over it, 1.28\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c9ce3260f223dd19675c52d4dda7529d862e0498489fb80d46a28cca21d3ea5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classic/SparkSession.scala: FileTooLong \u2014 637 significant lines (blank, comment-only and punctuation-only lines excluded), about 62% of them inside a single declaration: SparkSession (92-939). The bar is 500 significant lines; this is 137 over it, 1.27\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d827c0f4156d5d682529ed35e778539a8c0cdb2d1ad36cda504a076cebe1548"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TaskMetrics: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/TaskMetrics.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"b152d5ead1d6a6b180760112958c96f10e7ba10d4eb49f73c281f3c11f552d70"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Catalog: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a3d4a6ed63faa16f8357a9a240e00a0493b85314213ff59cd7d54d65f35afb9"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: MathUtils: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/MathUtils.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"22310b9cc467642f95f3884ad151d0b7b928c0ce250b54c4032bc3a3f438c14c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkPlan: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c0ed34ce62d3f4a4fddd9d515a5f1f5337d75eeeb26b2f4685bdcab2cc74593"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: RocksDBFileManager: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fb6f2cf976f4bbb60d90e5d9ebf6504ec47d38082ac04b70a5d06829954cacd"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/WholeStageCodegenExec.scala: FileTooLong \u2014 633 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 133 over it, 1.27\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3511e39aadfe1f17e5d027f51689e3c226dfb5cb1f659347a75abdb7fe61776a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: resolver/ExpressionResolver.scala: FileTooLong \u2014 632 significant lines (blank, comment-only and punctuation-only lines excluded), about 95% of them inside a single declaration: ExpressionResolver (75-1444). The bar is 500 significant lines; this is 132 over it, 1.26\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ExpressionResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b578962d008cba2a3c492eefd36a78252e0400cc1673735eb040b494e9a26d7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/tuning.py: FileTooLong \u2014 631 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 131 over it, 1.26\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d32fedf3831743a827c9bdf13582b728d1e99d89fe11b8d60782aa360640dcbb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: aggregate/collect.scala: FileTooLong \u2014 630 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 130 over it, 1.26\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"25a08fa6efee74e3060e8e6cf9bba0d243380344ee7e462de6d1a62fb339b915"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: streaming/readwriter.py: FileTooLong \u2014 629 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 129 over it, 1.26\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ba854684d6f970ffb82182e260cc2fb92eef78dca9171d4695505822b623a68"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: yarn/ApplicationMaster.scala: FileTooLong \u2014 629 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 129 over it, 1.26\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cff50fda088f85b1ab34809f654cd02bd76d720710d507cddc63f753773dd8c1"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ThriftCLIService: ClassTooLong \u2014 499 significant lines (blank, comment-only and punctuation-only lines excluded), 43 methods. The bar is 400 significant lines; this is 99 over it, 1.25\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"7bddace3798628195060f95fee4f44e6f2818ee3c697971ba980922b9ef2eed7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/DataSourceScanExec.scala: FileTooLong \u2014 623 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 123 over it, 1.25\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a915d1f20ec07f3925b331347ff3abc4ff47260134ddd04df29774888605249"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ArrowColumnVector: ClassTooLong \u2014 498 significant lines (blank, comment-only and punctuation-only lines excluded), 27 methods. The bar is 400 significant lines; this is 98 over it, 1.25\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"9833293a75a4044a385c03c275faf564d24877244b4891d4f97e93cba3373266"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SymmetricHashJoinStateManagerBase: ClassTooLong \u2014 496 significant lines (blank, comment-only and punctuation-only lines excluded), 13 methods. The bar is 400 significant lines; this is 96 over it, 1.24\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":1085}}}],"partialFingerprints":{"codehealthFindingId/v1":"d60b4e8f9e73ef6909dbef9958705b2fd4260031aee5979a7910837eda2f4c32"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/ReadWrite.scala: FileTooLong \u2014 620 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 120 over it, 1.24\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c8eac5c0873add67912492f4ca17e663c8cc01365081a21122c6b73357d4828"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: ParquetFileFormat.buildParquetReader: MethodTooLong \u2014 buildParquetReader runs 124 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 24 over it, 1.24\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7213e37a90445c68864ef71e0a60974133913ad65a6bb51fe022c9970c17a30"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SerDe: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/SerDe.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"580c56442d1b2dfe711ef0b351840c451720e29ffabc296c6457d90de8e6a002"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: MultiIndex: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"31d9885e443c7718632eb34aa32e8d4706d5550e3bdf4f95332893d764c16f39"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSession: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"aead005dd546ab33d935a439e04fdc0705b4c198555efecbcc675120f75b5729"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: YarnAllocator: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"956e175eb0f80147ca1845d0519fea95bbf82d71ac0434dd037f5c024e89877c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Row: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"c753a4b561af8b714f4ba2a68971c48b7cd743140a73db40b8da63d9c91b1d94"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: MutableColumnarRow: TooManyMethods \u2014 37 methods. The bar is 30 methods; this is 7 over it, 1.23\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"10162d3a1db8c53132eb74da25015bee28b10e8a09d4b72f97b5700ce97a2764"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/ParquetRowConverter.scala: FileTooLong \u2014 616 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 116 over it, 1.23\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4092f3f8f0ffddaa2514350923bd4d94c4cebc56f15c6a2292ddf7ec0d45d2c8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: eval_handlers/_arrow.py: FileTooLong \u2014 615 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 115 over it, 1.23\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca78994509d117dee890ee6813c0ce30e515185bc39e7de3168eeee050f9769e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: aggregate/ApproxTopKAggregates.scala: FileTooLong \u2014 614 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 114 over it, 1.23\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f712f7c213f9f1c601ecc63d6f61b3459ad2a1df47378b45bfb8e986a79e80d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: json/JacksonParser.scala: FileTooLong \u2014 614 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: JacksonParser (50-1028). The bar is 500 significant lines; this is 114 over it, 1.23\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa2a7c0d522f21a23dfe7efc4666b1d3de6eed480569ab0f9b24e4c3521e61e5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: eval_handlers/_stateful.py: FileTooLong \u2014 612 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 112 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3965c30c9bb96fbc16b0c6401070f1f197e3f378d06513e1fe33375b078ba5f9"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/unresolved.scala: FileTooLong \u2014 612 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 112 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd4dbcb46a6cf914be228f1f5131c3026df5e6174b2938c631cae5e63d3a1d10"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: logical/object.scala: FileTooLong \u2014 612 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 112 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e353c30c18fa7a3162e3022c08dd2a754b085255bd7f71c24d691d736b512b0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: catalog/CatalogV2Util.scala: FileTooLong \u2014 612 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 112 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9d2917621844683f82283387874d22282e7ec57b3b4882a5025e7f0a445c38a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasources/DataSourceStrategy.scala: FileTooLong \u2014 612 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 112 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"89e20add9c5d2a5db6d6188987b0250612fb0e98d2bc43e6ae755393e09e5efa"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ui/UIUtils.scala: FileTooLong \u2014 610 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 110 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5191c8100a106592610171626dd2392888a214234817d6fe0690b3c7e15dde07"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/intervalExpressions.scala: FileTooLong \u2014 610 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 110 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/intervalExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e9b6566d59b7bf9ef1e06f06d0ce5ebe96ab505f2be8e2d21e6f1f5841f2509"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: LogisticRegression.train: MethodTooLong \u2014 train runs 122 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 22 over it, 1.22\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"c617c4b53986d1277794f951d495cbe6ab476d3c2f3322f91a73f4753cf66469"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SqlStatementSplitter.split: MethodTooLong \u2014 split runs 122 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 22 over it, 1.22\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"22070adbb5330799617c034a916df005f8f06f55adeb10ef08507d6990ecbefa"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: yarn/YarnAllocator.scala: FileTooLong \u2014 609 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 109 over it, 1.22\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"078d0dc0a7384ef906ac5951f37543d634481004435091bf993a35cca0861174"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: join/StreamingSymmetricHashJoinExec.scala: FileTooLong \u2014 603 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 103 over it, 1.21\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0028035490d96535bc38ea950c63d8846f3c86750af6de959d431d75501f9fe"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkFirehoseListener: TooManyMethods \u2014 36 methods. The bar is 30 methods; this is 6 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/SparkFirehoseListener.java"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"f879361693fd60b73ae4a6b338bcb776f075d53a8371e4f2ee36b8d2bee3d712"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaDoubleRDD: TooManyMethods \u2014 36 methods. The bar is 30 methods; this is 6 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"1443c6da7d89bdac066791885aa9f880dd28e8c22f4f12ab7f1ee78b306453fe"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataTypeOps: TooManyMethods \u2014 36 methods. The bar is 30 methods; this is 6 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc6c17f8f425cd9f1a4ac0d1dfca7ff695b443a22e11cc90ada2f9e1aa9104a5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaStreamingContext: TooManyMethods \u2014 36 methods. The bar is 30 methods; this is 6 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e6f4fdf4f0c48838178417f494e0d7123a1087a4b4041f39eda86fe7f2a8d19"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: IncrementalExecution: ClassTooLong \u2014 480 significant lines (blank, comment-only and punctuation-only lines excluded), 5 methods. The bar is 400 significant lines; this is 80 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/IncrementalExecution.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"e89adcf37d76c649b0aeac65502f8591c43ca7c6ad056c14277a62dc186a71e7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/ExecutorAllocationManager.scala: FileTooLong \u2014 600 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 100 over it, 1.20\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ebe1aa0fcc09761a97e72a34345f18df098f68fbe2467c6253409d392572b43"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SqlStatementSplitter.split: MethodTooLong \u2014 split runs 120 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 20 over it, 1.20\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b7bc9a113f0ca954af940218fd56f940d65be0e8850ec3a0ec881ea022cecc6"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: python/PythonRDD.scala: FileTooLong \u2014 599 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 99 over it, 1.20\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee134732aa59f04714e9d2cd5985d8f1a5b53a91803493949daeffaed96a3157"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/variant_utils.py: FileTooLong \u2014 599 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 99 over it, 1.20\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/variant_utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ffef6416557c36fabebf74377dc342d4e3ea139b5526d0d0854b9bd912cb897"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: TaskMemoryManager: ClassTooLong \u2014 479 significant lines (blank, comment-only and punctuation-only lines excluded), 34 methods. The bar is 400 significant lines; this is 79 over it, 1.20\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c37cad7aa4f268131794fe7749ca071a9df701a5959b3e29da91e922627a9d0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/kllExpressions.scala: FileTooLong \u2014 595 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 95 over it, 1.19\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/kllExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"704d7ed2343b7ce38970ee19afc960c138251ac37bc6684a5470b74c6f854d59"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: graph/SqlGraphRegistrationContext.scala: FileTooLong \u2014 595 significant lines (blank, comment-only and punctuation-only lines excluded), about 79% of them inside a single declaration: SqlGraphRegistrationContext (105-797). The bar is 500 significant lines; this is 95 over it, 1.19\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1dc8f3708c6a5fe884c9fedbf559f05c7db1d5c0f7ae9ee78db7e865578a630a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/LateMaterializationParquetRecordReader.java: FileTooLong \u2014 593 significant lines (blank, comment-only and punctuation-only lines excluded), about 93% of them inside a single declaration: LateMaterializationParquetRecordReader (105-1163). The bar is 500 significant lines; this is 93 over it, 1.19\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6050ef9911bfa67c306d86b235610ea349514fd7f7d946875b3078ceca51bd04"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: TypeCoercionHelper: ClassTooLong \u2014 474 significant lines (blank, comment-only and punctuation-only lines excluded), 21 methods. The bar is 400 significant lines; this is 74 over it, 1.19\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4a79add8fca15e76a074a9227131e4d28b39a36e0d091fd73f3598c8cfe5af4"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ui/SparkConnectServerPage.scala: FileTooLong \u2014 592 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 92 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b0a515275557cab80cffb23628059931c0ccbe8c8b127669f75a12fcc1668c3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/SparkShreddingUtils.scala: FileTooLong \u2014 591 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 91 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c78e348ba5e7488ca8b9714d19a01817a0ecb11979b3832123f48ddd95ba5ca"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: plot/matplotlib.py: FileTooLong \u2014 589 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 89 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d9cc86de92f163436f0c23eeb748756a99edde433ae55dff800370b0d462bc0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasources/DataSource.scala: FileTooLong \u2014 589 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 89 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"37f1454dc3528b3096f5d1f728e330dae5c450136804b4bafa6c834ceaad8183"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: protobuf/StageDataWrapperSerializer.scala: FileTooLong \u2014 588 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 88 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9eab74ecfe9db46ec254a0a484d6a3cf037b2fd87d17f2e9a6edbe6cd8c2e9de"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/ClosureCleaner.scala: FileTooLong \u2014 585 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 85 over it, 1.17\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"acf04e4fd44fcc6194eeef0c8f53f5142d6fff1cfbaa9ec51b1e4b9120bf9163"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TaskSetManager: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4c24c4b59802256e38d715489c7abe9abf2a9b440efcdca88ec1607da805d95"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: BLAS: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac5e0ac85907419bc04193f8f912f5f1290db7922b2e7c3d08bfbe44064894e0"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: FunctionResolution: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"42c21eac062fe0d214218260ef6f4694a0c392a0f995fcb02aac0a2a7dffcec1"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: LateMaterializationParquetRecordReader: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"067c4562ce6ff8b67537e93fcd5dc82a5f4b794e632bd17079bdc94a73b00379"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VectorizedByteStreamSplitValuesReader: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedByteStreamSplitValuesReader.java"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"db12981772f824f9a26900e1de662a906e978e79ef9663d498d5729a8cb18285"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VectorizedDeltaBinaryPackedReader: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"228cfe7b967be01f12a77a139b54278f9bfd1b2f972d460dc846ed78ab2e16ce"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: PushDownUtils: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PushDownUtils.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f9dce14100aec388e42cc00e22ecff8f47ba4765f3824548068968851aadd17"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: V2ScanRelationPushDown: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2b2d7afa3d86f99bdf1a428875b792863b713e605610bff0ecbafc1d7e829df"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: xml/XmlInferSchema.scala: FileTooLong \u2014 583 significant lines (blank, comment-only and punctuation-only lines excluded), about 84% of them inside a single declaration: XmlInferSchema (48-857). The bar is 500 significant lines; this is 83 over it, 1.17\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f31497ef7a6d19c504126e4065e5c053451fa21befa34b4f7c3039865a650d34"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SqlStatementSplitter.splitWithPositions: MethodTooLong \u2014 splitWithPositions runs 116 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 16 over it, 1.16\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"576bce29b9376973d13cf6b105dd484bd79219f87d4382250199165036153c30"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: command/views.scala: FileTooLong \u2014 579 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 79 over it, 1.16\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b956cd657d72ad130979ef8153607dc1d1aef35ac1b11361d5a1b3371383fd63"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SymmetricHashJoinStateManagerV4: ClassTooLong \u2014 463 significant lines (blank, comment-only and punctuation-only lines excluded), 6 methods. The bar is 400 significant lines; this is 63 over it, 1.16\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce8b17df88f1dd6e205341e8ca6c7558b79513d2daf4b0cb4f46d3feb3a6bdd8"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SparkConnectResultSet: ClassTooLong \u2014 462 significant lines (blank, comment-only and punctuation-only lines excluded), 2 methods. The bar is 400 significant lines; this is 62 over it, 1.16\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectResultSet.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7cd448058d756007e0924431ed2fc55d1e4ea116a65518c00c83062d9e2e2a3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/Vectors.scala: FileTooLong \u2014 576 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 76 over it, 1.15\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf4b3e6dbad885b5d61b1268e0b53df513d894781501af3a7bcb6db6d7242fea"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sql/udf.py: FileTooLong \u2014 575 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 75 over it, 1.15\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b50ac895e1f74262bc93448e457232a5cc6042bb31519aa9b742c746e4594fcd"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/SparkSession.scala: FileTooLong \u2014 575 significant lines (blank, comment-only and punctuation-only lines excluded), about 60% of them inside a single declaration: SparkSession (81-821). The bar is 500 significant lines; this is 75 over it, 1.15\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SparkSession.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"208a6b6aff55af98e3b15831605143c38448b6ca22da1734882c9780a5a6d0e4"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classic/Catalog.scala: FileTooLong \u2014 575 significant lines (blank, comment-only and punctuation-only lines excluded), about 87% of them inside a single declaration: Catalog (90-1104). The bar is 500 significant lines; this is 75 over it, 1.15\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3db5c15714cbc5c280f108618683002e5b9b6ac6ccb3ae5681d17a668df44c1"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: StreamingV2ScanPushDown.buildScan: MethodTooLong \u2014 buildScan runs 115 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 15 over it, 1.15\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingV2ScanPushDown.scala"},"region":{"startLine":558}}}],"partialFingerprints":{"codehealthFindingId/v1":"041e37c35a7513522fbcebb5891dcb27a67ce1ac97e9bfc337b8cb4260df5456"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/StateDataSource.scala: FileTooLong \u2014 573 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 73 over it, 1.15\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4859f3c3b53a67467c4f53a1315bd7edf90d3dbfbd4d897e4ae5a6bc1fbbdc70"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: resolver/NameScope.scala: FileTooLong \u2014 572 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 72 over it, 1.14\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/NameScope.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d282f3800bb4e2ff56b2bd53d4fe3b3667bccfc100e165083b0acc58a70017e8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: regression/LinearRegression.scala: FileTooLong \u2014 567 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 67 over it, 1.13\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"af21fa815b2d54f1beb7ecf5a06648f1b940a7c3de595e10e6508717c7a1c3ad"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: TaskMemoryManager: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"17400590abb9f34c4f5dd6777d18f424ecc2365302d0d46c99ee17a0be3bc356"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkConf: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkConf.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d5f4b479d54dd2b8a1f404ec96a5e9d0fa21ab6c7c0322420646d61f6b98ebe"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: AppStatusListener: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bdc212d2e5086afe42a93820ed392e237e06cab9db54b6e9860733b9fda39aa"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: StageDataWrapperSerializer: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f6213dacc078c640efe693fbc2a8a45302e60cbd457418efa59596397cc87ea"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ColumnarArray: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarArray.java"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecd5a7b42815089cf6937543b8e6a31e8e45067628c25e407b67f034ce1f4d11"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkSessionExtensions: TooManyMethods \u2014 34 methods. The bar is 30 methods; this is 4 over it, 1.13\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/SparkSessionExtensions.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"20ff3af4c9d9c03f9d50def37af6b600f878bffde67b515bb7140cf8cf70cbed"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: linalg/BLAS.scala: FileTooLong \u2014 566 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 66 over it, 1.13\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"69c8a82d084edb59886f75cf4422c23144296f76f5b545e83514175a1fc55426"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/generators.scala: FileTooLong \u2014 565 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 65 over it, 1.13\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"314b56fc2c508092f1dd2cac1f3e6288b01ed207b1dc97dc8e02148d9f973a6a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/QueryExecution.scala: FileTooLong \u2014 563 significant lines (blank, comment-only and punctuation-only lines excluded), about 67% of them inside a single declaration: QueryExecution (67-761). The bar is 500 significant lines; this is 63 over it, 1.13\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/QueryExecution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"13a606d61436658f29444ec53d4e3e5fca8490bc180f45b73bfbd47fabf08575"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: InMemoryCatalog: ClassTooLong \u2014 449 significant lines (blank, comment-only and punctuation-only lines excluded), 7 methods. The bar is 400 significant lines; this is 49 over it, 1.12\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"b298b3ecd68619714e2bca58e445d0f8f4ac8aae7e71e6ba2742e9bb6c5eafcd"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/local_server_pool.py: FileTooLong \u2014 561 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 61 over it, 1.12\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/local_server_pool.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d2abce7dcf64ca035904abb3b0d2bdcf53d8b33282204ac2236ddbeb5bda8bb"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: InterpretedUnsafeProjection.generateFieldWriter: MethodTooLong \u2014 generateFieldWriter runs 112 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 12 over it, 1.12\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/InterpretedUnsafeProjection.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"4628170b0c0a44761a50b3132aad5eb822d386e54ca9b592cb9c7cca2641ba51"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: vectorized/WritableColumnVector.java: FileTooLong \u2014 559 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: WritableColumnVector (57-1142). The bar is 500 significant lines; this is 59 over it, 1.12\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d3bde8e40f1b24653ea2ed3e75b78a7e299b12200136efbc27c51ca4f09d03d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pyspark/util.py: FileTooLong \u2014 558 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 58 over it, 1.12\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d629cb08b90850529be503a8bd82825bb915716262a837e27772fe84d2858bc1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/TypeCoercionHelper.scala: FileTooLong \u2014 556 significant lines (blank, comment-only and punctuation-only lines excluded), about 85% of them inside a single declaration: TypeCoercionHelper (105-959). The bar is 500 significant lines; this is 56 over it, 1.11\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e68ae7894e2d7bb36080e63816c77cb27ba1b76370f3998a5aeae2a27467373"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/CollationSupport.java: FileTooLong \u2014 555 significant lines (blank, comment-only and punctuation-only lines excluded), about 99% of them inside a single declaration: CollationSupport (31-816). The bar is 500 significant lines; this is 55 over it, 1.11\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"484eb035053847dc52332796c353557b600a36e54918dcc78b68d1b8be313ede"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ml/evaluation.py: FileTooLong \u2014 554 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 54 over it, 1.11\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/evaluation.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b6f63064aa4cfb79a78d185f9a7079aa69c1bf9ae88cf385224dae4a4644b52"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: aggregate/kllAggregates.scala: FileTooLong \u2014 553 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 53 over it, 1.11\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/kllAggregates.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"38992cc9e959c353b1f65b885736381ab7b509ea4a044ae551044c9b2b08a2aa"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CountMinSketchImpl: TooManyMethods \u2014 33 methods. The bar is 30 methods; this is 3 over it, 1.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java"},"region":{"startLine":24}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d847594b6fef1232a62e4ef55bcaaefe8b3188d2b0c4f430d9912d757fe1198"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Master: TooManyMethods \u2014 33 methods. The bar is 30 methods; this is 3 over it, 1.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"882086a2e7b38e5ae6b9656267104814824d2c76f3591114b9ad044f0598a87f"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ColumnVector: TooManyMethods \u2014 33 methods. The bar is 30 methods; this is 3 over it, 1.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnVector.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"41b1a51fb87e0db794d5e423f255c41783174604e3862cf5e93fd4f3a4167313"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Resolver: TooManyMethods \u2014 33 methods. The bar is 30 methods; this is 3 over it, 1.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/Resolver.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"81d0633698d64ec22fb48243ac2dad1bc444c0d5c61b82b5483eff687302ab54"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ColumnDomains: TooManyMethods \u2014 33 methods. The bar is 30 methods; this is 3 over it, 1.10\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb8f33f086bd128c4c642c44229bad1f207cf4f56a7cba7d71bca1621d701cf8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: kafka010/KafkaSourceProvider.scala: FileTooLong \u2014 550 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 50 over it, 1.10\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"59b066b1b2458eb5e3a0477737bdd114e39ad08f7a34b0ac6d505cd27d82900f"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: InjectRuntimeFilter.extractSelectiveFilterOverScan: MethodTooLong \u2014 extractSelectiveFilterOverScan runs 110 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 10 over it, 1.10\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"875439e8760cfa08f0e83f0d395a88443899e32efcdb31b02be12b9322c40676"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: sort/UnsafeExternalSorter.java: FileTooLong \u2014 548 significant lines (blank, comment-only and punctuation-only lines excluded), about 95% of them inside a single declaration: UnsafeExternalSorter (52-1002). The bar is 500 significant lines; this is 48 over it, 1.10\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"42cc9003f6e95f27107aadfbe375f302de8fcdb30ed54d71ae37013e10cc734c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: eval_handlers/_pandas.py: FileTooLong \u2014 547 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 47 over it, 1.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5838b9d2c059ea704bde76877ae6c6a36986160d39ae5c703b4fde71697bc44"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/bitmapExpressions.scala: FileTooLong \u2014 547 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 47 over it, 1.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7c60c9f5243cd0dda8bc4b9b2a5b2f9c101a2a3f5b510a57387a4a3c8cfd22d"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: MLExpressionUtils.scaleShift: MethodTooLong \u2014 scaleShift runs 109 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 9 over it, 1.09\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"268184f0ebd4b3098cab2c384056cc7bde1c8de6b34ea4ba51cdf716afae81b0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/SparkException.scala: FileTooLong \u2014 544 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 44 over it, 1.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/SparkException.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f392961a93de27f80d2409e96c9a895a2836a28a4916f5a654b9f8dd17eb369e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pandas/window.py: FileTooLong \u2014 544 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 44 over it, 1.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"42c1db4e0b5c708af67e725a7057c1862e2814a2de554e41e786c1f4642260c2"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/ParquetSchemaConverter.scala: FileTooLong \u2014 544 significant lines (blank, comment-only and punctuation-only lines excluded), about 62% of them inside a single declaration: ParquetToSparkSchemaConverter (58-607). The bar is 500 significant lines; this is 44 over it, 1.09\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8ca79f25f5c1371241806b790ff35f2343af14614f2cb5969eaebde811498ed"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: connect/KeyValueGroupedDataset.scala: FileTooLong \u2014 543 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 43 over it, 1.09\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/KeyValueGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0de184c579ae2c40ea4182d7d2ec3e33d2fe2a5b716f577bdc7f14b52df8469f"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: V2ExpressionBuilder: ClassTooLong \u2014 434 significant lines (blank, comment-only and punctuation-only lines excluded), 17 methods. The bar is 400 significant lines; this is 34 over it, 1.09\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"06521465d5dfb93692e706f098a95e65598a5447839279bac683a6a634976ac5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/SparkEnv.scala: FileTooLong \u2014 542 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 42 over it, 1.08\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkEnv.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c3aacaafcd353a6a97a57ca6bf15c691eab55076a2f82a6db696dcf45c5e15d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: types/DataType.scala: FileTooLong \u2014 542 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 42 over it, 1.08\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6e1c4767472614eeb634fae0adde3bde6a088fa1e468e66ae527415de01010a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/ParquetFileFormat.scala: FileTooLong \u2014 541 significant lines (blank, comment-only and punctuation-only lines excluded), about 64% of them inside a single declaration: ParquetFileFormat (61-577). The bar is 500 significant lines; this is 41 over it, 1.08\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"34d291a3ef7f1c7341157862171365038bda1eaf9cd68c8afa0709c3e1720a9e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/TimestampFormatter.scala: FileTooLong \u2014 540 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 40 over it, 1.08\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"460c1861a54e2f48c5e0c6fdd24fc99be193269137fdce65a2bd5a2b18df8b1b"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: DAGScheduler.handleJobSubmitted: MethodTooLong \u2014 handleJobSubmitted runs 108 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 8 over it, 1.08\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2619}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e7bdbf4e42c60f11e231310ef885f2497c68024144bc9033c79437f88914af3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: analysis/FunctionResolution.scala: FileTooLong \u2014 539 significant lines (blank, comment-only and punctuation-only lines excluded), about 88% of them inside a single declaration: FunctionResolution (63-915). The bar is 500 significant lines; this is 39 over it, 1.08\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b36e1f6bc362178206fb1705a3fd0ea13add5c8d5b049bde46ed8d3acf1147b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: common/LiteralValueProtoConverter.scala: FileTooLong \u2014 536 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 36 over it, 1.07\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/LiteralValueProtoConverter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b413c6fcdf2b136d7788b1238288f30dbe37e8a6fa6fae6574ad6a81e44efa0e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: compression/compressionSchemes.scala: FileTooLong \u2014 535 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 35 over it, 1.07\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba136b8b39cf6964d73b58e8c4defa3c1605b4fe7e3a3304c06bc7bbc5f43a23"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: VariantUtil: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"108880da5c9c7fb91bff3edd59c205fd954685cd748669fd0dee6cff1d75e344"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: BytesToBytesMap: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"d036190d79b74040d861c0530c3aea5ff13bba034614b06547e33ec24f07a6f0"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CoarseGrainedSchedulerBackend: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"8be40f1d6f55573ba4f28891c031165a325f762eaab8bc7096d0728bd5793ed5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkLauncher: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkLauncher.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"965e3a9e44c7a291dc0b4b878bc258d9ed68b810484d3df607f1b68aaa9d40b0"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ImplicitAttribute: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"5118303de8e5e0c0b68f1129a0b9889dfcb5c6d3749bfbfe6c053a17fabfc247"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JavaDStreamLike: TooManyMethods \u2014 32 methods. The bar is 30 methods; this is 2 over it, 1.07\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"33c859e512156d93dbd01a210143325148010b72ab120d75520cb052e1eb5a1b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/ToNumberParser.scala: FileTooLong \u2014 533 significant lines (blank, comment-only and punctuation-only lines excluded), about 90% of them inside a single declaration: ToNumberParser (121-884). The bar is 500 significant lines; this is 33 over it, 1.07\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c04126c086fa8d6e3a0b9b99f6727440ad52600ac80776505b83cf91ac06f6f7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/ArrowUtils.scala: FileTooLong \u2014 531 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 31 over it, 1.06\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"39c1c275e73046a5b9d6c21cfe3f376ed9b3936d526ebca510d63acd443ed49b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: thrift/ThriftCLIService.java: FileTooLong \u2014 528 significant lines (blank, comment-only and punctuation-only lines excluded), about 95% of them inside a single declaration: ThriftCLIService (55-776). The bar is 500 significant lines; this is 28 over it, 1.06\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c282cd51244d351c6b22cb71bff6447a94ced2e508cd2413a6cf5320e63edf19"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: state/StateStoreErrors.scala: FileTooLong \u2014 527 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 27 over it, 1.05\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b12ad4af08f260de2e9cf1ac89925b3ebe2e26e239651998a513d116dee7b55c"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: TableChange: ClassTooLong \u2014 420 significant lines (blank, comment-only and punctuation-only lines excluded), 18 methods. The bar is 400 significant lines; this is 20 over it, 1.05\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableChange.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"718086d908877da4713f2de8fbf18b5e9385886bef30ecb8a9b85d1b2638d4d2"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/MavenUtils.scala: FileTooLong \u2014 524 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 24 over it, 1.05\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/MavenUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"789b27d815836fffa74d522aee2028fd48bce043d424a9c467a45d3bacbde6c0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: resolver/ResolverGuard.scala: FileTooLong \u2014 524 significant lines (blank, comment-only and punctuation-only lines excluded), about 84% of them inside a single declaration: ResolverGuard (67-719). The bar is 500 significant lines; this is 24 over it, 1.05\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ResolverGuard.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8a7a733665f3b3c4f706a1b813439f4833204c1d92ebeaa37b1f94519b8dc19"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: TimSort: ClassTooLong \u2014 417 significant lines (blank, comment-only and punctuation-only lines excluded), 6 methods. The bar is 400 significant lines; this is 17 over it, 1.04\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"78fb6b10b89c4b919b954a3927c48e5e48ef7b462fb215a2bb816c1a1ff43b2a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: clustering/LDAModel.scala: FileTooLong \u2014 520 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 20 over it, 1.04\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"57bff22c051a16e7c0f1f58378b23756c049a93d7d408c4e9d6f31c7ad298be3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: clustering/LDA.scala: FileTooLong \u2014 519 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 19 over it, 1.04\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff58075b56fbc8969dbb3afa239b43a4c657acfbaef05170c92b544b4ef3e14d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: vectorized/ArrowColumnVector.java: FileTooLong \u2014 519 significant lines (blank, comment-only and punctuation-only lines excluded), about 96% of them inside a single declaration: ArrowColumnVector (46-889). The bar is 500 significant lines; this is 19 over it, 1.04\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ed09ccf3137eda5eeca5878ab1dacdaf507e91cdc468443702467fe7b7a4a4c"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: VariantUtil: ClassTooLong \u2014 415 significant lines (blank, comment-only and punctuation-only lines excluded), 32 methods. The bar is 400 significant lines; this is 15 over it, 1.04\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"a11549fd8b1e2ed6b7c7394b967a644809600a659a2f75a208a458689178454a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/complexTypeExtractors.scala: FileTooLong \u2014 518 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 18 over it, 1.04\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeExtractors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa824954f25bdf9b503b0cf2fbee3ffd69608594f75e463e567db92c9cbdd2a8"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: OffHeapColumnVector: ClassTooLong \u2014 414 significant lines (blank, comment-only and punctuation-only lines excluded), 63 methods. The bar is 400 significant lines; this is 14 over it, 1.04\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a70508ae31dcb8ae163e3bfb1d38cb13ccb66b8fc600ff6318b7c96246db8d0"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: jobs/AllJobsPage.scala: FileTooLong \u2014 517 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 17 over it, 1.03\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6dfd3446ec388cedad59f090feba57ca96c610775dbb869e690de51ffe8a247"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: SparkLogger: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils-java/src/main/java/org/apache/spark/internal/SparkLogger.java"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbfc354c58bc05ab54516d1a52ad7035860248ca2a96f8aa4f8567b1673170d5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: BlockManagerMasterEndpoint: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6d21c63476215bdc8b6da306b673d2b518fcea5e1bfc43c413b8c3a0ff3caec"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: StatefulProcessorApiClient: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f9a076edc251fda5056bd93260ba23cc81cf73d6d890478f1fde3e07bb5b22"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DataFrameReader: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameReader.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"71a8fce5ffb4383ac403d14398df9b4c58cb77b7c566cfabebd7b88425225d60"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: WkbReader: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bd3b5744bae897241fc96eca49c24f8e0bab53dbed305349428609f84036f7c"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DelegatingCatalogExtension: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/DelegatingCatalogExtension.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad21792a6cf09c21494c4fb84cbd9d9e4371c0bca3ad82028c97f505d57cdd68"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CheckAnalysis: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"6129745297533bc162878936d8ce2434398389668315ba33d901af0ea8a3648d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: ResolutionValidator: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ResolutionValidator.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"69cf008b11002d231e3bb10115993495f6e1bf39012541b02a8c1a64d3c4a5cc"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: JoinSelectionHelper: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6734bede4622f1e3a408e3e147cfc4dd01f4862a1857e9e1412bce465802033"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: HDFSBackedStateStoreProvider: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"26542f112b9968bd2d341b3db73f82231b0af193f4fe4604d058569c46e917d0"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: PairRDDFunctions: ClassTooLong \u2014 412 significant lines (blank, comment-only and punctuation-only lines excluded), 73 methods. The bar is 400 significant lines; this is 12 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"09e07aa1dd5e6c5d2c984062534057ea2fa06d2765c81d023de348b5253d9f2d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: columnar/ColumnType.scala: FileTooLong \u2014 515 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 15 over it, 1.03\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"85abbd3f163a0c29b7717c5bef22567ec28f8cf565f86627cb54cf1ef25be88c"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: VariantShreddingWriter.tryTypedShred: MethodTooLong \u2014 tryTypedShred runs 103 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 3 over it, 1.03\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantShreddingWriter.java"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"0aeb6d9024b73c46a583e5f54d8916a5267ef9e41b470ae9a221dfad907a8fff"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: UnsafeRow: ClassTooLong \u2014 411 significant lines (blank, comment-only and punctuation-only lines excluded), 65 methods. The bar is 400 significant lines; this is 11 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e4b3192aa6313d9aba416ba2371630d5cfd9aa19e3af026ecf94837b92d0c8e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: runtime/IncrementalExecution.scala: FileTooLong \u2014 512 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: IncrementalExecution (68-881). The bar is 500 significant lines; this is 12 over it, 1.02\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/IncrementalExecution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b28466f0259c05d5e6a8ee007c654725f80f4343c53e9dc58a9240a62928e31d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: pipelines/PipelinesHandler.scala: FileTooLong \u2014 511 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 11 over it, 1.02\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"180ffda4ddb9c863f58a13ed15561698a28a40cc91b0586b68b1884063262aa6"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: TransportResponseHandler.handle: MethodTooLong \u2014 handle runs 102 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 2 over it, 1.02\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportResponseHandler.java"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"d49e800e58259685a4b183d781ed71779bb37137400a0c66d3affd31109bf8d5"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: ExternalBlockHandler: ClassTooLong \u2014 407 significant lines (blank, comment-only and punctuation-only lines excluded), 23 methods. The bar is 400 significant lines; this is 7 over it, 1.02\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5c092ff38699a7c051798e6ef79e3099b0b48f73df4f28d593d16c02e1428be"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/misc.scala: FileTooLong \u2014 508 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 8 over it, 1.02\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0464ea8180ded16e6dee64c257945e50b9bfcd70ba851a4fd3747265b4105fc"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: classic/column.py: FileTooLong \u2014 506 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 6 over it, 1.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"64b40206ecd27cab9fffc018b6671a0581185c674026b7a6f48e20046afed53d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: columnar/InMemoryRelation.scala: FileTooLong \u2014 505 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 5 over it, 1.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0df3aefa6b9b8771e4791eb0d9f471622acd6e5077abf74672f9f4882387240"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: memory/MemoryStore.scala: FileTooLong \u2014 504 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 4 over it, 1.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ef8c6818c353eb0b3ab2495a8500a282526aabf14b95b1419ded992a9ff77fd"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: expressions/literals.scala: FileTooLong \u2014 504 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 4 over it, 1.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"69df1260a861abe950cd4f95c81ff99f11ec663643830ea0d13da6806aee2605"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: util/SparkDateTimeUtils.scala: FileTooLong \u2014 503 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 3 over it, 1.01\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c04a2ca1dcbca832698c605c2ab2f5477f1feae1f70d3632662c5622a366909e"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: KeyValueGroupedDataset: ClassTooLong \u2014 402 significant lines (blank, comment-only and punctuation-only lines excluded), 21 methods. The bar is 400 significant lines; this is 2 over it, 1.01\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"341bcbf1e71c2a5c31e0e822438c70b1b18e748f0d13a543424a906e604b8839"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: param/params.scala: FileTooLong \u2014 502 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2 over it, 1.00\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/params.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b160eddb8dfcb5790352dfbc37e1809c3be6d2245a713e25f16caf283064c02"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (6 members, 27 shared lines): python/pyspark/sql/connect/readwriter.py:210-263 | python/pyspark/sql/connect/readwriter.py:351-403 | python/pyspark/sql/connect/streaming/readwriter.py:352-394 | python/pyspark/sql/readwriter.py:358-531 | python/pyspark/sql/readwriter.py:814-947 | python/pyspark/sql/streaming/readwriter.py:710-801 \u2014 These 6 members are variants of one another: a block of 27 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"149f425ffa5ad0b2fc1bb09843f2b5fb0728a4bcd6e7e7246842e20a480b9711"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 29 shared lines): core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:30-78 | core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala:29-77 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:64-132 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:46-92 \u2014 These 4 members are variants of one another: a block of 29 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"9823f4596fba3b1fd2c83c072998301dbe97b9d462184cc239903e00a458160f"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (228 shared lines): python/pyspark/pandas/frame.py:8823-9157 | python/pyspark/pandas/namespace.py:3126-3601 \u2014 These two members are variants of one another: 228 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8823}}}],"partialFingerprints":{"codehealthFindingId/v1":"769d7f48b122b0d3247f2145cf45adfed6f904d41eedd3a6fd7d4eba93a16d7e"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (68 shared lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:92-207 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:255-378 \u2014 These two members are variants of one another: 68 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"afba4f5d0c206b5a0c083ab8b4b6166b60d46b4195994f32c43de6ebed77b405"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (66 shared lines): python/pyspark/pandas/groupby.py:4108-4312 | python/pyspark/pandas/groupby.py:4321-4522 \u2014 These two members are variants of one another: 66 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4108}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb85efb5becb2f41e37bbf956a563d86516f6fe010bedf1e5663f1b2e7e4d22e"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (62 shared lines): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:542-608 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:152-223 \u2014 These two members are variants of one another: 62 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1e11e63adb490d6f3c1b179aaa4a5ff693826df8caac7838d467c97ae28184c"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (59 shared lines): python/pyspark/pandas/frame.py:12634-12772 | python/pyspark/pandas/frame.py:12775-12907 \u2014 These two members are variants of one another: 59 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12634}}}],"partialFingerprints":{"codehealthFindingId/v1":"37003521e0d6da871bbd9e2c800774e4e60f8a0a7dc96e38bbd19d4912f8cf24"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (45 shared lines): core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:269-394 | core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala:198-354 \u2014 These two members are variants of one another: 45 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"f47a462cd6aac6297a7d01c8d0c4206d0262d0642f22cd2492a1f9a4d41e4080"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (45 shared lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1244-1293 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1107-1156 \u2014 These two members are variants of one another: 45 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1244}}}],"partialFingerprints":{"codehealthFindingId/v1":"719b25287790193bb85b75f125f4dc199865706a5a59109693255cab7ecce4f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:208-222 | mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:252-265 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"531a54ed406806d3fa0857843bde69e8e1f1c2d4711b56f1c283e6d5ae6469e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:144-174 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:342-386 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6586e0b8bc118cac7bd41ea16b7d459f72819928dd671f1afa422bb93efdc44"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java:111-134 | common/unsafe/src/main/java/org/apache/spark/unsafe/Platform.java:262-285 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b5102faa315e962464d1183593c1851c4867ed2c269e7e8976dd8a7752964bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (24 members, 50\u002B identical tokens): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:179-193 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:199-214 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:220-236 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:242-260 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:281-300 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:322-342 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:365-403 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:427-467 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:492-534 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:560-604 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:632-678 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:707-755 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:205-219 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:221-236 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:238-254 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:256-274 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:276-295 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:297-317 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:319-357 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:359-399 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:401-443 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:445-489 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:491-537 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:540-588 \u2014 These 24 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 24 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 24 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6e0dfa152c7c62f76af05efb2dd099cce6cebb2115d350aeb66c91f2d143125"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (22 members, 50\u002B identical tokens): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:273-284 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:302-314 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:333-346 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:366-380 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:401-416 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:438-454 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:478-495 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:520-538 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:564-583 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:610-630 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:658-679 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:725-747 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:795-818 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:868-892 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:944-969 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1023-1049 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1105-1132 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18203-18213 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18232-18243 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18263-18275 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18296-18309 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18332-18346 \u2014 These 22 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 22 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 22 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"c85bdfdc77558a9fec2bb3d5cd1bda6078e6e00470f62e9620f65f46c73efb86"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (10 members, 50\u002B identical tokens): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:142-158 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:164-176 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:182-194 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:202-216 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:224-239 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:245-257 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:265-282 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:289-303 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:453-468 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:473-491 \u2014 These 10 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 10 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 10 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"54ad52331375fed20a65522be2b05ce0fd77f771bc64d2cb93cb9f85f533c13f"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (9 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:132-144 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:143-156 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:126-139 | mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:150-163 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:134-147 | mllib/src/main/scala/org/apache/spark/ml/r/GaussianMixtureWrapper.scala:125-137 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:135-147 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:154-167 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:137-150 \u2014 These 9 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 9 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 9 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee7f98856fb367b17ef81b0ce198bfb64c48a0d1479f9b328639fa7cc43e64ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (9 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:594-614 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:618-638 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:642-662 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:666-686 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:690-710 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:714-735 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:739-760 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:903-923 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:952-972 \u2014 These 9 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 9 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 9 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":594}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f1145c7498058c6618eb7cb8986778a12c7c0b5578503153d929664e6f53089"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (8 members, 50\u002B identical tokens): python/pyspark/pandas/generic.py:1229-1298 | python/pyspark/pandas/generic.py:1307-1407 | python/pyspark/pandas/generic.py:1416-1515 | python/pyspark/pandas/generic.py:1522-1585 | python/pyspark/pandas/generic.py:1590-1654 | python/pyspark/pandas/generic.py:1867-1966 | python/pyspark/pandas/generic.py:1971-2065 | python/pyspark/pandas/generic.py:2198-2309 \u2014 These 8 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 8 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 8 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1229}}}],"partialFingerprints":{"codehealthFindingId/v1":"a540325096e0a9a8b7929a561588fd61138add4ce097560e97a7e39d5b46729d"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (8 members, 50\u002B identical tokens): python/pyspark/sql/connect/functions/builtin.py:4370-4413 | python/pyspark/sql/connect/functions/builtin.py:4463-4507 | python/pyspark/sql/connect/functions/builtin.py:4586-4609 | python/pyspark/sql/connect/functions/builtin.py:4644-4667 | python/pyspark/sql/functions/builtin.py:28417-28613 | python/pyspark/sql/functions/builtin.py:28661-28869 | python/pyspark/sql/functions/builtin.py:29139-29276 | python/pyspark/sql/functions/builtin.py:29309-29439 \u2014 These 8 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 8 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 8 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4370}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ec533fb57343d88baf8670ed7ebf062d80f1958c4c6c7f7c72d47549b48fe0d"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala:142-154 | mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala:164-177 | mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:145-157 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:112-124 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:140-152 | mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala:150-163 | mllib/src/main/scala/org/apache/spark/ml/r/LogisticRegressionWrapper.scala:205-218 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f78c15a1bcaa3386149f121d1f801b77a542ac629f3522d206fb6834c6db8ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:75-106 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:68-99 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:73-107 | mllib/src/main/scala/org/apache/spark/ml/r/GaussianMixtureWrapper.scala:70-99 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:59-87 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:77-109 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:74-109 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"c81cf72f1c699d35711fd217cf26ceeb25c4fbcca98e92b04fdc76f202304690"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:506-526 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:570-587 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:592-609 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:633-654 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:658-675 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:901-918 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:923-942 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":506}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3814976c298b058ef2bb9031e10ffadfe7ee10a80b1fd206bfd416b4a282bb8"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:125-138 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:108-121 | mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:132-145 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:116-129 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:135-149 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:118-132 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dca612591dffe6d856ff560ceabb903ad7417cfb050a66fe9ecfc427b37b8ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:94-141 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:146-193 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerSessionPage.scala:90-138 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:70-115 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:118-164 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala:71-118 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"697ea08ac1379d2613f0a670af082ba5f8e741125156e684791cf5b9b8880c51"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:127-146 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:272-289 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:555-572 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:149-168 | sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveFileFormat.scala:118-143 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala:199-217 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b448db29ae6660dfda23ce6f54c4d02016e53d2ad9c95f4afa9a1a0b897c6a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:529-568 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:571-625 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:628-728 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:732-825 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:828-897 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:937-982 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c34fb918ebc8e44710bee31d8a213e3ceb62f418170dee92d02229b6b08ef17"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:38-113 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:124-183 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:194-257 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:265-308 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:316-359 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:397-444 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e4f254f247a0e613f9c17a7a69eb81bf2abff5a6dec1a0aa9912241c17b5da6"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:125-159 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:148-189 | mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:122-146 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:341-449 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:142-173 \u2014 These 5 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 5 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 5 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaae500fa2f4f58974ced01253b8c39750766c97c189d3c077935fe949c25386"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:112-221 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/ColumnarArrowEvalPythonEvaluatorFactory.scala:210-269 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonEvaluatorFactory.scala:92-174 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonUDTFExec.scala:55-145 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala:353-369 \u2014 These 5 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 5 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 5 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac70419c92e2aeda2e32f7cbb031cc5a6d40a9e4b2f768d356c72320838fb138"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:111-139 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:142-168 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:171-197 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:200-226 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"c406ef78191d19cfdba3e2313e56c4cd6d9157b680e2e94b6863d283485672c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:779-834 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:858-894 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:656-711 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:722-760 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":779}}}],"partialFingerprints":{"codehealthFindingId/v1":"729a06495d77d2a41c528e0be5279b747eb6bb8ecb3576c46664142cc6a6a499"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:575-585 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:719-733 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:720-730 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:874-888 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":575}}}],"partialFingerprints":{"codehealthFindingId/v1":"c359eda3a5096bf46d9ecc969729c3bc0687e666d607522f7d3afcd78da21aae"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:296-353 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:943-1035 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:298-351 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:549-621 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"9aad936d4de3637876279f212321ba5851eb7aa445b51b24770968e33d311542"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala:125-137 | mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:128-140 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:95-107 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:123-135 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"750721bedddbd42954cb18c132aac3e7108cf0f6ce63951f11952200e5e517eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:330-360 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:372-402 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:414-444 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:456-486 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"4898c45cf7ac0c68c6ab505dd07f7f5ea6295171eb06924e9c37f52145ba7fb9"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1181-1205 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1216-1247 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1250-1311 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1314-1377 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1181}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6e600fe7cde3b390dad4b9ba20da00ce3322a0e54c658c391e9b01230955cc9"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:155-192 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:418-446 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:191-228 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:403-438 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"c880762785692ddf51494e272a7266bfbfcbc8e0c0fe8cae3e41048ec241cd23"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:130-144 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:501-515 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:600-612 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:698-710 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"b55ab3891a4f69454e9cfa53e40e56e6c74194a793cab7ef1c1e4bb7553ebbfc"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1559-1587 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1697-1725 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2785-2813 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4527-4542 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":1559}}}],"partialFingerprints":{"codehealthFindingId/v1":"01bc48ab73819aa7acb1c33975ab1bbd06768dcf972514c11dff9187526bb810"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4815-4890 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5012-5093 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5237-5331 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5461-5549 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":4815}}}],"partialFingerprints":{"codehealthFindingId/v1":"8df94bf4b98861ea207a8ea82cf345673e86cf56747777106126132eaabeeb12"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:122-141 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonTable.scala:59-76 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcTable.scala:53-68 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetTable.scala:53-70 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"27654e0a577f4c47df56b54de77d18a792e05ec802ddcb2fef65c5144ec52c52"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:809-844 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:849-884 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:889-930 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:935-977 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":809}}}],"partialFingerprints":{"codehealthFindingId/v1":"8afe3511680b8ec1c6d844bbf83b1974dd56837811c4c692581b6fade4917d8c"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:453-492 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:518-535 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:573-597 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:636-661 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc1872e772d7542e8c01b44389284e41083afd8463712c8d281f42e388ae2d3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:121-134 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:107-120 | common/network-common/src/main/java/org/apache/spark/network/shuffledb/LevelDBIterator.java:39-52 | common/network-common/src/main/java/org/apache/spark/network/shuffledb/RocksDBIterator.java:45-58 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecb1ad8e60b3f39cc62839085fd99e41d5460785d45b49f2a9110ad6e1407d72"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:302-312 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:329-395 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:304-314 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:331-397 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"da0035ca4d113256974dda61d4293b40991408cb1930cff864c98ae4ccecdab5"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/eval_handlers/_arrow.py:278-287 | python/pyspark/eval_handlers/_arrow.py:350-360 | python/pyspark/eval_handlers/_arrow.py:551-564 | python/pyspark/eval_handlers/_arrow.py:606-618 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"53ea5dca0f5769d0f5e44fabdd3e4327dbe5eec7ba74abcb8e888a176fec4d53"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/eval_handlers/_pandas.py:246-288 | python/pyspark/eval_handlers/_pandas.py:313-369 | python/pyspark/eval_handlers/_pandas.py:397-449 | python/pyspark/eval_handlers/_pandas.py:482-532 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"7eaa0058f3963a4b1c68b8ca4e6e99150dcd9f3e054a56acb08c943d4837e110"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/mllib/evaluation.py:670-688 | python/pyspark/mllib/feature.py:1053-1063 | python/pyspark/mllib/random.py:682-694 | python/pyspark/mllib/regression.py:1039-1050 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/evaluation.py"},"region":{"startLine":670}}}],"partialFingerprints":{"codehealthFindingId/v1":"f34fbdf76d4c926e9fb0b30e17402551f14c1d0070979af9ed47a9dc135dc69d"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/pandas/accessors.py:202-430 | python/pyspark/pandas/accessors.py:435-763 | python/pyspark/pandas/frame.py:3020-3344 | python/pyspark/pandas/groupby.py:1825-2192 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"65bf14d173ff1190a2abad383ded25ea9c29e033563ac25be4b276a871ed2465"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/pandas/plot/core.py:168-180 | python/pyspark/pandas/plot/core.py:394-419 | python/pyspark/sql/plot/core.py:502-527 | python/pyspark/sql/plot/core.py:574-585 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ec9e1b9c849cc2bf00616179b2763a944a078cd0a8ef8eaded77b9e0fcd17d8"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/avro/functions.py:204-240 | python/pyspark/sql/connect/avro/functions.py:91-133 | python/pyspark/sql/connect/protobuf/functions.py:116-158 | python/pyspark/sql/protobuf/functions.py:297-335 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/avro/functions.py"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"72c172703eaeaba2e8747d4750f18a9a62bd0237cb52f9a988c7a9c3fc2656b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/connect/readwriter.py:656-699 | python/pyspark/sql/connect/readwriter.py:712-744 | python/pyspark/sql/readwriter.py:1570-1661 | python/pyspark/sql/readwriter.py:1672-1745 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":656}}}],"partialFingerprints":{"codehealthFindingId/v1":"e489e21dce86b09660b0d426d1ff94fa22d9ae352d4de9ec670ff129c8246859"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/pandas/typehints.py:53-199 | python/pyspark/sql/pandas/typehints.py:212-325 | python/pyspark/sql/pandas/typehints.py:409-480 | python/pyspark/sql/pandas/typehints.py:502-577 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba52818f0f5cdadeed746cbcb5d584c02e045c7615f4fd737943f3ef56c9b8e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/streaming/list_state_client.py:43-60 | python/pyspark/sql/streaming/map_state_client.py:53-70 | python/pyspark/sql/streaming/map_state_client.py:96-120 | python/pyspark/sql/streaming/value_state_client.py:39-56 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"55a0b0cbbf446c364e752b4666b6a32936d7792dddffe824d16f228cb5cd7b1e"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/streaming/list_state_client.py:111-126 | python/pyspark/sql/streaming/list_state_client.py:129-149 | python/pyspark/sql/streaming/list_state_client.py:152-171 | python/pyspark/sql/streaming/list_state_client.py:174-186 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e1b3a3bec1036c5cb49d7b611cce5e3fa9b0149cdf683c03fab5495df438e82"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): python/pyspark/sql/streaming/python_streaming_source_runner.py:217-309 | python/pyspark/sql/worker/data_source_pushdown_filters.py:119-298 | python/pyspark/sql/worker/plan_data_source_read.py:279-383 | python/pyspark/sql/worker/python_streaming_sink_runner.py:43-107 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/python_streaming_source_runner.py"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdb3cc495e9db687877a37faca0a3119cc47119c146ada5314a3713104a2443f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (108 corresponding lines): core/src/main/java/org/apache/spark/util/collection/TimSort.java:686-793 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:806-917 \u2014 These two members are one piece of code written twice and then edited apart: 108 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":686}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8b86538eaeb72e4f8205cc68d9ecae4400e3537c1dc6b14a123725ca368fffb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (100 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:528-627 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:441-542 \u2014 These two members are one piece of code written twice and then edited apart: 100 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":528}}}],"partialFingerprints":{"codehealthFindingId/v1":"34b967217b9f7b0aa0c773555a93b508cbc57f6059836f76dc3a63826d4ea699"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (66 corresponding lines): python/pyspark/pandas/plot/core.py:315-383 | python/pyspark/sql/plot/core.py:726-791 \u2014 These two members are one piece of code written twice and then edited apart: 66 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":315}}}],"partialFingerprints":{"codehealthFindingId/v1":"2be96ccea413c8fdc18e90156a874f0efc19b4bd389f09a8b1ac4426fc29dd64"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (111 corresponding lines): python/pyspark/sql/classic/dataframe.py:1560-1670 | python/pyspark/sql/connect/dataframe.py:1526-1650 \u2014 These two members are one piece of code written twice and then edited apart: 111 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1560}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc2bde4efca3bfa74b9f5ea00252c35fcbc4237847e186222dea124c04877db5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (50 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:56-105 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:57-110 \u2014 These two members are one piece of code written twice and then edited apart: 50 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"1dde78657adc52e3f8b99a2613fd354bee29a004c924f15597ea07b0437ef0d8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (95 corresponding lines): python/pyspark/pandas/groupby.py:2422-2516 | python/pyspark/pandas/groupby.py:2519-2613 \u2014 These two members are one piece of code written twice and then edited apart: 95 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2422}}}],"partialFingerprints":{"codehealthFindingId/v1":"194eb7f4b2bea6e468fd66428f82fb03414ddb8ea6e3e363d4c83c106e4d4212"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (79 corresponding lines): python/pyspark/pandas/groupby.py:4675-4753 | python/pyspark/pandas/groupby.py:4757-4838 \u2014 These two members are one piece of code written twice and then edited apart: 79 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4675}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d39f32a68f35f900db25ad5c9ec0f6939c4c84acc7804ec808d914a15b06ddc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (46 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:980-1025 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:841-886 \u2014 These two members are one piece of code written twice and then edited apart: 46 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":980}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc97f66a46ab4e36eb3932a5fc4a97c45a3d47368e44d30a52b88baf4511d27b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (84 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala:429-522 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala:151-234 \u2014 These two members are one piece of code written twice and then edited apart: 84 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"11070bd6064506193c9e427f353bd1a11c3f9abc20400a4972508d4df542d753"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (60 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1303-1362 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1166-1225 \u2014 These two members are one piece of code written twice and then edited apart: 60 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1303}}}],"partialFingerprints":{"codehealthFindingId/v1":"79d316b71532a73df55977b565d6b79a66e35938017d78744a7479eee79f6421"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (55 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:58-118 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:50-104 \u2014 These two members are one piece of code written twice and then edited apart: 55 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f610a70e53c10f6ec54f7401427308f7073ecf23db6a5975927ef9ffb724c35"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala:116-158 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/LiteralValueProtoConverter.scala:351-390 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"241eb355d9abad59fc82b6dfd6e70cda6b8e1bef5d3424b861fa15094ff5b800"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (59 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6607-6678 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6715-6773 \u2014 These two members are one piece of code written twice and then edited apart: 59 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6607}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae4918d659ff63d1a2f72e96342b87607bc3a45784f567511874d7ca69df1751"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (78 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:355-432 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:551-656 \u2014 These two members are one piece of code written twice and then edited apart: 78 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala"},"region":{"startLine":355}}}],"partialFingerprints":{"codehealthFindingId/v1":"c84b000f94dbe03093a36ab91a2a32f3a3cab99ba9dcfb1f9754a21eca87fd87"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (155 corresponding lines): python/pyspark/pandas/strings.py:1942-2105 | python/pyspark/pandas/strings.py:2111-2265 \u2014 These two members are one piece of code written twice and then edited apart: 155 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/strings.py"},"region":{"startLine":1942}}}],"partialFingerprints":{"codehealthFindingId/v1":"8da9cb218445e900bae880890ee397e8107fdf396eecf5ef6f180cf228f7d0ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (56 corresponding lines): python/pyspark/ml/linalg/__init__.py:563-636 | python/pyspark/mllib/linalg/__init__.py:630-685 \u2014 These two members are one piece of code written twice and then edited apart: 56 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":563}}}],"partialFingerprints":{"codehealthFindingId/v1":"628b766596077cd068aa1dd6341894ad2c31779fa357389b5dafa13b20d89f3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (70 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:848-925 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:1014-1083 \u2014 These two members are one piece of code written twice and then edited apart: 70 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd855c53aecd0499f08218b5a7224744d5b9fa2009611ec3ac0de651be631b87"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (68 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:83-153 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala:80-147 \u2014 These two members are one piece of code written twice and then edited apart: 68 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6defe3c5565c3134206aacc792a65e2df27e608d2bda30a98881d95e2a7a074"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (61 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1413-1473 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1493-1573 \u2014 These two members are one piece of code written twice and then edited apart: 61 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1413}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ac3e59541cf20e64899d8796beee796627064eb8d5360ac631bda2bbf2a73b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (56 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java:54-115 | common/network-common/src/main/java/org/apache/spark/network/protocol/SslMessageEncoder.java:54-109 \u2014 These two members are one piece of code written twice and then edited apart: 56 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"32ced21235e547b8e7c29bb43b1a8f087ff182e0f3b8f4f2395c1656a4ef0783"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (57 corresponding lines): core/src/main/java/org/apache/spark/util/collection/TimSort.java:540-596 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:611-668 \u2014 These two members are one piece of code written twice and then edited apart: 57 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"167e89bc4eda6fc304c2d30dafe625ee644d03f455897473bf506a06b6383326"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (74 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1825-1899 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1922-1995 \u2014 These two members are one piece of code written twice and then edited apart: 74 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1825}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ba71a14310e9b8a96bbd9678b6fc49b7e4ca5a37d90a5427352a1e887763a25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 44\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:187-234 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:192-237 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:197-240 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 44 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"206ac15521fe9f08ace9c8bb3c204c01309ba0bb66e5e3422ec286936df1ea15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (116 corresponding lines): python/pyspark/pandas/frame.py:11444-11567 | python/pyspark/pandas/frame.py:11575-11690 \u2014 These two members are one piece of code written twice and then edited apart: 116 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11444}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b5141ac76a713a6fcfd245669792189c2065d6daca000a489607e18be4b3632"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:176-217 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:172-204 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"99d8d925dda9ffd476dd8dba3a1badb57a169796d610215eb8db94318e573af3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (88 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:1067-1171 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala:231-318 \u2014 These two members are one piece of code written twice and then edited apart: 88 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1067}}}],"partialFingerprints":{"codehealthFindingId/v1":"067c28d374a1c816195cfbe1b38eaf17a29d1eeb8758542079dabc9e1156e4c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (75 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala:197-271 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala:87-165 \u2014 These two members are one piece of code written twice and then edited apart: 75 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc3575644b496308bca6d4d2cd3b378831e20239d4c67ad912bd2a8fe0b829eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (57 corresponding lines): python/pyspark/sql/connect/streaming/readwriter.py:580-636 | python/pyspark/sql/streaming/readwriter.py:1367-1495 \u2014 These two members are one piece of code written twice and then edited apart: 57 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":580}}}],"partialFingerprints":{"codehealthFindingId/v1":"12de979b3488b0d5d6174a5ceb73d0b68b58d1961a6dba8df734e80c2e9d2b45"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): python/pyspark/pandas/plot/plotly.py:101-146 | python/pyspark/sql/plot/plotly.py:216-253 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ec076233b635fc26ef0e414c97d881d3d56f3b3676b4eaabb5973f26d1fe69a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (65 corresponding lines): connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala:58-122 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala:96-176 \u2014 These two members are one piece of code written twice and then edited apart: 65 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b75fe73b918fd802035d519b7ce2936373684a6e12bb28d7e120fcffb30894d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (65 corresponding lines): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:176-240 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:156-220 \u2014 These two members are one piece of code written twice and then edited apart: 65 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"35988255ef722255536d782cf03835eaaed66eec77a4771ceb57bf1b5f747dd8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (49 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:226-284 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:336-384 \u2014 These two members are one piece of code written twice and then edited apart: 49 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"34f6987e1f439dd947877c8b9f7d4321cbe45acf07b4e5d56fe1fb10ed4a2994"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (61 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/submit/KubernetesDriverBuilder.scala:41-110 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBuilder.scala:38-98 \u2014 These two members are one piece of code written twice and then edited apart: 61 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/submit/KubernetesDriverBuilder.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fc210280b837ed87000e793579456123f46a4da969ef60ddc7e0900065c4b5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (60 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:378-437 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:1668-1732 \u2014 These two members are one piece of code written twice and then edited apart: 60 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":378}}}],"partialFingerprints":{"codehealthFindingId/v1":"93e500f1e98736c2c6f845c783862a58c1f4d723c23f3562bde0659da423bd0d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (58 corresponding lines): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1413-1530 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala:216-273 \u2014 These two members are one piece of code written twice and then edited apart: 58 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1413}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd4fb0e04177c26ad40db5c633374ffe0ace9e49c4fd73665844ca0c20e314d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 46\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/Row.scala:478-523 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala:87-132 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala:90-135 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 46 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"5951792129f5a80851108b0c9d73f73e87ae80020625de69e0608863b0623182"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:461-500 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:421-455 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":461}}}],"partialFingerprints":{"codehealthFindingId/v1":"3932e1a14ba746ab7571920557ba78a5b0d8b14a025bdda39cfa9764eeb57188"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:166-203 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:198-235 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"71e5eebba05116ac28dd514c41a092a4bb95c62bc94bf857122b3c9337e37561"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (62 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:457-518 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:523-590 \u2014 These two members are one piece of code written twice and then edited apart: 62 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bf461a7bdb9efe3466dd67a21cd0bde3a1c80d5f31d97fec142dc7660b6d41f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (39 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala:296-337 | mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala:509-547 \u2014 These two members are one piece of code written twice and then edited apart: 39 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a6c689e0688b468e604d3b85229a92bc7bc5c5b6937c63878f87d682380c092"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:902-928 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:936-957 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":902}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e7ecd19233e3b844fb3a1a1ce0555aafa621f0c864e9f91f71901a10016f3a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (41 corresponding lines): core/src/main/scala/org/apache/spark/deploy/Utils.scala:63-103 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:140-187 \u2014 These two members are one piece of code written twice and then edited apart: 41 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Utils.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"729fa84b9bb27830f4c03861a060d4c20ba7e6e5b3548ee820d2c532bac38e62"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:277-311 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:241-274 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":277}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f5d2ad1bd9f670d52db01051f8e5b6005b8787ea5f31f9731a002cdc442eec4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java:1133-1174 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java:1180-1225 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":1133}}}],"partialFingerprints":{"codehealthFindingId/v1":"2aa21fe06ea6c138452ba602d5bfa1fc1ba3e0ae62a678ca663b17d123361331"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (59 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:390-448 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:469-527 \u2014 These two members are one piece of code written twice and then edited apart: 59 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cba7ae4283261ec5876f0044a275f56b8d8e9b3b06cdd6e57662350497d9a15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (51 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:220-270 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:465-515 \u2014 These two members are one piece of code written twice and then edited apart: 51 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ec13e29be5708771fa1903fea731decd230c1b215c3b64c7390ed6f353f5b94"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:500-525 | core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:595-614 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":500}}}],"partialFingerprints":{"codehealthFindingId/v1":"d87f9b7e9288c792f2c23268eb4df300fa884f7e530d97a7e97261475cf6bf24"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): python/pyspark/pandas/indexes/multi.py:514-549 | python/pyspark/pandas/indexes/multi.py:561-596 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0afb5dd317247c4efd39d30cbef6d6956db7b4daa147f5af53ea1e2827e4734"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala:43-91 | mllib/src/main/scala/org/apache/spark/mllib/pmml/export/GeneralizedLinearPMMLModelExport.scala:41-76 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6700051d1e0fbd5e860c5a3b25a985d72bd409c0fd33bff9511a634deacf60a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:349-382 | sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:396-429 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala"},"region":{"startLine":349}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a48a185104450f0eaebba32d03b90e411d50fec012246d78801602f49c09aa2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (58 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:108-165 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java:116-182 \u2014 These two members are one piece of code written twice and then edited apart: 58 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"b34e0c8ff7b688060fc7def9747af1c5c0d76bc626355cae5faa544dec3ff274"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (91 corresponding lines): python/pyspark/pandas/frame.py:7639-7747 | python/pyspark/pandas/indexes/base.py:1327-1417 \u2014 These two members are one piece of code written twice and then edited apart: 91 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7639}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6aed525157c4be4e4904fd086f12726ef072c6b70595afe845a17666c4d5198"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:154-204 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala:345-377 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"113c11d44144c30efd77626841c0f99950ccb69ad889ce6a86f64b3d336a2059"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:401-436 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:257-294 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d710f0151d350b14cc9093fe0c918837c09dc620fa62b9235b00a8df45fde96"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (49 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:136-184 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:174-228 \u2014 These two members are one piece of code written twice and then edited apart: 49 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"dadb4752ff17ac469133edab6151be7c68139abe8b66c60195640cd24564c42d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java:262-300 | connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java:322-343 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"47493732425ed692d2e131737fffc9f046db788f2218b8e0affad8cfd986f972"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:419-453 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:382-413 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"f18a8380e288a6abda296c9f9415dc558c995a3478eee2bc1c1d3b0316d9181d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): python/pyspark/ml/tuning.py:557-595 | python/pyspark/ml/tuning.py:1226-1255 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":557}}}],"partialFingerprints":{"codehealthFindingId/v1":"e64cefbc20b193884895516340bbece10e3c76af18befdfb3347b30246524ce2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTimeWindows.scala:63-101 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTimeWindows.scala:114-151 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTimeWindows.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"68340204cb8d92ce004a7dfac4574b583dc5fe13b0f79f1bc57cf002a86fc62d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/Edge.scala:71-97 | graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala:142-170 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/Edge.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceddb1af8378aad7fa8c8030729e49fae5b5a505e5043f782c9ceeea9c60d8a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java:120-153 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java:164-197 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad8870fd35f6ac604396ce37e6abbaa5e57554cfe448e5c81ae03e21622b9627"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1683-1713 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1716-1742 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1683}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd50e2fe7b20a4ee135161ed04c97343d9d209bbd957a1a8374a3cb330ea36e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:188-226 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:418-449 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"eca05b424f109620a81cd8c0166489438e9b22cfecfd225828033499db44f508"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): python/pyspark/sql/classic/dataframe.py:2201-2238 | python/pyspark/sql/connect/dataframe.py:2590-2642 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":2201}}}],"partialFingerprints":{"codehealthFindingId/v1":"160c029f90b6e41c23b7174bafe8f9c219653ac9d3212c2bd879a0117ce20414"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (68 corresponding lines): python/pyspark/pandas/groupby.py:4014-4099 | python/pyspark/pandas/groupby.py:4593-4660 \u2014 These two members are one piece of code written twice and then edited apart: 68 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4014}}}],"partialFingerprints":{"codehealthFindingId/v1":"e235c94df984df6350fccdec4f581f12913f93dfe8a7d71fcc8ebd88d58d7986"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (54 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:316-369 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:353-407 \u2014 These two members are one piece of code written twice and then edited apart: 54 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"de69d7839e2bb6540b66c5b71c920af183b6256c85e3a2d25e2d64708e2ef175"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (41 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:97-137 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:199-239 \u2014 These two members are one piece of code written twice and then edited apart: 41 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"101b7e3345bbcf7a283fecfee8a94160deca1d7e77c359031b8e32ede068b745"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): python/pyspark/eval_handlers/_arrow.py:157-199 | python/pyspark/eval_handlers/_arrow.py:225-266 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"3707231f67773dc17e22690314bc4c9a95ec6d343ebbd4adc810a0e9de8e9aa5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:999-1026 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1030-1058 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"8deda5d34e283ce60ec4dd6785c658fe4a168bcc7451fdd912e81f0bf4757e82"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (39 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala:201-239 | mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala:397-441 \u2014 These two members are one piece of code written twice and then edited apart: 39 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ed9d8ecb6f702a7ca7b238df32be216e4785761dd3fe71e59ca2d03e3d2a939"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:110-135 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:214-236 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"72176a277c79fa2d5c442cb359805cd1e99dd8a42ec6a77753e2399de28880af"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:312-348 | mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala:128-176 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"27c0263915af5c6d42c4cb29aed790f1dfeba42956c5ccc5e0286545b661e144"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (73 corresponding lines): python/pyspark/pandas/series.py:6602-6675 | python/pyspark/pandas/series.py:6678-6750 \u2014 These two members are one piece of code written twice and then edited apart: 73 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":6602}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b2d39506ad24d1c8e53623604302b8bca2211a24dfaac418a27f75d47521498"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): python/pyspark/pandas/plot/matplotlib.py:426-457 | python/pyspark/pandas/plot/matplotlib.py:544-578 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"85a9401546f91319e11ebe34cfa2e54a0bdca9e19ede58a13ccad2ed8ef7d420"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:233-258 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:379-406 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":233}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd7c8ca336433fb4f29254fc4eb5360bf2988bc3775e42fe5b461c8d7f44e3a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/FetchCursorExec.scala:173-212 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/SetVariableExec.scala:61-95 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/FetchCursorExec.scala"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7a350b67dabde277f4d61665fe0ba38671ece5eaa52f08ffee79121d037523f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (46 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala:120-166 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala:168-213 \u2014 These two members are one piece of code written twice and then edited apart: 46 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"53bcf012bfd1004c9decadc6a176ddd9aa96d12a639ce0d4df344bcf5e0344ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1037-1072 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1157-1199 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0d82dc8cf43a578ce8d6dd6a8b611e05764cbcf9701482e6177be0c843f696d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala:105-127 | mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala:651-673 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"738ccd4f1d7b42241fffdd2bd0e936f9adf0bc2ae4f70adc97f01497a66fda8c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (87 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:750-847 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1239-1325 \u2014 These two members are one piece of code written twice and then edited apart: 87 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":750}}}],"partialFingerprints":{"codehealthFindingId/v1":"3094513e1d96fa70c3755b64f96f8123361695f77dedda04c96dfa0c966ffd8b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:457-475 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:555-579 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"e52aa1ff293f8737d6b47a1334ccb9202b262fc12e1239d10fcd05d396979ecc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): python/pyspark/pandas/frame.py:8432-8460 | python/pyspark/pandas/indexes/multi.py:407-474 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8432}}}],"partialFingerprints":{"codehealthFindingId/v1":"e92495a830bfb4d632c9d3d9714d11cbdb15597002a71ef14bc6f907e8738a65"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala:135-162 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala:137-164 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ac581737504187c25ee9926ade22a9e8f06e0c09692a5dc22ebbc93cb4a47b8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java:160-191 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java:196-222 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"8202abf41d7b715905199f573d407ecf9d254a00802e267f134ed967d28bb2c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (39 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ReplaceTableExec.scala:85-124 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:263-301 \u2014 These two members are one piece of code written twice and then edited apart: 39 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ReplaceTableExec.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c1dd9f6071b0e946988ef5f1ff71022aed38307b6d7a93082695e217628eec9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:69-114 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:132-169 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"c79965b238020cafc02bbea38fad64080d7b318599214a2ba3bcdefdbd2170ba"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (74 corresponding lines): python/pyspark/pandas/frame.py:3832-3935 | python/pyspark/pandas/frame.py:3941-4014 \u2014 These two members are one piece of code written twice and then edited apart: 74 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3832}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe5fbe9af3d5d2167cd794628651ca9466202e95e383274413008a3722f408ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:667-691 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:557-581 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":667}}}],"partialFingerprints":{"codehealthFindingId/v1":"02f01fc3dec7aced7426e9d0f2f0a4fc44cf6a80c3d48fc8f6375a752048bb17"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 38\u002B corresponding lines): python/pyspark/pandas/frame.py:14555-14592 | python/pyspark/pandas/namespace.py:4050-4097 | python/pyspark/pandas/spark/accessors.py:1231-1273 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 38 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14555}}}],"partialFingerprints":{"codehealthFindingId/v1":"82c695c61613dfc0a86d5e99a7e25758816c750adbff3d05e27b4bee6f3fb184"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 38\u002B corresponding lines): python/pyspark/sql/streaming/list_state_client.py:63-108 | python/pyspark/sql/streaming/map_state_client.py:151-201 | python/pyspark/sql/streaming/map_state_client.py:204-255 | python/pyspark/sql/streaming/stateful_processor_api_client.py:278-315 | python/pyspark/sql/streaming/stateful_processor_api_client.py:320-363 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 38 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c345af111fda8b95ae1342acd4ebea8722830d8194c8fb03285f64562b10269"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (45 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4563-4607 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4713-4757 \u2014 These two members are one piece of code written twice and then edited apart: 45 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":4563}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c2102d3004cc181a18a9d55d5c37de93779680f9d794d013c5c1c3752cbffd6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (55 corresponding lines): python/pyspark/sql/classic/dataframe.py:1694-1748 | python/pyspark/sql/connect/dataframe.py:1751-1810 \u2014 These two members are one piece of code written twice and then edited apart: 55 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1694}}}],"partialFingerprints":{"codehealthFindingId/v1":"54c71654d203102465819031d26d5d3652302131cd204ee2f2686f41c0637fdf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): python/pyspark/sql/connect/group.py:393-432 | python/pyspark/sql/connect/group.py:445-484 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":393}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cf9a31b9f8139556abba912520e08fd4cf69628738d81dbca22511b8690cd5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (41 corresponding lines): core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:743-783 | core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:786-832 \u2014 These two members are one piece of code written twice and then edited apart: 41 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":743}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dda5ee700bbb276f105ba2e71610c4244b36f6a8dc894b624702e36a715d210"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): python/pyspark/ml/connect/functions.py:53-88 | python/pyspark/sql/connect/tvf.py:138-175 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/functions.py"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0e2219656cd600715bc6ef782cec44a57311b6c2bb7651a3f6988bea4753773"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1534-1559 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1567-1594 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1534}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e1194b6fb5da1c0fca27ec1dadf7be80d5ee34a08d13ff9e97e3910fc92354e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameReader.scala:164-200 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameReader.scala:276-306 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameReader.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"b54389cd59c0847a5d42f76984bfd212063a6cfa9f569c2688ee598e54a32b64"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (43 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala:102-155 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala:83-125 \u2014 These two members are one piece of code written twice and then edited apart: 43 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"487f73614dcfb3bdc6f309c664702fb2e1d72d757a6759c74a3ed30928b048db"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1142-1158 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1162-1178 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1142}}}],"partialFingerprints":{"codehealthFindingId/v1":"f928c293306156ab2b6e012a7a362849a8c37c36a62ec51c2c9c103512153f38"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:350-385 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:426-462 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2fc8334247f76402f0841797fa4e98503d57aeeac29734358bc8df857a1ab88"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (112 corresponding lines): python/pyspark/pandas/series.py:4536-4647 | python/pyspark/pandas/series.py:4650-4766 \u2014 These two members are one piece of code written twice and then edited apart: 112 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":4536}}}],"partialFingerprints":{"codehealthFindingId/v1":"66eaab9ebbfba1c6911029961cefb7712426f23cbb2cc50fbe39edfd622493c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:304-334 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:288-317 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd57a98e5f48a35480718669a8e1f25794a8dddba2b21fd44f0a7b14120f8db3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:793-828 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:830-862 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala"},"region":{"startLine":793}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8d31038e2f87a777a3bbd6609c0793ad0fb5a659240224dc8a0a38d24625b95"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:355-370 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:445-461 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":355}}}],"partialFingerprints":{"codehealthFindingId/v1":"14161b2ca142fcc2e589fb87ffef97ad713a36844831b38573fb16c5269bc833"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala:93-122 | core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala:128-160 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"80b8c805a01137fedaf690d20710a3fb1df69119d45cd0f7f692a81f885a93c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 15\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:190-204 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:226-241 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:264-279 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a24f4c1a0489168cd404938a2926d0e015a87e1563e849398c65f78d8295b06"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPVCResizePlugin.scala:79-109 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorResizePlugin.scala:57-94 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPVCResizePlugin.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"281c0a9e18631a885fdca41b97622dbd9c75564b146c38d970b5db6c04bdace9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:339-363 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:373-402 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":339}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b82df82a4c04a3ea4e9c0d6cd5d0011f51456543cff494d0719c457a61ea977"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:82-106 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:118-139 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffdd495616c936ac576107a10ed1d439abb8539de7a5ed9ade8eeeb034695fbe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (43 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:130-172 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetScan.scala:131-185 \u2014 These two members are one piece of code written twice and then edited apart: 43 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb350b9701ea6f074e0a0ba16b1621b4dd73e989a188ae3d724bb35c23abca67"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala:248-264 | mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala:156-172 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e2256b32ea23631b09f4c71d064e24f6c3de5597746bb6b9a754588151a219e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (49 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:143-191 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:217-277 \u2014 These two members are one piece of code written twice and then edited apart: 49 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"d95f52c4f7958003325d4c4609686453c3fd8280ad43503398b9eb36cb5328b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:338-353 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:427-443 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"74b1b0cd3729af9ba469e0821923b899c2c20eb78293e0314113f3b8c6894785"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:451-492 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:370-411 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":451}}}],"partialFingerprints":{"codehealthFindingId/v1":"0806d858118d53d85379dcf82aa821d589f857c3d3e1b62b25f5d5ced3c6ded7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:132-159 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:140-167 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"1660272265d5384fcd541342c69838e72b67168749b3fc48d3046c42b2c1b64e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:83-122 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:79-118 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"13f38d8edfae23f26935a0a6ad26ea1809f95db8540818121e22624247ed3f1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): python/pyspark/ml/tuning.py:605-629 | python/pyspark/ml/tuning.py:1265-1288 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":605}}}],"partialFingerprints":{"codehealthFindingId/v1":"167184696adc6f91e4374a728935f8d0a9729c08a3950c3bee57900f32c52be1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (45 corresponding lines): python/pyspark/sql/classic/dataframe.py:240-292 | python/pyspark/sql/connect/dataframe.py:2179-2223 \u2014 These two members are one piece of code written twice and then edited apart: 45 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"395fc99e6f009515e6e21d273ce64ae65c2b7e074a9f42965f63f71ed6f20bdc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:304-323 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:525-549 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"7037a9e96d453eedf801b7b8cfe2589b11d2b5e2cba502d792c536e79113d809"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (43 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala:169-214 | graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala:264-306 \u2014 These two members are one piece of code written twice and then edited apart: 43 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"02e47aa1619c00b33338d4ea7311da37336a16cd13ba4e8a14d2376218bcc526"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:51-70 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:62-78 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"05dcab87e54269e10d3c9bc2d8c71c9ff78df750040abbfc55b2f9e11decbb21"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): python/pyspark/eval_handlers/_base.py:228-267 | python/pyspark/eval_handlers/_base.py:270-316 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_base.py"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c959ed79e31f5bf2e17bd50b138734d0e769b51b8cc9986fd02f348d0e27f83"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/ml/common.py:107-137 | python/pyspark/mllib/common.py:97-123 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbb342dfba15fa1259f922c32270715d117e81afaa40715571e60acbc14f5c9c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (61 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:782-842 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:3316-3376 \u2014 These two members are one piece of code written twice and then edited apart: 61 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":782}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d76732fc8c6904f7495c4b8bedf8f9c8147d81dc15607fadcddca2e43ae770b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:453-503 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:547-579 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"be7de77d5ef5ca04032ac6b747930b433e7ab2f34b7bc835f4753cfa063dea25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (44 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala:216-259 | core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala:287-344 \u2014 These two members are one piece of code written twice and then edited apart: 44 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd0ed9278e128fc5c89f836adb28bf726a3c886042c43ff4b535b7924aadf4d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:150-174 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:167-190 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"cec7cf38023c486696ae43c115e5104ffeb460437e81cbdfbf2692f6b8099209"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): python/pyspark/ml/connect/pipeline.py:187-210 | python/pyspark/ml/pipeline.py:121-142 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a728f1f3d1f0a5c6436a65025f9a7261e489471d48f8c91a927e1e9dea5dcc3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): python/pyspark/ml/linalg/__init__.py:1247-1276 | python/pyspark/mllib/linalg/__init__.py:1442-1473 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1247}}}],"partialFingerprints":{"codehealthFindingId/v1":"753dee1dfd8edf0398ce8e9a1e8854c4751c3fce029c8045aab6238df669e0e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:281-301 | sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:315-335 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"af689f1357ab8a4785ea91f79eb6babf2be49beab5cf159c9e50df9b7f6b6d27"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (47 corresponding lines): python/pyspark/pandas/indexes/base.py:2481-2527 | python/pyspark/pandas/indexes/multi.py:1065-1118 \u2014 These two members are one piece of code written twice and then edited apart: 47 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2481}}}],"partialFingerprints":{"codehealthFindingId/v1":"95b5233d364ee935c609da42035d4e5289d368cb6a9fc153a34e81c8d3abcfdd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:45-66 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:185-207 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"c37c7b28e1dd0548bbd7c4785a3fb50afbf950fafa61102ec4c6cd93caccb023"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:177-188 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:213-224 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:250-262 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala"},"region":{"startLine":177}}}],"partialFingerprints":{"codehealthFindingId/v1":"4119b0b1576a0ed1d38391ff987635c37e178352f1fea535538846587b509c55"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 32\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:538-569 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:600-631 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:666-698 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 32 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":538}}}],"partialFingerprints":{"codehealthFindingId/v1":"898d7902b5e5270a112c23ef19bfc4442d25c55a024c6283ca6dd36f70311731"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:325-336 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:413-425 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"68ffdae1df46da20d8fe28d2cb13664188e5999f00545bc1981e0a3b7ecd9ab6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala:583-612 | mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala:623-647 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":583}}}],"partialFingerprints":{"codehealthFindingId/v1":"d925538c61af011880aac4aad065b7b1b33462324dab2230a298cb258477e561"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): python/pyspark/sql/connect/group.py:302-336 | python/pyspark/sql/connect/group.py:491-523 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"404fa3fca3b97869ffa9c5717c6d2b90e8da9ad390ad90d3622b4a2587e19da7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala:266-285 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala:287-305 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala"},"region":{"startLine":266}}}],"partialFingerprints":{"codehealthFindingId/v1":"482a887f6bac5f48591e2ca3c4ab2656268443bd93ef66cdef61f7436688bb45"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): python/pyspark/pandas/plot/core.py:424-457 | python/pyspark/sql/plot/core.py:536-568 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":424}}}],"partialFingerprints":{"codehealthFindingId/v1":"71426d0f30780b5d92cbf4a5a6814cd9fae0da5e99adf25f5efac14f17a83dd0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (45 corresponding lines): resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala:33-83 | resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala:37-81 \u2014 These two members are one piece of code written twice and then edited apart: 45 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"3164bf9a7b69cf785dbc91a801b745084b9a2fe097fbb89c77b88e6bb9363094"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 38\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:78-115 | mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala:92-140 | mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:83-123 | mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala:85-124 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:84-125 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 38 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"42c4be97e5b849246d591376b028163c430ea45f909df673e0e2d764d4df161e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2250-2283 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2287-2320 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2250}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e3a8cf164dc9bef6660155d8a9373be230c84a25e25f9989a55c48ec8d9b63f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:848-869 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:874-899 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":848}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c500f49d1c167d17baece7c2c9db4bf4d6f6e12d3adcc3192305ea8e6bff71b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:90-122 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:147-176 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"10224b8b4bf027aea89f86e8fe4225345d1879fcac66eb3bae64a8e390fb2318"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:31-53 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:59-78 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c3835aa63b6d71978d58e0329227c3100b250145d58f0f70f2eb6425f1794dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala:191-205 | streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala:210-227 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea459496dbd8da08d45022b51e529ea538b1c84417c185d7cddc95facdbe8f16"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:223-240 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:255-272 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"01ad23938a7c497203aa434b545d89f08648c8884925d52273218613277a45bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1655-1675 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1686-1706 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1655}}}],"partialFingerprints":{"codehealthFindingId/v1":"57083c1036064f4467c9846038b961d51cfe6c89674cd49a8914a7b40f6fdf54"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:105-131 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:197-223 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"385d7303f95477e9afae05bedca524e20eaab21fd275e4cbd1c1c272e171bb48"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:91-123 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:105-145 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a3c29a8f66e07eb82da385b3edaa48397a6cae901a8d73859f292cecbbf4c58"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala:57-94 | mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala:48-82 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee8ca5394e328bce39c362761f82b3acc31db72d6786b99c52e1dd77ac63e952"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:401-446 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:747-786 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"4142a31acea61c50b39de0db34bcb3f2dd5f20514ff05d011e0470f3bffc9fee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): python/pyspark/sql/connect/group.py:545-569 | python/pyspark/sql/connect/group.py:576-600 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d42073da9d66aec77e83f9793aadae49a4850a00e1d3e82341fbfc1705abed7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:288-320 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:587-618 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"44e3bf702bd74d85e3f833d664e6263be9909328d1428af9dfefd75d5c1b4e37"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (50 corresponding lines): python/pyspark/sql/connect/udf.py:316-365 | python/pyspark/sql/udf.py:788-939 \u2014 These two members are one piece of code written twice and then edited apart: 50 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f3ab3220776ddcba3d712b03c52650db1b1cdd4f3e3ba718080eaebae6624a9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java:433-459 | common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java:486-518 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java"},"region":{"startLine":433}}}],"partialFingerprints":{"codehealthFindingId/v1":"20098ee436ab099459b1616a085561c76b957a2b6731cb2e819c2f1105ca65f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala:188-210 | mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala:66-88 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"0571ecad85f939de33f94e46f16506a401224746eb3865050a3a6a68aa2ca9f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1465-1487 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1490-1512 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1465}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c17a62198dc2c8fe1257b7d975bddf3404376ade722e48a441cb1c215eb9acc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:405-434 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:439-463 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"2513dcf6acc6d03cafd7ee7a50a4ca4dc52a23f6ed935dd359dc0a2d4b554184"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:78-108 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcWrite.scala:41-72 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"4607208838f4c6072781fc3a0ef87fc3a4dcd75d90085e152ff90934f8d51c66"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:183-195 | mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:218-232 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"abb5703f77d814ae0ce6a178c5c390635eec2d156f20f42d5af00884575ad3ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala:841-859 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/DataTypeUtils.scala:59-78 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala"},"region":{"startLine":841}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c4d8de07394a5e2f70ae5eabba505525fcda3b2c9598cde599b953a29adf4d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala:179-205 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextPartitionReaderFactory.scala:48-74 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"e766b13d7102cfe9d4086a2e52a891ddff71172f99449244e8fb3745ec189c66"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:83-96 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:243-259 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"5bce404633f6ead69fc10b1a80e3991d96e69859ec8c954a2a239fe8cd40df05"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala:112-133 | mllib/src/main/scala/org/apache/spark/mllib/stat/distribution/MultivariateGaussian.scala:122-143 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"d59d4ae3cff77f1bb91e0cdc96ea4d186888f611f861992550549827416a36eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:519-558 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:562-602 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":519}}}],"partialFingerprints":{"codehealthFindingId/v1":"813b5fdd1ac2e5da28c90060bd6bb1d118ccd7a7008c32c815cfa914f5520b97"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:430-454 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:400-421 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":430}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae449fe45596569f57b5159e775a8188bac03c601df100df1c56c36b08913a36"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:542-551 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:603-612 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala:250-261 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"4af599d27c737b12f3314eb625f72b64f27ecdceefb44cfdd7cc3e54326dc593"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): python/pyspark/ml/tuning.py:1146-1186 | python/pyspark/ml/tuning.py:1706-1745 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1146}}}],"partialFingerprints":{"codehealthFindingId/v1":"edc17c436f898c72b774ec01f66a27a3f6d637418163bd86da60bcbbfb648054"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (70 corresponding lines): python/pyspark/sql/avro/functions.py:37-126 | python/pyspark/sql/avro/functions.py:131-200 \u2014 These two members are one piece of code written twice and then edited apart: 70 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/avro/functions.py"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bf646f9a365077820e1c9738032deba8262f8b76088432850cb731a9771276e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2665-2700 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2702-2737 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2665}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3499c696a7eb80c03835e7016d1fe9ece39bcd50c5892ac5550fb19a24533a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:512-527 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:626-642 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d772f3c8d571c0e271d96bf2d57fa73a6bcc8a795b5b310dc0663673a580ca6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:299-328 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:718-744 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":299}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d85482474bffe3bab718c6076bc27c1c648df94d584c17f517ad1252b7b98de"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:557-576 | common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:589-605 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":557}}}],"partialFingerprints":{"codehealthFindingId/v1":"70cd7c1a374e830e981a4fbf4d365b2bd7e9a1a6ec74cc916ea68337532fc02c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 20\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:509-530 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:535-556 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:389-410 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:339-358 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 20 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":509}}}],"partialFingerprints":{"codehealthFindingId/v1":"6465aa4ce3f647628388778a74ee40a2e1b44f04fd4a07021ddce60423f6a3e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): python/pyspark/ml/tuning.py:1111-1143 | python/pyspark/ml/tuning.py:1672-1703 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1111}}}],"partialFingerprints":{"codehealthFindingId/v1":"851900b30c6863478072ee1d91695f71978662847d1330ce300022b15960cad1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (72 corresponding lines): python/pyspark/pipelines/api.py:138-209 | python/pyspark/pipelines/api.py:242-313 \u2014 These two members are one piece of code written twice and then edited apart: 72 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"fec4563cb428401a59ed62244226de724569705224f4c9d432b36e74d44109ec"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 58\u002B corresponding lines): python/pyspark/sql/catalog.py:321-379 | python/pyspark/sql/catalog.py:646-712 | python/pyspark/sql/catalog.py:770-827 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 58 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":321}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d9b72ad4d040d24fb7a6afaf0c88595db3545b4692b5c2602ddf5b248b93be6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:2031-2054 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6296-6317 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2031}}}],"partialFingerprints":{"codehealthFindingId/v1":"880aacbac40bbecea8cc8915b98088bf26aab4d4d53c323dda6c333e1ea1d75e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala:38-58 | core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala:41-61 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"e00e9a768d6d2ae13be8e7294d44122fc732530773ec3c88d3cc68674095c70e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala:470-500 | core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala:515-545 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"646de0ce5becc6b67f3d009163dad8caa73b8b30d1fe70a7caa7f4e1d2c8e95f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): python/pyspark/sql/utils.py:365-388 | python/pyspark/sql/utils.py:392-415 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/utils.py"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"44af67f438a4add54f396baa16fa4bc78fc09e867b86f2a303fe5c927eaaff2f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java:127-143 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlocks.java:128-143 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4507003510d4085560bed5733d4915eaf938c3452b33a363f645ff1cc4387a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (51 corresponding lines): python/pyspark/sql/connect/udf.py:65-115 | python/pyspark/sql/udf.py:100-152 \u2014 These two members are one piece of code written twice and then edited apart: 51 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6aaeb0a761e708f190114b000119fbf3d1c509e6ea238835ed1a2c9fb68925c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:286-311 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:492-512 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"366cf2ca63139db3dfdbe2503e6f3aff63b0cb21d101c1ac6641f458f75be40e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala:174-195 | mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala:97-120 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"66c8db21666b9b4851cfaaf46b0a990f4eb2f759cb7276540d61b8e4c8f9b325"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:746-761 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:1121-1134 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":746}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d9e7285c7b19577499a615f3d2845cbf9086208b06a904f1d9eda001b4433aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (63 corresponding lines): python/pyspark/pandas/frame.py:14076-14138 | python/pyspark/pandas/series.py:7383-7507 \u2014 These two members are one piece of code written twice and then edited apart: 63 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14076}}}],"partialFingerprints":{"codehealthFindingId/v1":"c31a291c68e69c0be5ba9aaba670ea01b86958f43d6b7d55e404729634f03b40"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteUpdateTable.scala:131-155 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteUpdateTable.scala:196-222 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteUpdateTable.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"1638cd1838beddd5a95c8949222a402700a4a4be854f83cf4241d14b5f4ca324"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala:694-718 | sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala:182-207 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala"},"region":{"startLine":694}}}],"partialFingerprints":{"codehealthFindingId/v1":"27d5956b58c96b7d6864bd98ac15d09be8169b0e4bfee1dd409c729a6de40fdb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:2184-2201 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:2223-2234 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":2184}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8b75585bedfd10e478471def8fc1a24b97b8a8e5941f1721cbccad506a27b57"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): python/pyspark/sql/connect/dataframe.py:420-456 | python/pyspark/sql/connect/dataframe.py:461-499 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"17017b57c5f194571adf40923d493c4fa971aa513ce8784a6022478b2b7d4669"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): python/pyspark/sql/connect/types.py:408-431 | python/pyspark/sql/connect/types.py:435-458 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":408}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5ef619a75af3d6ef8deeb5d4339bc70cdb57b9799479243dc352454e205e432"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DataSourceOptions.scala:100-122 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DataSourceOptions.scala:130-151 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DataSourceOptions.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"32deac2fcd9195b388293aa5ae1cbf25dede0e3781005d856b4c1a29e4ed7eef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 33\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:866-898 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:984-1022 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:1035-1076 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 33 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":866}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d500f50bb0fba8c9e77dbf04e17d33e5795e8ac236049b1ab6d3de7486eef69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:357-382 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:851-872 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"cae80d109575a6c54c11541a9dd0a6303b154b6b1ae5f723b7f9d8538eb0127e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:302-311 | mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:463-473 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"562734f76ec2e46b76d4acc0a35df996699a6371b3dc941c99c6e92b83855820"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala:386-414 | mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala:590-621 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala"},"region":{"startLine":386}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c6c5c4613870614d6245be8fc9d08c94e902a1d6e6d9f9e039d3db716f0ca63"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:186-211 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:212-243 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c02abe36898d3432c6c84898a93494ba2bfd38ad0545a6c013a670eed748650"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:496-525 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:527-573 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":496}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b917131cd0cee75c56e15dc0806018ba3df44b02806eec13b2efd88c8da5fd8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala:202-220 | mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala:222-235 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"afc95225a8861437cfb3f0742d2e77732056c0e38c68071381a89fb07689bafa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/DistanceMeasure.scala:308-336 | mllib/src/main/scala/org/apache/spark/mllib/clustering/DistanceMeasure.scala:444-466 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/DistanceMeasure.scala"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"739a4a37da0c7b5e66134a79b2dbb76b4108eb899366aa24517b0a80bf746361"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4223-4233 | python/pyspark/sql/connect/functions/builtin.py:4248-4258 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4223}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0ceddc4f9be8ce3232ed0c2b3d2c8b9cdc9b4c301a1a9dda8b09a2d6cff625e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/deploy/history/HistoryAppStatusStore.scala:70-79 | core/src/main/scala/org/apache/spark/status/AppStatusStore.scala:114-125 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/HistoryAppStatusStore.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"b41e101a9c5a5cde3b2e4c7a743d361193688ea3825f80c13100b3e6c65bdd61"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): python/pyspark/sql/classic/dataframe.py:706-742 | python/pyspark/sql/connect/dataframe.py:1860-1902 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":706}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0677e94cc855bdf61a75cbc3d10849b99fbf25ef12b83b018209dea308cc453"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:94-113 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:191-230 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a8c679baec70eff47fc6035eb7c45bd68930009f85598fc88eaec03573a7ede"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/linalg/JsonVectorConverter.scala:31-46 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:434-449 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/JsonVectorConverter.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5484fb98faa33275bbd2d44b03e961f59b52ee2d8c2cf1d9e6e8b63b3074b6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:171-181 | mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:204-216 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"b75f1e0428d5d2781a9a1c1b41899b1c1234d4fdeacbfb8a308af5519e99fa2d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java:456-467 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java:476-493 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java:509-527 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java"},"region":{"startLine":456}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb91db6e364c3518941dddeb3f097d0485974b85677718a41d0882a879533ff1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 23\u002B corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:245-267 | python/pyspark/pandas/data_type_ops/boolean_ops.py:270-294 | python/pyspark/pandas/data_type_ops/boolean_ops.py:297-321 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 23 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"07916c29c31e6296a8ca515c966a98379d4ea2b7fc6cada6ca6943906a136efa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:5945-5976 | python/pyspark/sql/connect/functions/partitioning.py:83-109 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5945}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbeda87e639b7e532db4c072d8c0472bd1c2603274b9b6ee88342d0e71ad2de8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:936-967 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:3077-3107 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":936}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bb992169837f753668c28c02d6571a1f1993dfa5a94f3afea6c46e76a9a0ea4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 26\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:254-279 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:303-329 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:341-368 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 26 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"789bd8200f6735e9a06e00b6fc82e4cf09c5022825702015a79a2244a44770da"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1796-1823 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonUDFRunner.scala:120-148 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1796}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9954b7bfc23bb76e151151bdd599240674defc38b6d22fa686726fe066b7951"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala:124-137 | mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala:114-127 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"35604c53ed8dabbc4e58bbbe8216e7e2a4c89999ec9e34313758b03f95a8b696"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/ml/common.py:81-103 | python/pyspark/mllib/common.py:76-93 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"31e8ac9edb87d5a6e0494997ec146f42d70d28421a112977949b6950a4fcd6ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): python/pyspark/shuffle.py:292-314 | python/pyspark/shuffle.py:329-353 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"743a75a7ee88703d76985df83b9c45dedec93d0cfadb9b5f368ca01d94a16f89"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 37\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1784-1822 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1827-1886 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2096-2132 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2137-2184 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2189-2234 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 37 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1784}}}],"partialFingerprints":{"codehealthFindingId/v1":"eea28795a68c0ef0e5bf787bfcb27f7433978a43370222f5b08993092b623946"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 17\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:162-180 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:214-230 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:264-280 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 17 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"990279e10fa9a35c6f9f79dbb5f5510551cbd926740e97678b670636055c7c78"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala:718-756 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala:1026-1059 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":718}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceb9b1ab589c24f5989a84897df09a089ada49fc74e93367900031102b70d1ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1675-1692 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1694-1711 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1675}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb3dfca198c5856fc6db4cbc87ad883457630cb178777c61a672bf0ef46ad2f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/sql/connect/readwriter.py:1086-1112 | python/pyspark/sql/connect/streaming/readwriter.py:773-799 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":1086}}}],"partialFingerprints":{"codehealthFindingId/v1":"c439b933b44e330e972c8ccc1487079c59c8eac3441231ca847fd6880affdf4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:423-452 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:1014-1051 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ef41ddc5bd2ca40546a7189574a256f978754600ba63173eeeaf4daa0bc89b8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:1472-1489 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:1506-1525 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1472}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cdaa19fbf678ac7e185ac07e1027b24ec6f12c9366ef5022989cfcae28b5a74"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 19\u002B corresponding lines): python/pyspark/sql/streaming/stateful_processor_api_client.py:204-222 | python/pyspark/sql/streaming/stateful_processor_api_client.py:227-245 | python/pyspark/sql/streaming/stateful_processor_api_client.py:382-403 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 19 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"779bd67f1d19138824b8326e1b05b91184862f88dcea3d891915b81067162fd1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:792-816 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:820-843 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":792}}}],"partialFingerprints":{"codehealthFindingId/v1":"caf3c17476ec0f21ad08075cecd3a69cb4dc648d62fb1661dbfcffb615da616a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:550-571 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1030-1051 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d26fe081ddcd8ff4df890cc6986ac4b536d3a2f67b0e75aa3533258ed685d0e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): core/src/main/scala/org/apache/spark/rpc/RpcEndpointAddress.scala:53-73 | core/src/main/scala/org/apache/spark/util/Utils.scala:2513-2532 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/RpcEndpointAddress.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d841ba5bd62d684483343f88b668b3d956f355f5fb68dd861c2040ef13220cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:247-266 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:281-300 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6b6e73b526698326c58ee5c5bc93e11390ff47287c353de519b01d54e4c463d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SQLFunction.scala:383-395 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala:490-502 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SQLFunction.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9adedabc9c552da28ed6dd774c215622c8e62345f0bcc4ecdc719bd4a05cf6d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsExec.scala:66-100 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala:64-99 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsExec.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f22378173e99c203277991af533d0925c798ef89f094f36cbcf592b2a4c449d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousTextSocketSource.scala:170-203 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/TextSocketMicroBatchStream.scala:71-101 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousTextSocketSource.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7ce639d96add98c41986dd8cb432b85051591a03e3669198360ada8fd94cddb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:296-319 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:328-351 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"ebca7e266dfd84568300bbc2f6d5e377b867c2871a560216a418efab402539e4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala:254-268 | mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:174-186 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"04a2b26eeda23133791c8f262784a07c7a09edd4b8d6ef44e1da251025eb61a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:218-231 | mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:237-248 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":218}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b4764bd2f51978a99464c3d15f73a8bb87434807e14cce661b6c9867bc8e0c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/pandas/extensions.py:360-386 | python/pyspark/pandas/groupby.py:5034-5061 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/extensions.py"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"655418ff51cc5d23e1ee60fc04b9c1849296578e1303e8e8255d93c0d26d1a67"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 22\u002B corresponding lines): python/pyspark/sql/connect/group.py:609-637 | python/pyspark/sql/connect/merge.py:229-250 | python/pyspark/sql/connect/streaming/query.py:472-496 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 22 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"3eb3f930bbad76b46342bd17894146ce0525351f8c3b347c188fcb493ffc4d72"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4422-4450 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4452-4488 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":4422}}}],"partialFingerprints":{"codehealthFindingId/v1":"19ce8a261fdb81413f67104921d52621a2aae8054d25e1aa3e60078102cebab5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 24\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:615-643 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:726-749 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:832-855 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 24 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":615}}}],"partialFingerprints":{"codehealthFindingId/v1":"506344a14cd4d9c8d1655e85d12e43bf244664f9a96fef640964cf518646e440"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:176-201 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:268-295 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"baa23d06bf69682eaab0851250813879dead9a9f2fdd0b48f3143f33554ebb11"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:369-392 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:451-474 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dcfe20debed6e9b8461f3daf03857f5b9308036e977228f93bfd13e912df1ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): python/pyspark/eval_handlers/_stateful.py:425-450 | python/pyspark/eval_handlers/_stateful.py:575-601 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f7d3f6c06b7fb73bbf7deed77c43d8062da09b775efba19e9c4ce7b7b64a05e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 24\u002B corresponding lines): python/pyspark/pandas/indexes/base.py:2656-2687 | python/pyspark/pandas/indexes/category.py:642-665 | python/pyspark/pandas/indexes/datetimes.py:869-892 | python/pyspark/pandas/indexes/multi.py:1266-1292 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 24 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2656}}}],"partialFingerprints":{"codehealthFindingId/v1":"b50308d36cad4e074cee03c2b62a0047aa7fa7112a1d4df7c6f1731c16916044"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 19\u002B corresponding lines): python/pyspark/sql/functions/builtin.py:34922-34948 | python/pyspark/sql/group.py:536-557 | python/pyspark/sql/pandas/functions.py:1034-1063 | python/pyspark/sql/udf.py:1024-1042 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 19 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":34922}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c6b836bda21e6ff32645f7c443cf547a7b4e31aa2bf801f992635bc96a0e03c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (79 corresponding lines): python/pyspark/sql/streaming/readwriter.py:391-480 | python/pyspark/sql/streaming/readwriter.py:826-904 \u2014 These two members are one piece of code written twice and then edited apart: 79 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"28c0399be6a7bed1d649b87877b3bdacfe1739014000841cf33b78e85be4c243"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:2791-2810 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:3179-3192 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":2791}}}],"partialFingerprints":{"codehealthFindingId/v1":"68c25533ce6caeb0b7662e9a8cddee38afd03ed557056d713420836d5105ae39"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 31\u002B corresponding lines): python/pyspark/ml/feature.py:1211-1247 | python/pyspark/ml/feature.py:4817-4847 | python/pyspark/ml/feature.py:4858-4890 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 31 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/feature.py"},"region":{"startLine":1211}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0e31234cf27f7d5a13479d5f15627788f594fb09ec8c2659777dfc1f775b6fa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 32\u002B corresponding lines): python/pyspark/sql/connect/streaming/readwriter.py:189-223 | python/pyspark/sql/connect/streaming/readwriter.py:352-394 | python/pyspark/sql/connect/streaming/readwriter.py:421-452 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 32 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecf02d54764aa7b02b92dc556ce27bcd416939a4f221db7135b8c64f400d17c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:564-598 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AQEOptimizer.scala:50-72 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":564}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf11e284e19f7c9ceca2070a7494005a678a79cec085a835696d7ae453310b54"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala:111-128 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala:251-268 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"16770c4c30cb15dae34766f96d6114998df6032acf7dd32e2c5a9dfe7fb0cae1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala:2008-2042 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala:2084-2112 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala"},"region":{"startLine":2008}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ea8df6c080362b2fdfbb61061a8e3a7e4626a0d3a34dcdc59e3d4df33534e69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala:253-266 | mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala:345-358 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala"},"region":{"startLine":253}}}],"partialFingerprints":{"codehealthFindingId/v1":"af8480bc0e50c4e67486071c56d6fcce4b2dd48b3f07432005f33b9178f569df"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:62-79 | python/pyspark/pandas/data_type_ops/boolean_ops.py:96-112 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8fe20cd37d439e407510cfe646c143689697f0a05d0135673a7da0737a4fc69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): python/pyspark/sql/classic/dataframe.py:1337-1371 | python/pyspark/sql/connect/dataframe.py:1232-1267 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1337}}}],"partialFingerprints":{"codehealthFindingId/v1":"040f3f3d2c62835b1f22ccfb7afa6b63cdd227db2eae75b32346b5cb14cb1821"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala:227-250 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala:252-275 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"3604dbe48df58b644b9e9eeea9173c5c8789b2443fa95b6197dae8d618699a26"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1452-1464 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1510-1522 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1452}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad6c553bdf9b80352f1898b6c134bec6adc44d1b4dcfd88433205e7ef06b92dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ml/VectorPosExplode.scala:229-255 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ml/VectorPosExplode.scala:266-292 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ml/VectorPosExplode.scala"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd144c906cc525159921317539297a16d0b70808956691804dd0ad3ba7da901e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:407-422 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:390-405 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":407}}}],"partialFingerprints":{"codehealthFindingId/v1":"f98eea7fa83352d78e2dd09467da3c58d592356580d8ce14a3edf6780b40b2be"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (181 corresponding lines): python/pyspark/sql/pandas/group_ops.py:121-308 | python/pyspark/sql/pandas/group_ops.py:775-955 \u2014 These two members are one piece of code written twice and then edited apart: 181 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/group_ops.py"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"d463b7216bd9b314dc2df43b0ce9d2678a5f8751c4d7262230486b4de0b6b9ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:751-780 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1126-1152 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":751}}}],"partialFingerprints":{"codehealthFindingId/v1":"584ab5435965f52b121a87d29afc015d6941442a0e692661f294e71ec0a8803e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala:253-281 | sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PlanExternalUDFs.scala:72-94 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":253}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7c60879ef8743d17c27393a87fc499910e8c18bdb4a5fa0e854036fab503162"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala:716-735 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeTableExec.scala:107-124 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":716}}}],"partialFingerprints":{"codehealthFindingId/v1":"e57951e6763d060703bf6b37a28720dca74375a0607102da97db91908ff21508"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:920-942 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:944-965 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"b96612e2d8af6ae724c5c7d094b593cbc5f67f0c82b8f7230dc120a90e089005"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:263-281 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:295-313 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"a863a206c077f093343d9cafb31faa3f7396adc023cd9940fbedc76b43d63d3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala:149-171 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala:122-153 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"f57071b525b2bc25a55bf88d90b43392398f984095c7cc7ef674f3bb6fcd26ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:483-494 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:416-430 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":483}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd806282bba079d0190bdf7816f3a867f763c95fdf9a2ca0731114bcd7997eb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:265-281 | mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala:235-250 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b08eea86e6eb550fd2033d6652bdcb19b459fec6dcf70bee032afd5e3c6e5ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:2838-2864 | python/pyspark/sql/functions/builtin.py:16656-16738 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2838}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a7097a155a622a24f44550193fe72221284fdd4df1ff2a81efcaa856d2b8764"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): python/pyspark/sql/conversion.py:615-653 | python/pyspark/sql/conversion.py:1257-1281 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":615}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8f1932ee4ba57c2939f95fe80af0e2cf977dc86a6fb8e990bf9e2b05325996f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:620-641 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:1168-1198 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":620}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb7e24e4e2d1decb8a63fed63e9128a04237e4da72361f14eb45cc477aee9dc4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:477-496 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:563-582 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeae705ed1255a9ea999d64a6a4ecf381fecb645e7634603d2405b009a6c862c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ThetaSketchUtils.scala:80-111 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/TupleSketchUtils.scala:232-262 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ThetaSketchUtils.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"24ec03acf8ba8bd4f5114d46991ac693bd0f684b163877f379b5ce33f050bf7b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1455-1480 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1649-1684 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1455}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea94e28e9cb520af60a91f97dd7b1b9079e514b34215eac102f286d1e00efdba"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 27\u002B corresponding lines): python/pyspark/sql/merge.py:225-251 | python/pyspark/sql/readwriter.py:2620-2646 | python/pyspark/sql/streaming/listener.py:1120-1148 | python/pyspark/sql/streaming/query.py:782-811 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 27 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/merge.py"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"37285d9ebca73e832d49a76116adeb60f3100c412de5d5401ec22daafa1b163c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): python/pyspark/sql/profiler.py:335-363 | python/pyspark/sql/profiler.py:377-411 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/profiler.py"},"region":{"startLine":335}}}],"partialFingerprints":{"codehealthFindingId/v1":"622d3c06d6f0da78f5146e7de2f57ececd8148b9a667982fb860d7feb77432fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:181-204 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:653-675 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"0350f7104ed89dd88627be80c4177caef481540b372f26d93d30b327238e4d19"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:1352-1381 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:1660-1688 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":1352}}}],"partialFingerprints":{"codehealthFindingId/v1":"d94222fe6c6d159182f6ee882035ca98e4702a4c6b525e6240ef6de7962ca37b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala:110-130 | sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala:142-159 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e8938589cd0beb9d8557c7c9a946a31685162e097e608906473e0f63206457b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala:139-169 | graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala:115-138 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"65eed0d2e29b4f20caa08ecafa2913661d7a4d422540db4b0c707934c82e813c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala:74-92 | mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala:69-83 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9036739ac6103dffddd28e3f1957ae580586bd04610d6f97fab98ffebf2f064"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala:144-158 | mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala:134-147 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"d508a0b89c1ead58f4ebab2158d9558d4c883287bbfb66292b5be1e397efbff5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/pandas/frame.py:14156-14173 | python/pyspark/pandas/frame.py:14176-14195 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14156}}}],"partialFingerprints":{"codehealthFindingId/v1":"81b96cbf5794d55d2ac10cbcb36bea72eef8c8f93fd33b73865b4d596cfffbfa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:458-477 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:479-494 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"620a208f13163c90455be026845aad8bc617c9b014e0816902256cd65937d060"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:679-697 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:719-737 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":679}}}],"partialFingerprints":{"codehealthFindingId/v1":"f21378b8e62562638c46d59f8149c69b0cb01e1f73b08259d6ae4acdf291c97a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): dev/generate_srs_registry.py:165-196 | dev/generate_srs_registry.py:200-228 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/generate_srs_registry.py"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1a06526c0b1df4f6d3cba9a3e78a8404ae6d4bc0300b19c41c9e09c41312624"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala:118-138 | mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala:149-173 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cd80e7927b938633b2c77a00280a3366c993c01d5aa9e007b283d73bba513fd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala:82-96 | mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala:235-249 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9fa2582099d093a5ec6760b35b3332a962478c594a957bced43bb0a9077ed97"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): python/pyspark/sql/connect/dataframe.py:533-563 | python/pyspark/sql/connect/dataframe.py:568-597 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":533}}}],"partialFingerprints":{"codehealthFindingId/v1":"6494fbcb8ce433a18729995e16fd2f19518c8e5b58989b4febe946fc3985a554"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): python/pyspark/sql/connect/dataframe.py:888-932 | python/pyspark/sql/connect/dataframe.py:1714-1743 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":888}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8b882d51efda58c56ceda30eb8fb73fe3fad90b85a843254c3f0d85c7e1b342"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1000-1042 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1130-1171 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1000}}}],"partialFingerprints":{"codehealthFindingId/v1":"b943b5d8680f4edd027ff129a946d50fe213d05afd9f30ae0248477fdba7dbd0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala:940-964 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala:976-1005 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala"},"region":{"startLine":940}}}],"partialFingerprints":{"codehealthFindingId/v1":"603d0eefdcb053f76dcb76e30615f0f2352bfe78f078909824079e4c1ad23fc4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): python/pyspark/sql/connect/udf.py:223-246 | python/pyspark/sql/connect/udtf.py:176-199 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd4a36996682e8c3da4823f231d2eb61c4ed815e7843a74c6f19a4678ea5858d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala:672-692 | sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala:160-180 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala"},"region":{"startLine":672}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b6e6041886b29f75883889aee4512eb739d778db9c357460dae4ff6f7ca0e15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleClientHandler.scala:110-133 | core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleClientHandler.scala:135-163 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleClientHandler.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5fd034d642ce7c38568563b1772ef3a7de88cf44a0809c93e32eff5efb64eeb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): python/pyspark/sql/connect/catalog.py:152-163 | python/pyspark/sql/connect/catalog.py:195-213 | python/pyspark/sql/connect/catalog.py:360-373 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/catalog.py"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"a23bdb5158d36a238eb43fe58ee1d49fc87b7d5b0896e3dc7b0106e89240723b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:237-246 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:476-488 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"00a360d54de62648af93b3141445b462266e796e19e0e92f118801a7d402c8a9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:112-138 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:376-401 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c77e3ae0acb9e9d0244f918c784a9424848c0feff6b84b209e083973236d552"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:234-253 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:269-289 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"23946a2da1da21e97f50f374b656fad9623db33026feb007df39faa6067794e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 23\u002B corresponding lines): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:247-276 | sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryPage.scala:91-115 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:446-468 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 23 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"81657cf98da9f14bc514043d60274002e9163d47f9700a810ac4bd0268bfdf4c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala:54-68 | mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala:90-107 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7017a979eb19e5e1193e9e51cb473556584e1273f0f13b05e9306219c175e15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (101 corresponding lines): python/pyspark/pandas/generic.py:2590-2690 | python/pyspark/pandas/generic.py:2693-2795 \u2014 These two members are one piece of code written twice and then edited apart: 101 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2590}}}],"partialFingerprints":{"codehealthFindingId/v1":"8918db140639ec6bbe1f7b212b0b8d8e8151663ca9d57bf462777b7ed36def8a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/pandas/utils.py:512-533 | python/pyspark/testing/sqlutils.py:183-202 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/utils.py"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c548e6e30e56629218f7389a103a36e9284aca0f4b0519d455516afbad99d27"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 14\u002B corresponding lines): python/pyspark/sql/streaming/map_state_client.py:73-93 | python/pyspark/sql/streaming/map_state_client.py:128-148 | python/pyspark/sql/streaming/map_state_client.py:258-271 | python/pyspark/sql/streaming/value_state_client.py:79-94 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"80699e65189c34a90687ed47a33a7c21783c39ff9206ee5178129c128521a473"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:500-526 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:530-559 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":500}}}],"partialFingerprints":{"codehealthFindingId/v1":"55b9c39d2fdcfc516c634ddc6be40e0c796593f34d3cbf8c905b0c7547cfc526"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:762-777 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:427-443 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":762}}}],"partialFingerprints":{"codehealthFindingId/v1":"41ce6bb0376aa236dabfd0e942bf4394b3bf13c8711e6d3fee8596026ae2a541"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:419-440 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:908-929 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"947bb3480106d50d72e28b6b7b403148a6116c9e5f874a526c0307878941cc86"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:334-359 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:379-404 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala"},"region":{"startLine":334}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcae54e5b4b09f9e229cb9fc8e9dd042d1ec9d4b93ffd01f80c66be43f0bcf60"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:914-925 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:932-943 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":914}}}],"partialFingerprints":{"codehealthFindingId/v1":"db1c3e264674a40c50cd4d5c850db40a5889ea94e8d7c0c2c5084a7fcf9689b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala:110-132 | core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala:134-156 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"862fc91bae492eb7da47416bf5fbd6967110b4b77c141bc3f56c526602ba22c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:374-393 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xml/XmlExpressionEvalUtils.scala:32-46 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"41060db476bed1502f867cf00a2602ea3fee840b66677b1d2c7c77e721183c83"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:687-710 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:793-816 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":687}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecff9200413b051350626e6e6cbcd75c596854821763f45dbba0e19705d94cb5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateUserDefinedFunctionCommand.scala:97-111 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateUserDefinedFunctionCommand.scala:119-133 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateUserDefinedFunctionCommand.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"00aec3e6e710f962444d4cb9e124d8fd5a37be4ad1a81e68b2b5c50da0be2c2f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DropTableExec.scala:47-70 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DropViewExec.scala:40-62 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DropTableExec.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"4182a57101c27d946e9ffef27b5663da139b488cc7fb47113310328379446556"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:156-169 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:206-219 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ea6d4b6d9b841943519a8c874cfcf717469bdca2fe777c1e386d82e85870acc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): python/pyspark/ml/linalg/__init__.py:410-448 | python/pyspark/mllib/linalg/__init__.py:465-502 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":410}}}],"partialFingerprints":{"codehealthFindingId/v1":"adf973577c8fbb9c190c7dab8bd2aed8f1500b3e7220c7b2ce2b27deb21fe0eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:144-162 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:168-185 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ab3bd1d0c1bb93845b0a5cbfcb0cb46b9fdeaac8617c262fbde7f014ef5ea32"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 15\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:452-466 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:468-483 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:485-500 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java"},"region":{"startLine":452}}}],"partialFingerprints":{"codehealthFindingId/v1":"66cc080b9676d5d3b9f54293a48ccf1984ef33a6555c53c982044b612e919077"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 10\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Check.java:95-105 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/ForeignKey.java:96-107 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java:70-79 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Unique.java:77-86 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Check.java"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d422950c019092aac63496f8350be50793817074a7b4b412f15dbeeef6869fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteDeleteFromTable.scala:70-97 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteUpdateTable.scala:95-125 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteDeleteFromTable.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b524971a938729f3c4c89085af0bfcccd956a68da1b925bba5804ff288f5e66"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:391-403 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:471-483 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"2519dd8aa4e1e30ee7aa82ff9a5fb45490ab96b5609c2a58553e4ed83531910a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/window/SegmentTreeWindowFunctionFrame.scala:243-273 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/SegmentTreeWindowFunctionFrame.scala:275-308 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/SegmentTreeWindowFunctionFrame.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"002ca18de9ff8a3c7cd224fa62c14cdb059b76a1bb1c8a754872b8855016abe8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:701-718 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:199-219 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":701}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb42610107a2a373f463ea99fd7dae0e1ac597e89d4f7a384133f1590ddd3d4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/pandas/config.py:505-519 | python/pyspark/pandas/config.py:522-538 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/config.py"},"region":{"startLine":505}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fae10e46aa18d02851ec2fc6c006b933c8cd3e73065706f7b783de9e9a7e081"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (128 corresponding lines): python/pyspark/pandas/plot/matplotlib.py:654-781 | python/pyspark/pandas/plot/matplotlib.py:816-945 \u2014 These two members are one piece of code written twice and then edited apart: 128 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":654}}}],"partialFingerprints":{"codehealthFindingId/v1":"b174e0252d7d0b6ee81f439c457b0e4096ac554d594175658ec532a04eb3199a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/sql/pandas/conversion.py:1120-1137 | python/pyspark/sql/pandas/map_ops.py:108-125 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":1120}}}],"partialFingerprints":{"codehealthFindingId/v1":"be9260f8f821739deb1014fb987bda414b95b26676b79ce93247db7feecb2781"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/EncoderUtils.scala:104-117 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/EncoderUtils.scala:122-135 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/EncoderUtils.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"09c717a99baa3fd98b9d5c62a70e9af3d769527cd762d750f96314d7204bb095"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:975-998 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1107-1128 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":975}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed482f225d5b67c5813f9bcfb210dbd9dcbb0520441941fb8847dfad697a731a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:177-195 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala:257-274 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":177}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d3b5d546b6ec516ecfddd239a21138b3a2d319951cff88d2ddd3ada9243788b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:81-108 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:231-260 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d3fb088ef718310c346084d19ac1e8e3fe0ab6862453b4871aa9b65f62f9694"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:585-607 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:619-639 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":585}}}],"partialFingerprints":{"codehealthFindingId/v1":"904afe509cef71c3b110a212d7dfc90a82a842a788bfad5cdc65ca9ddc20966a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (49 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:477-526 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:644-692 \u2014 These two members are one piece of code written twice and then edited apart: 49 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"d92426e8289a0cb21fe52df7d9f993df7ab94ad0fd0f0afb3f96275d16c998b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:1672-1692 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:1698-1715 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":1672}}}],"partialFingerprints":{"codehealthFindingId/v1":"d845cf8e83a9bd65ad29fd9c98925f9b31e02085b6e43a71fd790222067b68cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:365-383 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:362-379 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"7601212f908a60918ec1d128dc631453cd433b86cb5ff7ac9b04e2b99253e77d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (49 corresponding lines): python/pyspark/pandas/namespace.py:1431-1490 | python/pyspark/pandas/namespace.py:1497-1545 \u2014 These two members are one piece of code written twice and then edited apart: 49 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1431}}}],"partialFingerprints":{"codehealthFindingId/v1":"19ae9bc48dac658f8f39fdd3a26ce4b8570315fd6e7c598d1ab371511ef4f75f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 22\u002B corresponding lines): python/pyspark/sql/catalog.py:1578-1599 | python/pyspark/sql/session.py:2604-2627 | python/pyspark/sql/streaming/readwriter.py:1944-1967 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 22 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":1578}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d89b4b8ab81e4f503da622114b90779d19817647762607a8488f9139e485c92"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): python/pyspark/sql/profiler.py:440-467 | python/pyspark/sql/profiler.py:470-505 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/profiler.py"},"region":{"startLine":440}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f2259f96cbddce718c472a3c789d8e7796f5bc27b4e9238eef0cbb62667044d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:626-642 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/AnalysisHelper.scala:167-186 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":626}}}],"partialFingerprints":{"codehealthFindingId/v1":"e01b8c3017415491b9f5d0a1cfedafbdd89edd5dc0fb1eb3494ec20c29a66653"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala:219-240 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala:246-272 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"e694fa27921f6ff4136f93478702a271d76aaab111ba326dc899e5e9b03db910"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/ByteArray.java:221-241 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/ByteArray.java:250-269 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/ByteArray.java"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9b3c79fa29ce95c83533026eb367c0c6a8d7033ba9e4ba7f69434cb4ff2927f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:128-143 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:155-169 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0b51dc5c9188f52c88bf9bf4a826be684993bd941eedcdc21a8640d386024bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala:53-65 | mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala:49-61 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee7c886c1329c243f64b3b3acf77c022ee67804a5baa11224d321a75f470a590"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/sql/classic/dataframe.py:599-618 | python/pyspark/sql/classic/dataframe.py:623-645 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":599}}}],"partialFingerprints":{"codehealthFindingId/v1":"60c76702ace292ef79b3be6c064ba18b7b309059760a5c16ff275aa11aa0cc23"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): python/pyspark/sql/classic/dataframe.py:1394-1418 | python/pyspark/sql/classic/dataframe.py:1421-1445 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1394}}}],"partialFingerprints":{"codehealthFindingId/v1":"99b3bc7ddbc729d7e24def9ab787304e0424f5dced2acfee518dc2fa1d615516"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/ExternalLookupJoin.scala:391-404 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ExternalLookupJoinExec.scala:78-91 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/ExternalLookupJoin.scala"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dc1be44d158ffe4572681fcd8bd8b128f3552c4922a3b1bac596579419955bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): dev/merge_spark_pr.py:889-900 | dev/merge_spark_pr.py:904-917 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":889}}}],"partialFingerprints":{"codehealthFindingId/v1":"188034ca58892d48c525d056765842d01d2e3b67b59be6f9ae68aa34016a34bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala:114-133 | mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala:120-139 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae1035f87c3fe80df020ee53a068f58e2d13fa6ec005f08c9438ac65ec6fa3b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/connect/streaming/query.py:84-98 | python/pyspark/sql/connect/streaming/query.py:219-237 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/query.py"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb6a5849c9bad57a5433a7f03ad85bda19ac49e0cc89e481455bcc1d458c99bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:86-98 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geometry.java:86-98 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d08989cdc810a647a1ad8d81fc1968c0e8950d5918be3d675295024c3a58b64"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:1236-1248 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:1250-1264 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1236}}}],"partialFingerprints":{"codehealthFindingId/v1":"32aad8ba8a163fed63b4035dd3a87b988f066a6c85f51d9b8cfac8ed8b2efa0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/package.scala:66-94 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/package.scala:108-135 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/package.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"03a2554882cf6a9cc9a080595bcdfe2d825a66ca74c2da6175d42bf88fbf9ea7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/catalog.py:137-145 | python/pyspark/sql/connect/catalog.py:182-190 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/catalog.py"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b420cec68b72fb65a9105909cbe7705b4c12500f750358e6452f45223855954"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:529-541 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:548-557 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4b6a80ec6ab7f17cb969c799e1b08e5997b478facb361c7cb922a7f0cb7fb4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala:182-203 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala:210-232 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcPartitionReaderFactory.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"d87729fd2125538aafdecf9b851ae7546829ff7b96c723172c00b4bf2cbe70a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java:104-119 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java:136-153 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ded9967e183e09230e316ec85046c4b50df6b028d6d772f82f2734dcd0a6380"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 13\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:105-117 | sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:122-134 | sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:140-158 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a9cda17588669d2dfe833ee171ec6cf7e32b75929b9cdfd17d67d9e737c9c24"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1433-1453 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1619-1647 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1433}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b77507d5f5deb39bfad5df71a70fd228737af8c18c7fee2baf4d84598af7f23"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:244-255 | mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:419-429 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"5721935455fc70e9e95f3228ef9279bfc988b25094841d88c999722d842a86f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 15\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala:59-73 | mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala:59-73 | mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala:59-73 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"78c5ca64ea22ba21c8331a11a6feb2ae043eeb23183a15b861a02e7128d145ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:491-519 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:521-549 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":491}}}],"partialFingerprints":{"codehealthFindingId/v1":"a57dbbed21647cea8b15d66b90d9edd81ffb87bfeac86d33d702ad10a49cf178"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala:111-126 | core/src/main/scala/org/apache/spark/rdd/SubtractedRDD.scala:71-85 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"629714b1db647528684779feb7f7d0b6dd7b04f2923adea78442f69b0d0d1e21"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 16\u002B corresponding lines): python/pyspark/mllib/evaluation.py:70-85 | python/pyspark/mllib/evaluation.py:146-161 | python/pyspark/mllib/evaluation.py:285-302 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 16 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/evaluation.py"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"49a63ac40507629c0b533a8a5f6d48afb7983eac031bbded2415981ca47ea250"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (45 corresponding lines): python/pyspark/pandas/frame.py:2002-2060 | python/pyspark/pandas/series.py:6290-6334 \u2014 These two members are one piece of code written twice and then edited apart: 45 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":2002}}}],"partialFingerprints":{"codehealthFindingId/v1":"0741532d6706f564c33f4683efffe8881f74cf2ea20b427d3cabef12d5862c2f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/sql/streaming/map_state_client.py:274-286 | python/pyspark/sql/streaming/value_state_client.py:97-109 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"0292c6e060797975f1eb67ae705ffdf38ce4c8aa69dac9693b444589c33f7810"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbUtil.java:59-72 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbUtil.java:86-99 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbUtil.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"412eaa57e01aec32297871700b1186b5e949e333a6d40dcfe88a4d13cb064ce3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 26\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HistogramNumeric.scala:94-122 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:922-951 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala:771-796 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 26 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HistogramNumeric.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"db80621feded1a2b199a8904ee4f238a000acfc5860dee1eb9057b727aec8af7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:781-809 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:3109-3134 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":781}}}],"partialFingerprints":{"codehealthFindingId/v1":"c801e997c50fd7367e89aa707df16b3b8e3312bd9759bbf25ed663bf7ec7aeb6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:601-618 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:653-668 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":601}}}],"partialFingerprints":{"codehealthFindingId/v1":"bde98dc12a0b19f6d4d5992d97a8b4a65ad657c987da96501e2d77c97ea97d75"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:460-482 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:494-515 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":460}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee6ef25c0a0cdd92797e9be1974734eac4ef56efd7774dbd196d1bca658315ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:359-366 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:375-384 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:393-401 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d4624668178765a41954fcd475c21af2970ab9bab150e78806ff014f0b9ca81"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala:64-79 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala:157-172 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"31b15219197dfa9df6b0bcacc33dddad8db4bf722a2ab738f52dcfbd01b7a2ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:76-95 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:84-103 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"a318869a9bcf75c9edcbd3623fa0548d4b0f0674a6e7845178f6cb2803dfad72"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:259-284 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:461-472 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ba0f6cfd5c6f9973113907fad8e9c102130e881312eed7c99b3b87757605d4f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java:66-88 | common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java:92-120 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad5255ea2d09166950d32f2ff74a58fd16890ce3dd697f1237ecc290b951f20a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 16\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/StructType.scala:460-475 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:151-171 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:493-513 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 16 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/StructType.scala"},"region":{"startLine":460}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd7622e8a0c39c4f519af91c2091002697087b306ec1e519cd7b9974a4777326"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:996-1012 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1024-1040 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":996}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0e70fbd30f22a2b7e0be04f136f208f5fb95498dc790c1673454bc550248a75"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:191-207 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:235-251 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc44e920136e5624c7cd7b334d4f9280d101448c3627b767f46deb1db745dc7e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/sql/classic/column.py:687-707 | python/pyspark/sql/connect/column.py:636-661 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":687}}}],"partialFingerprints":{"codehealthFindingId/v1":"d43260338b79484529357057647b256d83d5c5e29146a4bdd3472d23331ff746"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/sql/classic/window.py:130-149 | python/pyspark/sql/connect/window.py:159-184 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/window.py"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fb0c1a6ed4ff837df6715d30eec7d1f9377e999fadc4325cb51b6893669c2cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/sql/connect/streaming/readwriter.py:139-159 | python/pyspark/sql/streaming/readwriter.py:307-363 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"2729525757ce18c7d24e2fafcb16d2eebb29b62a2546e5a6ee05c0c834d8173d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 21\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/kllAggregates.scala:881-906 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/TupleSketchUtils.scala:113-134 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/TupleSketchUtils.scala:179-199 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 21 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/kllAggregates.scala"},"region":{"startLine":881}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a641297321bcee16e695904ac2720ae5fa5bf3aa35951fc21875063e18e93b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:498-513 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:823-839 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":498}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbd653dbcb9025043840b11124cbd8f252d346a8ab00120894d8f5143c2a93f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:2861-2879 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala:1385-1405 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":2861}}}],"partialFingerprints":{"codehealthFindingId/v1":"577df9e2d045e1997bb7de2b91cc653969b3e6cb7c82406e029e7f9eb94a9e46"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 13\u002B corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:152-164 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:261-273 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:409-421 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:429-441 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:476-488 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"78c6b9ccc84021a02f276fed06bac22c1594b9c9430916d97f8ffa0bc398524f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:322-335 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:282-293 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d2da9f129de4fc599f22bb11d4c4be3d3006fb40872f1738cb95928c66eefaa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:73-91 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:104-120 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1ff4335db43d2cf6ea3fbacef5f8278a241e212cd1aa39e039c793f07ae06e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:467-480 | core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:482-498 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":467}}}],"partialFingerprints":{"codehealthFindingId/v1":"72bb26096d5052318f65ac071282c0c7aa040196fdc654cb6f202d2c2a6bf5d8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): python/pyspark/eval_handlers/_arrow.py:290-303 | python/pyspark/eval_handlers/_arrow.py:801-818 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d1717a45c34ef64d5f6a068d3d35717d96796cf9e4b4d4ed3e1810ac13fb13d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/ml/pipeline.py:199-220 | python/pyspark/ml/pipeline.py:352-371 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/pipeline.py"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"e08e3dfc24704f6b75a5994252f7a444aadb63dbd3738d2a723b414e06015ca6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:2818-2826 | python/pyspark/sql/functions/builtin.py:16539-16646 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2818}}}],"partialFingerprints":{"codehealthFindingId/v1":"047ecf71989e972f2739d51861b8b980f16762d8e03c5f3bf4c87aadbc9229c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 18\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4130-4147 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4199-4223 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4277-4300 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 18 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":4130}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6cca7ea475dd2cd482bccbb5878c3c6d9f0c98f910a8a033a207d736cd135c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:3647-3653 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:3669-3675 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":3647}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4cdddd3d9d0d5a607e16250174937c5f3f918480479268d88fa95b96ff84d36"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:786-802 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:871-889 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":786}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4683c05a724eebf66f66d115493a66276791d4e378531c6511fee0cff6d4097"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 21\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1325-1350 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1446-1471 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1485-1505 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 21 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1325}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7d36b56272bfb261c9e432f577813e53cf6136623170947e1b5f5b9c18dde07"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:443-459 | python/pyspark/pandas/data_type_ops/num_ops.py:313-336 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":443}}}],"partialFingerprints":{"codehealthFindingId/v1":"7fc62cc8b431f87ae249590209383eff21675b8b3e9929b45a93ab0a32466aaa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/connect/dataframe.py:2468-2482 | python/pyspark/sql/connect/dataframe.py:2487-2502 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":2468}}}],"partialFingerprints":{"codehealthFindingId/v1":"665730df9e009d121c74f15db16276290534514a8c0e40aa6b56bc216e8ec362"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesConf.scala:146-163 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesConf.scala:256-276 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesConf.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"626fc4c7665c2aa2e8fe361a553f30c7a1d3e110aa7202233e574417738fc0bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/GeneralAggregateFunc.java:83-93 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/UserDefinedAggregateFunc.java:57-67 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/GeneralAggregateFunc.java"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa6ebcaeb84d8287dda29b50b8d67d9b83ea7374abecd981b5be79ddc976defb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:582-619 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:647-684 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":582}}}],"partialFingerprints":{"codehealthFindingId/v1":"2663a8cfdb81921c019261c63d2f1e84acdb5e057129807ecfefd6839e690fff"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:474-482 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:497-507 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":474}}}],"partialFingerprints":{"codehealthFindingId/v1":"b970650f77ec6144f3d7123f31760fb04e1ef2ede9f12e864867c4dfb2b6a016"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java:142-161 | common/network-common/src/main/java/org/apache/spark/network/server/TransportRequestHandler.java:323-335 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ca48dc0e7ca2b5b9280af4457670d76c541fc5b33190ad4c3f1cbb3429dd8d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/ProtobufUtils.scala:144-160 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:458-472 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/ProtobufUtils.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"821cecef9f24062fa31040c021bf85a667220693fb8a1aee2e172d1029b77260"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): core/src/main/scala/org/apache/spark/SparkContext.scala:808-829 | core/src/main/scala/org/apache/spark/SparkContext.scala:840-861 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":808}}}],"partialFingerprints":{"codehealthFindingId/v1":"0bf9184ca7a80513ecb371708b4e96267e4f12216a2d620b098de7ab5f62867a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:363-374 | mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:317-327 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2c5f184e53dbd2459b40b5c613df778a5edebf0f572599f78348ee74fbcbf6b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:53-64 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1397-1409 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fc561a64f3af13e7ad1770b1d2ca0b1b25d1a983e108c229ec2bd212816201e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala:193-208 | mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala:319-333 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ff4cad7d241c174bbb65e9c767fa26ba1bb5c771cae3eb3cd992c941aee688b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/pandas/data_type_ops/num_ops.py:486-498 | python/pyspark/pandas/data_type_ops/num_ops.py:518-530 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":486}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2d0882122bb1f87c91c3c38830fd6ad1d53192387edae985c86bed3a11fc6b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala:461-474 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala:476-489 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":461}}}],"partialFingerprints":{"codehealthFindingId/v1":"2930c2c103720cbf49eb449fcc20d97c584294fbd074180482ce752a070b76e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala:508-520 | sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala:982-994 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"a756c9bb7aa9b205219e63cb47dcd32dcad3dac3b32d54d22af863350c01d5c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:346-356 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:420-430 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"493a08201fc38ecb61850321f82e149ca8bf2a8d749a0024bfc128e392dfedaf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala:195-204 | sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala:1050-1059 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecafd3403ddc19d5ad53e575b3009a975892ce637608d2f7e3d7219b1d330450"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala:484-493 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala:496-505 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/columnar/ColumnDomains.scala"},"region":{"startLine":484}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf1bb5317463095574bcd75148d8a59feec7db5580098172c3c92e2597bd1c92"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:289-310 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:367-382 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"f073821c3e648082d670ddab772d59dd1116e91027a2fa6e2a018b9c916203b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java:52-66 | common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslServer.java:80-98 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8e1c877f5864ce9695bf98903aaa72e55bf302720e790819a7d543e628d33ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/sql/connect/plan.py:1262-1272 | python/pyspark/sql/connect/plan.py:1438-1445 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":1262}}}],"partialFingerprints":{"codehealthFindingId/v1":"24a468bbe1f6c9e74efb8f3e98f5028d323491cbde55163d87f39cb6f4a7e11d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): python/pyspark/sql/pandas/map_ops.py:45-58 | python/pyspark/sql/pandas/map_ops.py:67-80 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/map_ops.py"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"33b959aa47229ef3e187071880f2e5cc4c4d747c5303ab4e4e0429778bdd1904"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java:83-91 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java:103-111 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"7bc9d784cef9d239e7eb22e1808af88b9466dfefce795cba7f2c9489c8320fb8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:540-552 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:576-585 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"e258a73e1c888e4cf2ac89a0b7a3ff1740799b26b22e6e7697f6228c5070d17d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:301-315 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:164-182 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0f275578db0b1017f57117ee0614915494f544677f0d21f6a79d9ed05bec48f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:675-690 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1153-1168 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":675}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bfc3cfa7f62a5f6f3430c0299d24e5b97631c5e315dcb3d5e6f90739f3c8c5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:671-681 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:701-710 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6734a580b73c0e157b0d8c867123974adeb0995d930c568bfa7f3e406839fcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala:56-70 | core/src/main/scala/org/apache/spark/ui/jobs/StagesTab.scala:55-70 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"484d72bc8f317ba2e7d945e20e9f1e4a411b9ab782792a6995ed48cac25e35cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala:149-167 | mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala:129-140 | mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala:675-686 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"19d33b9f8e12aa2f8bd62f116474ba630da1420e3cfc7b4efce3cfedca354eaa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): python/pyspark/ml/tuning.py:971-994 | python/pyspark/ml/tuning.py:1550-1571 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":971}}}],"partialFingerprints":{"codehealthFindingId/v1":"81f37cec46fcc4895f329a995095107f0c612dde78332a34330e8ba5142942d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 36\u002B corresponding lines): python/pyspark/mllib/linalg/distributed.py:97-132 | python/pyspark/mllib/linalg/distributed.py:596-642 | python/pyspark/mllib/linalg/distributed.py:1235-1287 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 36 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/distributed.py"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f53801a909c25cdfe0a7dc489728bf34fda4b628b09daf632bfb3efbcbb117f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (51 corresponding lines): python/pyspark/pandas/groupby.py:844-894 | python/pyspark/pandas/groupby.py:1059-1118 \u2014 These two members are one piece of code written twice and then edited apart: 51 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":844}}}],"partialFingerprints":{"codehealthFindingId/v1":"48f6a0d69f1eedc5f7fc1cd21af7d61caf38f178d118848d6341a0e7d953d469"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/types.py:986-1000 | python/pyspark/sql/types.py:1049-1063 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":986}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ae9e64294067cb3dc7b7454e7e0c8ca58a75c7028de40d580f7016e2d738530"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2454-2474 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2480-2501 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2454}}}],"partialFingerprints":{"codehealthFindingId/v1":"92e5bd2477ebf4da7e2b91072459ba7f84cfac452973187cc8b6f1a42c3ee39c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 21\u002B corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectExecutionManager.scala:315-339 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectSessionManager.scala:303-327 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamingQueryCache.scala:260-280 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 21 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectExecutionManager.scala"},"region":{"startLine":315}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8f10a934368ab767605a7d0fec1bbad9eeacc09e2b942e6d3451bfbb634d280"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 13\u002B corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:347-359 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:226-238 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:305-317 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":347}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9b3f8b0f95c277d6cecc283ac5ba56136971eff6cd23a75f5377e96e4f9d58c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:164-178 | sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:185-204 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"60fa2a4c803bcb953fc95ad0c09976d273516bbdb3ceeb40d28df07fb575065d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 13\u002B corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:507-519 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:522-535 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:552-568 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:571-584 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:669-682 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:686-700 \u2014 These 6 members are one piece of code written 6 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":507}}}],"partialFingerprints":{"codehealthFindingId/v1":"d055d4db867b0e1a4b42bcb0bcf7551c6fb08fe2d5fe1552a7fbdf314794b2da"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java:370-376 | common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java:378-387 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils-java/src/main/java/org/apache/spark/network/util/JavaUtils.java"},"region":{"startLine":370}}}],"partialFingerprints":{"codehealthFindingId/v1":"06e5af96e404cb4594a54f8fdf6fdc322f638f909b581a967e276a4854860477"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): python/pyspark/pandas/data_type_ops/base.py:176-189 | python/pyspark/pandas/data_type_ops/base.py:195-206 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"99b5404589737c818afc1df85b3f006cfd7e4e92b351239c99e5c6cc11f1e03b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (53 corresponding lines): python/pyspark/pandas/series.py:3326-3378 | python/pyspark/pandas/series.py:3381-3433 \u2014 These two members are one piece of code written twice and then edited apart: 53 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":3326}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9476ac7b57b1427ce11fdb24bdc86f33b237b66a4692644b1668b6667866c5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/thetasketchesAggregates.scala:439-459 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/thetasketchesAggregates.scala:615-635 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/thetasketchesAggregates.scala"},"region":{"startLine":439}}}],"partialFingerprints":{"codehealthFindingId/v1":"68c4728c29899888e9b7cacc0e6e0f53d09310e59a8f7f6c55722583b062f05e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:351-365 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:370-390 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"40d48d0f8ceaaf8b4f859b6212bdb269d2a2b9da552dfb4a52daba2dc522564e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionContext.scala:74-113 | sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionContext.scala:128-157 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionContext.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"2300e92fc2e77f050a9444e6c220e5d170a11cda5f121d17cf8ca95dce922147"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:243-257 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:275-289 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"24db43eb9852dfb3d88705879eab56c9c9fef0f7ef4eb2847bd0a30b9db848c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java:50-68 | common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java:70-89 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5585928463ed91d1ae537558aca9360de94db4c3edcba5d959005dfd29dd621"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): core/src/main/scala/org/apache/spark/TaskContextImpl.scala:486-503 | core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:430-448 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":486}}}],"partialFingerprints":{"codehealthFindingId/v1":"19ac08488ce836f802b15db0cc6682fef69e92c06fb119f338b834202c316b99"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:416-425 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:49-58 | resource-managers/yarn/src/main/scala/org/apache/spark/executor/YarnCoarseGrainedExecutorBackend.scala:75-86 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fced5b3e757652ea7192ed2b7d95351ca5f809af56c238cedab6ae6799d604b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): python/pyspark/pandas/indexes/base.py:1884-1929 | python/pyspark/pandas/indexes/base.py:1932-1963 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1884}}}],"partialFingerprints":{"codehealthFindingId/v1":"b56c4607e7acfc99ac171773f22ce5614e2b4b8b3d2d481db78da6af5d077e83"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala:137-156 | sql/api/src/main/scala/org/apache/spark/sql/types/GeometryType.scala:134-153 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"ace45216dd2fe77930bbded3d07929ce2479b84d0952d58abe0a5597bc200f0f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 11\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala:89-107 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:55-70 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledJoin.scala:242-260 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala:251-261 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0a981d13cf5c7d0a28c8e2da531da3549110e4d3aa7603e6e7ab1e2b96c80a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:469-498 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:696-730 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":469}}}],"partialFingerprints":{"codehealthFindingId/v1":"20eb2470a466a642757ee3159c92df539c2cd44e8df18269897c53803fd0ab94"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:320-326 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:351-357 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd6e5b29e4d3279c15a5af77e4f1631fce0712e740e95da38e350143f70e3272"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:211-220 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:243-252 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a3b693156164dfaf9786bb356a915196c5be6a661d937ee3b777adc7aae63e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/ssl/SSLFactory.java:422-435 | common/network-common/src/main/java/org/apache/spark/network/ssl/SSLFactory.java:438-466 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/ssl/SSLFactory.java"},"region":{"startLine":422}}}],"partialFingerprints":{"codehealthFindingId/v1":"39a537899d3ed848b1f90287a542f27f91c609e86dae1725f7a12c559f1630e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala:123-138 | graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala:249-265 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"d777e83adac3f53837c66b8f14ba76bd9a6c543bbf7673bdece9583e80c6d42c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 14\u002B corresponding lines): python/pyspark/sql/streaming/stateful_processor_api_client.py:421-438 | python/pyspark/sql/streaming/stateful_processor_api_client.py:441-456 | python/pyspark/sql/streaming/stateful_processor_api_client.py:594-607 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"9303abf43879c8c0b7beb9b9f5585fa869954a762bf34f044a35b3710b75aee4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 13\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:423-435 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ConstantColumnVector.java:282-294 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java:487-500 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"6bc4304ca5c7c1a3eff56b391349a8893643e105c03e0e8a79cda8a5c131d00b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/V2Reference.scala:198-223 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/V2Reference.scala:228-254 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/V2Reference.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab2b3aced0b22fe3b8b59ad65e60b871570d69def89eeae2dd60626d5e719d6d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala:558-584 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1775-1804 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala"},"region":{"startLine":558}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c4c1f828bdda52c1adeb361fb878975a035052e479f0a0e6910a7e8db16e256"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (9 members, 13\u002B corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:263-275 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:415-427 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:495-507 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:561-573 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:628-641 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:368-380 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:442-454 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:501-513 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:562-574 \u2014 These 9 members are one piece of code written 9 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 9 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"f28206ef506aed491f02740e4e67009ef489bf4e90eb0ba104f0a403bca70518"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:2204-2213 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:2215-2224 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":2204}}}],"partialFingerprints":{"codehealthFindingId/v1":"e46a5b6b4605c7593f50a89924e681badd16e01397adae5dbb4dee0554261baf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala:601-614 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala:632-652 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala"},"region":{"startLine":601}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fc0663b0afd02e68c9894bcd181fcd137b32ed2ebccc3c87ea40375538802d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala:88-103 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala:111-125 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"d00e1f107e90373122dfdd06f1da55861d9caa069c15f167e279ae0df990c573"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala:87-99 | graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala:106-119 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"604810c1e29b94e0345c40de875898bd091894e295b3bb1c47cbb8e15658de39"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala:485-499 | mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala:504-518 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3bbd77781720a0c4e43abe60d5124dddcc9f28c5034ae451ae3be61d0bea120"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:307-325 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1567-1585 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbb004271b94c9db033e443d299512719cd7cd4fa62574bdcd1da4eb518f9c32"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:711-734 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:746-770 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":711}}}],"partialFingerprints":{"codehealthFindingId/v1":"99579da31a57f9995995e130518b7a29b10237f44f99f57fd9d5c4d54250a9e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 19\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:476-499 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:510-533 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:545-563 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 19 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala"},"region":{"startLine":476}}}],"partialFingerprints":{"codehealthFindingId/v1":"939cadf9f1fba24cce4016de063a7906ff16b5abf70f9d1efef87368007a33be"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/deploy/Utils.scala:45-55 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:94-103 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Utils.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdf90c437543ebff77fb4478a08fb24437a81cb643b2ba3f927c68ade2e9a0ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 11\u002B corresponding lines): core/src/main/scala/org/apache/spark/status/AppStatusListener.scala:1296-1307 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:350-360 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:362-375 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala:278-288 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala:290-301 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":1296}}}],"partialFingerprints":{"codehealthFindingId/v1":"93a6805952786325758a62d5206915a238f90f84a57df5721850c1f371ff0a34"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 13\u002B corresponding lines): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:603-620 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:489-510 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:612-624 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:322-337 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":603}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2239d931fb17cdc2439a6e2800da02a89b984d8d98c164a9107d98aaeabbdb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:711-719 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:641-649 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":711}}}],"partialFingerprints":{"codehealthFindingId/v1":"847bab65acd4f2f30262bb2f2c996ef3d3b38cf2bbd132a9dbe1ab5009c01b28"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:466-480 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:485-499 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala"},"region":{"startLine":466}}}],"partialFingerprints":{"codehealthFindingId/v1":"666fc051d91e0f8a66d59faa0ff6d4955d0a438a1504f738de15539599d389cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): python/pyspark/core/rdd.py:4814-4848 | python/pyspark/core/rdd.py:4853-4887 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":4814}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4258d36572bd420668cebd1c4858e9b6f6042fa65a3ddcc2f338237c1d91d74"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): python/pyspark/ml/tuning.py:997-1018 | python/pyspark/ml/tuning.py:1574-1595 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":997}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0b92928757f2b4b8d425eb058b5c2d2631fca827132fb86f91ba462bac95463"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (94 corresponding lines): python/pyspark/sql/pandas/group_ops.py:993-1091 | python/pyspark/sql/pandas/group_ops.py:1096-1189 \u2014 These two members are one piece of code written twice and then edited apart: 94 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/group_ops.py"},"region":{"startLine":993}}}],"partialFingerprints":{"codehealthFindingId/v1":"5dfd853409c2c6b1b4c372ef8801dfca0f61fb1478b761350caa4802ec241f49"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkCharVarcharUtils.scala:74-89 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/CharVarcharUtils.scala:114-125 | sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala:383-394 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkCharVarcharUtils.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"482d43c3ac24da52a9a286bf7bb92e9f0c8d4df04ecc6e643ff9a1a9b32a5877"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala:130-149 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala:153-175 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"49596e2642c8ea822c5a3c2b7331cb2d61c8477744b5aec7b8a417e7fd8d33a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:478-486 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:807-815 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"d279c764d31ccfa0771cb4d67ba183410dd15dc3efb1abf3c0da5acebae3e7a6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java:30-45 | common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java:47-63 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4e673777e4f0e056326bff9f400ce3f749d66af6e54af68c4575cc04d2bd62f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java:1387-1401 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java:1403-1416 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java"},"region":{"startLine":1387}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c9f3843aefac4175ec142356c90ab527019bc364f71c00fd3151f3f51f83d0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/sql/classic/column.py:580-597 | python/pyspark/sql/classic/column.py:600-617 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":580}}}],"partialFingerprints":{"codehealthFindingId/v1":"f36af0def1132b865228529f7b35160c20037c9c5ee3e798b7380c41dcf424b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/sql/connect/client/reattach.py:208-228 | python/pyspark/sql/connect/client/reattach.py:231-252 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/reattach.py"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"765081aabbbcc83cb24ffafb91d331967cbd36164135a1f45ecfdb6e9ab4bfbd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala:257-265 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala:273-281 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"a87bbfe150e25b8fe5856344aed0df7af164f1830a1aaf7049ece0942de984ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala:645-658 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala:681-694 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala"},"region":{"startLine":645}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc77718dca45b04c0f16a6862a0bcb7c6bb10e8b8a0ba462b957210570be4867"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:153-164 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:186-196 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"4666f321d62b4a1a4ba4e50ed1381a77b15496a46ccd55fc2f8be6d689b7ec54"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:243-266 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:278-304 \u2014 These two members are one piece of code written twice and then edited apart: 24 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"0438cad9d5224c1eec506d2c1171f2b8e37a0574a5f5467b5eb9c57fb913163e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala:167-181 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala:196-210 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d5813efa3d6f673759f734b8b61236261275adf0b68310f3a3306cf666ac045"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1136-1146 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1160-1178 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1136}}}],"partialFingerprints":{"codehealthFindingId/v1":"efaab8d3b63705d7a4e7635deaf96dafba09efea131f969439b08dfcb40130cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): python/pyspark/sql/classic/dataframe.py:1895-1916 | python/pyspark/sql/connect/dataframe.py:936-962 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1895}}}],"partialFingerprints":{"codehealthFindingId/v1":"708c828bffbef75752bf22495bfacc30abf0545297702e1440e405530d1564ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/conf.py:36-44 | python/pyspark/sql/connect/conf.py:49-60 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/conf.py"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a15cd6c70b2f52253ca169a389497dc404fa595c0d734149f5bfc7a0500a94e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): python/pyspark/sql/streaming/listener.py:458-476 | python/pyspark/sql/streaming/listener.py:739-754 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/listener.py"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c1db2dd50fc634bd19f96f16a74b7647bc50a5334da0e59449c79a5e77fb406"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfDecimalsSerDe.java:58-67 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfDecimalsSerDe.java:115-124 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfDecimalsSerDe.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6ab0ddeb1d174242a832e69053f26d6fd0857a3874fcf3837fb8ace7bd4a981"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 13\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/kllExpressions.scala:272-284 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/kllExpressions.scala:310-322 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/kllExpressions.scala:348-360 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/kllExpressions.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"03f60029584dc11d602a364cf4721e9aecb90360b74f250e509dc36a4dfdcc0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 13\u002B corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:66-78 | common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:80-92 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:66-78 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:80-92 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3d620571c46b024f884e14d59316c78ff68d4727a0bd604dfb3ed3dedcd5f7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:184-195 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:201-213 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"a419c463d8baf2ae7e10760b65ef4cbf15fd500cc2ec4de11d8690c5db95c5cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (56 corresponding lines): python/pyspark/ml/stat.py:52-119 | python/pyspark/ml/stat.py:139-194 \u2014 These two members are one piece of code written twice and then edited apart: 56 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/stat.py"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4741b1bdbde4c5a2e7ed4fab4d3042ee3ae77707cd7428482d24dbaf3e470ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/mllib/classification.py:946-963 | python/pyspark/mllib/regression.py:1018-1035 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":946}}}],"partialFingerprints":{"codehealthFindingId/v1":"c38c76e230ff868cad360f2184790b99968dd15ec0433c9d61d3c971c444c78a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 12\u002B corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:82-93 | python/pyspark/pandas/data_type_ops/boolean_ops.py:115-126 | python/pyspark/pandas/data_type_ops/boolean_ops.py:129-140 | python/pyspark/pandas/data_type_ops/boolean_ops.py:143-154 | python/pyspark/pandas/data_type_ops/boolean_ops.py:157-168 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"7be0c63e32b60babfd00758dc7f5d44da549dec4d177b04ac02e828e8109c3b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/connect/client/core.py:1261-1275 | python/pyspark/sql/connect/client/core.py:1439-1456 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1261}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e976f8cc210352b42f7e80b09f5bfda7cec8da7979bb560e407f84ba07f84ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala:375-385 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala:387-395 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7cdd694229793c37cd53f9b076515922adf828ff14b68f5b594f97620bc8c9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/CustomSparkConnectBlockingStub.scala:62-81 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/CustomSparkConnectBlockingStub.scala:84-104 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/CustomSparkConnectBlockingStub.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"c365847424157b27c41a1ed226fd1663b5ab618326b0ec143574d83e2588f95d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala:135-150 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala:155-168 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"247a3b9af364a3ffc994a5cc370a47dc19daa009829ff18dfe83dd8b6033a3cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 19\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:64-82 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVWrite.scala:42-64 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonWrite.scala:39-61 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:76-96 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 19 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"091a2389a9a6c54ddc05c6ae8f09b38ee81c56056dfe32e3c8d067624fdd33db"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:958-973 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:991-1006 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":958}}}],"partialFingerprints":{"codehealthFindingId/v1":"a10d7dc1b9aa5e459e2036f9e3d86ef209ad0d0f8ded36a5bf5a5070300fadfe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java:477-486 | common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java:506-517 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"a799b6bcd468fb7673b128d98bd80abbdd51ece7fdeb1eff931d9b6ffbe5a517"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1365-1383 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1388-1402 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1365}}}],"partialFingerprints":{"codehealthFindingId/v1":"69533e87a56e89fbc44c78b7afefa1e5b28dab6bf971976958b86bb3e4822873"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 12\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:833-844 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:846-857 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:859-870 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:872-883 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":833}}}],"partialFingerprints":{"codehealthFindingId/v1":"04adbcf43a1bd8a55d345152f49fadbb3653eaaab5fdb705c0b3c71c540644f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala:178-195 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala:200-219 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e1f8309698336ca69e4c3f0f348ff6258f898fce36206e770a3d1cea4c4b2ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:135-146 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:149-159 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6e32a8cc3f50da9ac46e52f1a567a510a721189baccc7824d52e50c006765f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PullOutVariantExtractions.scala:407-427 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PullOutVariantExtractions.scala:438-456 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PullOutVariantExtractions.scala"},"region":{"startLine":407}}}],"partialFingerprints":{"codehealthFindingId/v1":"c871196e080e9da2b73bf1d0d12442cc245761f0b5042f5e0f37615b91505c47"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 12\u002B corresponding lines): sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1247-1261 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1268-1279 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1288-1300 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1409-1432 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":1247}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd9a91f8bc868ef13c9193d895d0246a77691627731babe079b6dca73a1b516e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:217-230 | common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:234-245 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f3db4b0ec35610851d200eae8a7582ee90cef562e5f18d87503305d3f89cd4a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 10\u002B corresponding lines): core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:417-426 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:443-452 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:486-495 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:512-521 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"19988b17741f37ea00e725069cb3160b4de9ab0c8f47297d7818894d13985a25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:460-469 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:529-538 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":460}}}],"partialFingerprints":{"codehealthFindingId/v1":"689bd970cc8f36fa71331a556d7bf30825bbf97dd252695830a35632e825c8da"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 12\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1277-1288 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1374-1398 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:288-299 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:430-451 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1277}}}],"partialFingerprints":{"codehealthFindingId/v1":"075cf3f2d5e222fc7cf2911b2b148b1184c30741173fe3a80a565f7fb21eca43"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:91-99 | mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala:89-98 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bca037e8f6b54f0b45237c8801fb63caba512419bbb806ca497bc5dc5a4a703"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tree/impl/BaggedPoint.scala:83-100 | mllib/src/main/scala/org/apache/spark/ml/tree/impl/BaggedPoint.scala:107-122 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/BaggedPoint.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"99d7716b95a718a496db208c398b3586f03c737f27d04d734e1143b72263d58a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): python/pyspark/ml/util.py:1195-1206 | python/pyspark/sql/utils.py:275-286 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":1195}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d5fbf012f2df44ce8bc44a130aa45195dabf92293f6c333db3f3fbdbdb98a4a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 12\u002B corresponding lines): python/pyspark/sql/utils.py:290-301 | python/pyspark/sql/utils.py:305-316 | python/pyspark/sql/utils.py:320-331 | python/pyspark/sql/utils.py:349-361 | python/pyspark/sql/utils.py:419-436 | python/pyspark/sql/utils.py:440-456 \u2014 These 6 members are one piece of code written 6 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/utils.py"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb524290fcaa95d393a08b2109f9c00aa1ff561cb69579f30091f7219150a693"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:639-652 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:655-668 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":639}}}],"partialFingerprints":{"codehealthFindingId/v1":"20ae4e138f588dd35e6dcf6ff1b6369af080e5b09ccd3fe12ed6257d08c352b9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala:140-155 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala:797-818 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"da47e9117358e89cfb590e7d25aefc2f4143f7977fe40608cdfe647c5faed2f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:254-269 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:396-414 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e146b0b4dbc702a21bf8584b38372a1b8a23d92e1d891b55b561620ca93d055"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala:86-97 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala:99-114 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"e04760ed51d5eb56c7683323baa61c0e2f7a5ba6c035d296ca8b426b453eb2ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 17\u002B corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:530-546 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:550-566 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:613-629 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 17 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":530}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2029d4b39fe1d18961865ad0e6d99ad58876e7ed48e44e578c3897a35673446"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:479-490 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:493-504 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:538-549 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":479}}}],"partialFingerprints":{"codehealthFindingId/v1":"eba7aebfc2607a006b4e1c64c92fa7221e7d6e77190ff409fb4fdd4210795439"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/DiagnoseCorruption.java:113-122 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/PushBlockStream.java:110-120 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/DiagnoseCorruption.java"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff76da5af77d3bc93e98fd23f194540d9b9dfb3a9bbd9eb4169be7fc72ff98c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:774-783 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:803-811 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":774}}}],"partialFingerprints":{"codehealthFindingId/v1":"84c47b8468dab76cf1dda1369b555b9b1c4a68d6885d27b6bfbe7a0df144aa46"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 62\u002B corresponding lines): python/pyspark/mllib/classification.py:343-409 | python/pyspark/mllib/classification.py:658-719 | python/pyspark/mllib/regression.py:304-375 | python/pyspark/mllib/regression.py:487-552 | python/pyspark/mllib/regression.py:667-733 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 62 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b4485d10222ab2dffda2688bcd45c897da9dcf80c9050926bad945d13865c54"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/sql/connect/dataframe.py:307-316 | python/pyspark/sql/connect/dataframe.py:1674-1686 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaca9903aedc371bf015716f1c14ca9e58baa5f797a782ddd8756bcea375dc2f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/sql/connect/table_arg.py:57-72 | python/pyspark/sql/connect/table_arg.py:75-87 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/table_arg.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"77f581f687535ead0781aea0759079e30076fff3510b5c1ce13e910d463a992c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 12\u002B corresponding lines): python/pyspark/sql/streaming/stateful_processor_api_client.py:173-185 | python/pyspark/sql/streaming/stateful_processor_api_client.py:188-199 | python/pyspark/sql/streaming/stateful_processor_api_client.py:248-260 | python/pyspark/sql/streaming/stateful_processor_api_client.py:263-275 | python/pyspark/sql/streaming/stateful_processor_api_client.py:406-418 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"0703b390d379a74977881fc4d53afaade67af2b4a25bf99a6e5ca31ec4b1a332"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:481-489 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:491-499 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:501-509 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"01fa16b5ccdb40fa689b61a4a001ec886794d3a87d5c14dbe79152707a19f8ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:572-583 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:604-618 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":572}}}],"partialFingerprints":{"codehealthFindingId/v1":"d29362b0e870ce2460e9df7b8582352955eb3a6a5a45345d9902f44f04d1cabf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4066-4082 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:954-967 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":4066}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c1aad579585d374cb99130a9c47c4f14dfc551c48cbe0999232fc1b42e0b477"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleSketchSummary.scala:87-99 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleSketchSummary.scala:158-170 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleSketchSummary.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"03f07d650bead905995063b1d2fc50da658bb407d28578db2b62e87d85d8c416"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala:69-91 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonScan.scala:68-84 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a942ebed465dedd8fe55e2cfc23a3068dc72e8dd1966c00cafd0de0969da87b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:410-421 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:423-431 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala"},"region":{"startLine":410}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c4374e581b4fad9486631ad2b011e3428b1bfdff4c4ea320280ee8ba97a8356"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:380-402 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:518-540 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"316d65880bdbf504543d5075a239aa865cca67927f4381da5f6cb13ac1049e5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala:521-541 | streaming/src/main/scala/org/apache/spark/streaming/dstream/DStreamCheckpointData.scala:132-152 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"aff4283268f6528923f99cf788cbb2c52cc94cf37a5c352ced55becf74de6bb5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:432-438 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:481-487 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:530-536 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3bf29c3117774d9920d5fea876ca928128cb89e94f2b9e99d2e3fce8fd328fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): core/src/main/scala/org/apache/spark/rpc/netty/NettyRpcEnv.scala:737-754 | core/src/main/scala/org/apache/spark/rpc/netty/NettyRpcEnv.scala:763-780 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/netty/NettyRpcEnv.scala"},"region":{"startLine":737}}}],"partialFingerprints":{"codehealthFindingId/v1":"22ea718bf36b7283b6b67043d50e79b7bb6d06c3500e1ee93d35247059abdf63"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/scala/org/apache/spark/storage/DiskStore.scala:197-211 | core/src/main/scala/org/apache/spark/storage/DiskStore.scala:250-268 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/DiskStore.scala"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b1a9910f9f9418c5da0ffc87a46ed57785d8cd8dc44558c0674e4e629c29be9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/OpenHashSet.scala:135-154 | core/src/main/scala/org/apache/spark/util/collection/OpenHashSet.scala:173-188 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/OpenHashSet.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"de6b56271c6b08faf541427115b28dfa6b8d7a88d09ec756588b06162c006ddd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 55\u002B corresponding lines): python/pyspark/pandas/testing.py:54-165 | python/pyspark/pandas/testing.py:188-261 | python/pyspark/pandas/testing.py:276-330 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 55 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/testing.py"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"7263f39b63628d9ddb818b778e7b6258fa30bb25c91238e6fb563ede6371a034"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): python/pyspark/sql/catalog.py:134-173 | python/pyspark/sql/catalog.py:526-571 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"6074edf71702fb34f958926035004f79c21d96f1891acfbb3d9a144b685b31f0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (47 corresponding lines): python/pyspark/sql/catalog.py:715-765 | python/pyspark/sql/catalog.py:879-925 \u2014 These two members are one piece of code written twice and then edited apart: 47 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6fbb08e2d1692b9096e0f59c867d3d6556c587b57d9f5a8e37712632aaecf35"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 18\u002B corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1981-1998 | python/pyspark/sql/connect/functions/builtin.py:2009-2026 | python/pyspark/sql/connect/functions/builtin.py:2037-2054 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 18 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1981}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ecb137730e9aca39b29884661ac5aee5b8acc0cb4ab1cc0ccd771d6b02de229"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:395-402 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:515-523 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":395}}}],"partialFingerprints":{"codehealthFindingId/v1":"766d5f81d1c77832ff0fb71f8d9c8ed58a53c7a6179b8875426d739afaa1ddd7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1363-1375 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1727-1739 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":1363}}}],"partialFingerprints":{"codehealthFindingId/v1":"359d09cd380f958bc68176eb5f9df531ab1d58455512c524e54e7adc30d4af4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:574-587 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:589-600 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:605-618 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":574}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a73a980329ad4ff15289cc835c01c3fd9cd515a80e96d0be8d03ee029fdda09"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala:75-90 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala:92-107 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcDeserializer.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c88c6778919100e5520266de99f540b0462fd9fbf529fceeda5bed71d47b4f1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:255-267 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:291-303 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2cc51485799e0994035e5387f55465fc97b41b036413f5e116306feba602246"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/java/org/apache/spark/shuffle/sort/ShuffleInMemorySorter.java:128-142 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeInMemorySorter.java:215-232 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleInMemorySorter.java"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"4caa465bf637fa15e39b6655654e6072ea103e5ea8a178f5e8f560ddb7ad48b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): core/src/main/scala/org/apache/spark/SparkContext.scala:3265-3286 | streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala:632-649 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":3265}}}],"partialFingerprints":{"codehealthFindingId/v1":"be7ca1601c3adb0297aed0b582e46cbfbf732f483771ad8f570b7998cfca7060"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:715-721 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:592-598 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cb0911337c11cd8328c3d913ecc950539770ab8b1057968ff617d96de7b92f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 11\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:240-250 | mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:352-363 | mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala:502-512 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:350-360 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b4cfd62ad0c050a416c09484f31b1621d908dd00e25f5b70fb2207dbee9a585"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (100 corresponding lines): python/pyspark/pandas/generic.py:998-1106 | python/pyspark/pandas/generic.py:1125-1224 \u2014 These two members are one piece of code written twice and then edited apart: 100 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":998}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e3d8dc4a2f80b69342d5b37c8e18c669adbc77c76a4f667aa3c17f095286142"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): python/pyspark/sql/connect/column.py:73-95 | python/pyspark/sql/connect/column.py:392-410 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/column.py"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c2b91c8d80d756527820458dda1e35a8aba92a4eeb3165485855d1fe1aa0902"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/sql/connect/observation.py:36-53 | python/pyspark/sql/observation.py:83-107 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/observation.py"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"1559f7e548aec96e032219e1c0a6f6c829621164d6baf434dd5a85f5c24af36f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:170-173 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:200-203 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7d9f8b9e92111d175ff8470857fc0664c28c92993998043622c61266f448625"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:286-304 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1609-1631 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7ab889699d3f3b416086331199a8468d3cc7af8d0f75cf01d6700864ad13114"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala:84-92 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala:190-197 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"d702d1a3c84aff8c9ced903f56587d0949cc21778c204faa913297e155c7695d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java:209-221 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java:244-256 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java"},"region":{"startLine":209}}}],"partialFingerprints":{"codehealthFindingId/v1":"41b5ebbdfe2ae3aea8741e1773eaea9363f77df920b9f7ac7b5fdf2a398438ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 13\u002B corresponding lines): python/pyspark/core/broadcast.py:363-375 | python/pyspark/ml/image.py:233-246 | python/pyspark/sql/column.py:1617-1633 | python/pyspark/sql/conf.py:185-201 | python/pyspark/sql/udtf.py:559-572 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/broadcast.py"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"5065b51dd720b271b02363a434f45889454bb7f4b549ed82fd957877cc9abdd8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): python/pyspark/eval_handlers/_stateful.py:102-119 | python/pyspark/eval_handlers/_stateful.py:896-919 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"fff5b367f8c88ccd5c0c7ada11402490ea2abccc16fb0852a70b1af8acf8ae6b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/ml/connect/feature.py:152-158 | python/pyspark/ml/connect/feature.py:276-283 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/feature.py"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"d616aa8477e0de121fea5fabc118369897a966a04bc064efdbf49cb61894aa08"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (67 corresponding lines): python/pyspark/pandas/groupby.py:1232-1298 | python/pyspark/pandas/groupby.py:3559-3636 \u2014 These two members are one piece of code written twice and then edited apart: 67 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1232}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4797beeebc9759a2afb8892fcc0ca5f5b0ecc81d8afebc0edeb15365ad1fdd0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:291-297 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:617-623 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c8b4aa4d8be26720b1708f5130b6bcaebc49dabf055fc1ad44a0fcf8649ee3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala:296-310 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleUnion.scala:353-370 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"a59551a4d3aeec762d93e7c3e30a985a66b07386ada216fafb288507383d3982"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala:247-265 | sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala:272-287 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"cde5e39cf4b840785324d8d800d9d8c0d17d6c734c2b06e4f53e50fb17c62e14"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd1BatchProcessor.scala:263-277 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala:1883-1896 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd1BatchProcessor.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"2480e03a0e72cda0fd0b0a93f1ac7465abad5d669b263b12926bb76b78b8bdc2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:254-264 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:284-294 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"96198a034f37bf8d2160976e744dfff3d7551c1b09fa65107646b2d5bf287a5e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1037-1051 | mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala:349-363 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"150d86c6905c426559cde5fdb1483a27bbc96672f526e022ef48d8663e188d08"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/eval_handlers/_arrow.py:83-94 | python/pyspark/eval_handlers/_pandas.py:302-310 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"d02a80e601f9ad1dc3850d77186ca72c2a8ffd5201433e557eb06d5fb94039cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 9\u002B corresponding lines): python/pyspark/eval_handlers/_arrow.py:140-154 | python/pyspark/eval_handlers/_arrow.py:210-222 | python/pyspark/eval_handlers/_pandas.py:384-394 | python/pyspark/eval_handlers/_pandas.py:464-472 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"c49d14a3ee321b0b9499a4c5f0ab029c77a3dd096f6141e73ea4f531a121cfc9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/pandas/frame.py:6853-6867 | python/pyspark/pandas/frame.py:6926-6940 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6853}}}],"partialFingerprints":{"codehealthFindingId/v1":"ead9df61fbffd5ee029cbd7d890a0195db64443539fdbd84a009a4c012a20ab6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 13\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/MultiLineString.java:51-63 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/MultiPoint.java:51-63 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/MultiPolygon.java:51-63 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/MultiLineString.java"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c1b5b6973dc08fadfc4c1fae98fe3684b9ddc31eedcd3a8a9c5b58e383858f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:374-383 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:390-399 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d47130828e272a5836d9e4525aa92c3d48937f0ac6a8d4e6bcb6c52947d7788"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Mode.scala:239-254 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/percentiles.scala:456-465 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/percentiles.scala:514-523 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Mode.scala"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"f765cda6e2fd7f765aa5722c1a3ec24dcaf7061f30b8e273ed39433cfb48ade1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AbstractSqlParser.scala:104-115 | sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala:86-99 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AbstractSqlParser.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc35c33f105f9bf99ee5dd1b1747715a4dd5439e16b5d04bc49677da32fedb90"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ConstantColumnVector.java:299-309 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java:502-511 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ConstantColumnVector.java"},"region":{"startLine":299}}}],"partialFingerprints":{"codehealthFindingId/v1":"30df84d842667b8a2e3418daeaaaa0a61ecd66203572994c32fe6b093b22b078"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:72-88 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:90-106 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa49d9203d8f6efea2bb6e2e488628e75509baf3319ca72a323fc810148b7e9f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:759-772 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:777-788 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:793-804 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":759}}}],"partialFingerprints":{"codehealthFindingId/v1":"f579ae63e69ee904386b65dab7aa43ef6075ee0e76e5834689d95f85e1eccf34"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1872-1884 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1919-1934 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1872}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5ecc01927ed5938b6841c1158166ddc212c4bf73271e39224ff4bfebea67993"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala:683-693 | streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala:715-727 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala"},"region":{"startLine":683}}}],"partialFingerprints":{"codehealthFindingId/v1":"403a1cb97277b12cc47b8b6bdd62cf2071c6165a68ceb9128c2c6c936c899f14"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java:78-86 | common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java:89-97 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4e032229b540c72b175df8aa55bd25e02d57a16533d53342751e26d1d7afdf6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java:100-111 | common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java:132-143 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a144e77d0f5051eb48eb7806dc918b6d73961aa7d8a79c0cc09396ff9b3a764"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java:214-223 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:241-257 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcd4ae2cd12f4b3d116a226405e7928b0e21578aa6903b334a356813e43d13e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:552-560 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:569-577 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":552}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fdfdcaf87037c2317ac1b3d436abbbaa09068d5ab1e26dfa0e1841374f9ebb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:428-438 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:565-572 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8a9a39954c88cf399df465cdef198616713f999e41e5bd158111ecf3296c5f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/join.py:46-55 | python/pyspark/join.py:89-102 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/join.py"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"77a287ba6f9aa4d8e064df736fe8cb071ef1260d413b9989835596da0116d9c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (39 corresponding lines): python/pyspark/pandas/indexes/base.py:1619-1657 | python/pyspark/pandas/indexes/base.py:1660-1698 \u2014 These two members are one piece of code written twice and then edited apart: 39 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1619}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe88b19d2a9d61354cc92abf52d1c7eeef6d0a92079852360248f3126048ae5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): python/pyspark/sql/connect/dataframe.py:1689-1711 | python/pyspark/sql/connect/dataframe.py:1813-1834 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1689}}}],"partialFingerprints":{"codehealthFindingId/v1":"b77297d60cd23208aa77f89e1916cb0bf5a21b158307040629d0da6c595fcb4c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 7\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:51-57 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:89-97 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:52-58 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:86-93 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"2596fedb8135bf7aa796d051ee908df3686177a0814916baefa3bad095d9a8c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/joinTypes.scala:38-53 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/joinTypes.scala:202-213 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/joinTypes.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b3aab7f553d064737c40dac89ad3e31e973ab6a8e789f395ef93bf709f4b49f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala:73-82 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala:136-146 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddced8a05538949671761f7ea1f7e8219a5cbf332ff39e4c614dcb1edc414638"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:400-421 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:1328-1350 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"370e71d4fec34e08c5d4a2fc2832d32ac30a8724319156b4998b1221f4d63281"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:425-431 | common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java:484-490 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"02d1009064c6f92b9189a9800b1a73af5f25d497ab6e28cac5d0452a037425f4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/ml/linalg/__init__.py:1091-1112 | python/pyspark/mllib/linalg/__init__.py:1274-1294 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1091}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc6878495c012cc21204adc070a31f962df59d84b4dc830f2d48ebfec9f07606"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): python/pyspark/pandas/data_type_ops/num_ops.py:180-192 | python/pyspark/pandas/data_type_ops/num_ops.py:228-236 | python/pyspark/pandas/data_type_ops/num_ops.py:633-645 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7b32448edb3b9218795aa6da2c588e552239178fbeec41e412abb01240a8652"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/sql/connect/group.py:275-295 | python/pyspark/sql/pandas/group_ops.py:48-116 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":275}}}],"partialFingerprints":{"codehealthFindingId/v1":"e09cf0e745bd3ded72d2dc78ce4acc777748c7b8783d838cd349ce3c9785e927"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/Artifact.scala:62-79 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala:99-116 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Artifact.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3506512538b0d4d04d0e9b5fe5ec42cfec54607ef98bfcbee960e23aed0cdff"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateOrdering.scala:162-194 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateUnsafeProjection.scala:397-438 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateOrdering.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd27d04bbe296ad75cd2f7137462bdc02e00c8abf19e8050dc796e177c4fe78d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:629-644 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:665-682 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":629}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e3f945367edb411e1459c2119571e77f0b7f372b8ae59f54d664d1520665d06"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameReader.scala:333-343 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataStreamReader.scala:120-131 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameReader.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1968e5e44a465b5ad864191a745692520f2be397011b8075f45e94f274a6510"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:622-632 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1099-1108 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"16609b1ca517d195d96138286f228a5f1c0420dab554a6baf47da00cafa3fa46"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala:118-134 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1354-1370 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"e023e00bea2a31ecec4644783519507c427d1f00b9f5d62acbe914248f53a727"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/Edge.scala:60-69 | graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala:133-140 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/Edge.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d73b0dcd26c08280fe1b41226fc9beca34c1f2a410620417a04ed9e7a5ef332"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala:68-75 | mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala:99-109 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"007a04c75643ac4a71734bcd19de62587b9ae1dc4de054879c06f855cf452523"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 13\u002B corresponding lines): python/pyspark/mllib/classification.py:967-980 | python/pyspark/mllib/stat/_statistics.py:383-402 | python/pyspark/mllib/tree.py:868-880 | python/pyspark/mllib/util.py:638-651 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":967}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b50772c765a9e5340cf521d9082be35a61d12462214fb10ec5c5e1c7a551f7a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/sql/connect/dataframe.py:718-724 | python/pyspark/sql/connect/dataframe.py:732-738 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":718}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc5f60af32aefef7e012e297159694d0d031f9ccc68a9216aae9a0cb153b5a7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4203-4208 | python/pyspark/sql/connect/functions/builtin.py:5552-5557 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4203}}}],"partialFingerprints":{"codehealthFindingId/v1":"46d092affb853ca028e605b57af3d0b73750e39e3688cbc95701b33b5d308078"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (78 corresponding lines): python/pyspark/sql/streaming/readwriter.py:1767-1844 | python/pyspark/sql/streaming/readwriter.py:1855-1940 \u2014 These two members are one piece of code written twice and then edited apart: 78 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":1767}}}],"partialFingerprints":{"codehealthFindingId/v1":"e68112905e559601b4ae7b6a3ebba0f910153eea2afa7aaf6dd97e03d99a9387"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/parsers.scala:482-503 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SqlStatementSplitter.scala:450-464 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/parsers.scala"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"77d348301ec3228865b60338f18f6322c2758b155e1f4931a280870fa5301ace"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:198-208 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:213-223 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"693bf0cb5b0a448ba4ff531fecdb480b778737f29d39d87b71f85b91b1a1961c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java:419-427 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java:429-436 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c607db09514de379b269425165e9361e5f5026e2c1413a2b75a72242fa111a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala:78-99 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala:50-72 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"46f727ef41362a7b835290475286997d3675cccfe31e61560bbb81fc57928759"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 11\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:260-270 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1547-1557 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1685-1695 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d1de95583b7fa2fb61add09996bb315d795cb007af8a7a9801fb1c93d6c19dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 10\u002B corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:539-549 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:606-616 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:480-489 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:541-550 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":539}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b9eee8750de74027ffe538bf3c33411e9be50329e3dd806d2972b6b0b0ab417"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala:85-98 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowExec.scala:104-125 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"3389bcf07532ef72c100a60ba1f6eca37daaee80bfadf4dddb937897d4fa2e77"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 17\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/EmptyRelationExec.scala:65-83 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStage.scala:110-126 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/QueryStageExec.scala:138-154 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 17 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/EmptyRelationExec.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"b69c1d5b6c09ee62a6d2eddd9d34eb726335678d7724bcb1b5c4e6b676edc002"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 16\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:112-135 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:137-152 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:237-252 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 16 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"665f694dd4d1b705d391e7c04f5f0d6f66c7e7530edfab48056c51734ad9535d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:945-955 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:987-997 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":945}}}],"partialFingerprints":{"codehealthFindingId/v1":"77e91e87cf5c72186b8363cf4fb29f0c9537aa130156a1bb790835d7979b5755"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala:125-136 | streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala:139-149 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a2410e01890947b66695134317a3b0daa79503401e2bf5b153cbd78db6517d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 9\u002B corresponding lines): common/network-common/src/main/java/org/apache/spark/network/protocol/Encoders.java:134-142 | common/network-common/src/main/java/org/apache/spark/network/protocol/Encoders.java:158-166 | common/network-common/src/main/java/org/apache/spark/network/protocol/Encoders.java:182-190 | common/network-common/src/main/java/org/apache/spark/network/protocol/Encoders.java:214-224 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/Encoders.java"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bf8184198fc31a8eb0772bee35f5a1ce629cedf7cf7f720ddb2449b1bd4fe77"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:357-373 | core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:375-391 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f3739f24434f3babd2d385e2d7c10bfccb6c6f9e5f56903c1eea6a5ea2803db"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala:139-153 | core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala:155-166 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"481f975f550de152fd976c2f7c6bb86f8e55644551b3c64eb5d25365d490bb64"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): python/pyspark/ml/linalg/__init__.py:801-803 | python/pyspark/mllib/linalg/__init__.py:921-923 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":801}}}],"partialFingerprints":{"codehealthFindingId/v1":"a90eaf2c31b230831ae507d8fb6c4b9bdb796f4da02013aeb65fa10832be3068"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/pandas/data_type_ops/num_ops.py:389-399 | python/pyspark/pandas/data_type_ops/num_ops.py:402-410 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7ab18bad0d210b9c8e318d330c02e63aea7563f7cc2ffbecb0d64c348bdf745"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 41\u002B corresponding lines): python/pyspark/pandas/datetimes.py:578-618 | python/pyspark/pandas/datetimes.py:669-724 | python/pyspark/pandas/datetimes.py:727-782 | python/pyspark/pandas/datetimes.py:785-840 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 41 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/datetimes.py"},"region":{"startLine":578}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ae1d2ce2b4b90a85e0cfbdb67daaa30b5383f44cecd2bf2c64334612b465711"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 97\u002B corresponding lines): python/pyspark/pandas/frame.py:8001-8097 | python/pyspark/pandas/series.py:2991-3107 | python/pyspark/pandas/series.py:3119-3217 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 97 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8001}}}],"partialFingerprints":{"codehealthFindingId/v1":"4eb71aec96fe99f38ebd15e75ce64d7f36c4b128851ab5229b89df3c0f83a86d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (61 corresponding lines): python/pyspark/pandas/spark/accessors.py:689-752 | python/pyspark/pandas/spark/accessors.py:763-823 \u2014 These two members are one piece of code written twice and then edited apart: 61 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/spark/accessors.py"},"region":{"startLine":689}}}],"partialFingerprints":{"codehealthFindingId/v1":"971deaa9e8adfa4d20e6b5d39c80fb211ad5f5f282b6b58e623a34adc8c43d25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (50 corresponding lines): python/pyspark/sql/streaming/query.py:178-227 | python/pyspark/sql/streaming/query.py:548-605 \u2014 These two members are one piece of code written twice and then edited apart: 50 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/query.py"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce103c322ea686654bf5ab580f6be356fa22945435c8472d8befd3b100156d15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:161-164 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:195-198 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f9b95bc7b5df0658329c61d217f03e19a0c00e38f27bcc619576b6f977fc904"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:441-450 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java:502-512 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/WkbReader.java"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"60304d41f4ec26987a4a46b038cc469c8be5691f69e524c749b3fdf1a25dad42"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1492-1501 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1554-1563 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1492}}}],"partialFingerprints":{"codehealthFindingId/v1":"023cc4fa8be7571acb3fddcb78b58c2fa23c9a4799896ccf478b9995aba64d5b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxMinByK.scala:267-274 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxMinByK.scala:309-316 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxMinByK.scala"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"9214ad5928966118bc8a2c24169aaa78a1db1a6f0c16fd7e0810ea578856106b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:1812-1825 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:1842-1857 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":1812}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4c99013d06fe9ff0b249d175df3a286a102cb7d83abcee09fd256ea447dd6e8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:186-201 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:401-413 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e622fed17d4dd73cc470e25432504242f74b3b0198ae98dca0cda6a55e2cd5a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala:477-501 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala:507-519 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"aadb554416e30321297c6482dbfb5e8fd8b25c8ccd49a70b5f0bdabea3722bb1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/AsyncLogPurge.scala:55-71 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/AsyncLogPurge.scala:73-89 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/AsyncLogPurge.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"40b6744ddc5db19a3d72af1ce6e8cb74ee5a7323a461fad7b5fbaca4ad41e456"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:143-147 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:180-184 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfa9632c750a8227f58b38b4cda431a6fb80d9abc4a38755b4b2ceb7b0e38094"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala:1246-1262 | core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala:1272-1286 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":1246}}}],"partialFingerprints":{"codehealthFindingId/v1":"337c52f436bd17bab09329837add1c125220f6a58c409a1de146dd25a097c95c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:547-554 | mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala:1241-1253 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":547}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f688c843bf8f035d5be19de0b5509b0739aeda424d624d2147133f16be6a249"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 14\u002B corresponding lines): python/pyspark/errors/exceptions/captured.py:134-148 | python/pyspark/errors/exceptions/captured.py:155-169 | python/pyspark/errors/exceptions/captured.py:172-185 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/captured.py"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"e06d2e662bd3691fc9abf1948b4ef43bacd154c8cd4d4316e5b376df883815ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): python/pyspark/ml/tuning.py:1061-1092 | python/pyspark/ml/tuning.py:1625-1653 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1061}}}],"partialFingerprints":{"codehealthFindingId/v1":"3919132ffa8dd06ad977908b6be1c687374aa8e2abf52c2896fd4771574c3057"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (61 corresponding lines): python/pyspark/sql/readwriter.py:2180-2247 | python/pyspark/sql/readwriter.py:2266-2326 \u2014 These two members are one piece of code written twice and then edited apart: 61 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":2180}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bfe5d692fb61a9ff0bbecf93dc08f646b16b52a7a563cafaa5ee8cc44c1b459"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala:535-552 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala:554-571 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":535}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff139162dd9a9ecabf93aa0e33907c6f6a92631ecf3020ad487358123ee28bcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SQLFunction.scala:365-375 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:791-801 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SQLFunction.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd44663586a2da9062b3ce09ac871eb8dd7d065f72187b8f724c75f19618444c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleIntersectionAgg.scala:299-319 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleUnionAgg.scala:269-289 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleIntersectionAgg.scala"},"region":{"startLine":299}}}],"partialFingerprints":{"codehealthFindingId/v1":"470a1c2625da7e9ff4cbdf8f651d05f6bd3d8991288d7693786381dd54b86c0d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1518-1532 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1862-1876 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":1518}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e265030b59a0f30b69025406c09fff9bebc42f69cb6417f2c19293409d87daf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala:87-101 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala:115-127 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"90b98ad4de1ce7478eca97f378f1e6c58e89886b8801e7499754329d12c4e2d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:756-765 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:790-799 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":756}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbfd925888222f5507e447ef899b59bc0d9d3ae1f10407f866ef6aaffbd99ad3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:381-391 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:746-758 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"b55e6c0b79b3489157725606c51274f698fcf9520392ef53daf268b645630f70"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:728-745 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:750-766 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":728}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d755488ebab330b85152ece0f6a9df6cf26d7224fd0ae68053294442ae7d88c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:240-246 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:320-326 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:405-411 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7874427b97afc2ca5f2dfdec9619a550165c46ba3f7cefe58966481bc6c11c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:383-392 | mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:336-344 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"785f455cde0260792a5fb3efa441ab01d403d65255c2ba0bf842fdcba3996735"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:650-661 | mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:666-677 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":650}}}],"partialFingerprints":{"codehealthFindingId/v1":"25bb6023848fb5ff780dd4e7a4f3bedfe759fa5187189cce0107e0674215b6d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:259-270 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:227-238 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"ebaf711bbac2d526cd1b1790db7b751501ea96548f7f57ce916edc4612a4d57b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): python/pyspark/ml/clustering.py:2144-2183 | python/pyspark/ml/fpm.py:495-531 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/clustering.py"},"region":{"startLine":2144}}}],"partialFingerprints":{"codehealthFindingId/v1":"06b50016ab03669a91a4f31a855d4c7516569659be2f2298d6cb5285e73f3d20"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (60 corresponding lines): python/pyspark/pandas/generic.py:1661-1720 | python/pyspark/pandas/generic.py:1725-1784 \u2014 These two members are one piece of code written twice and then edited apart: 60 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1661}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8210e40108a9007deb219e80c2a74908af83c71cdb450a344698e8f1654502d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 9\u002B corresponding lines): python/pyspark/sql/connect/expressions.py:820-830 | python/pyspark/sql/connect/expressions.py:833-841 | python/pyspark/sql/connect/plan.py:3179-3189 | python/pyspark/sql/connect/plan.py:3194-3206 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":820}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e4cc8f5ddb5b8b8485e6320579f5415e631ab4d5eeeb77369385bd1c18ef61c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/sql/connect/plan.py:1930-1936 | python/pyspark/sql/connect/plan.py:1952-1959 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":1930}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c201c05ced2ce113c60182602840f8cabca74100020bdfcb2f67ebac1863070"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/sql/connect/streaming/readwriter.py:518-524 | python/pyspark/sql/connect/streaming/readwriter.py:535-541 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"44b31347c3ec4e535b4f7a55fdbe2e902de71ba5d1c61024ba9dd3d9559756c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/Column.scala:492-502 | sql/api/src/main/scala/org/apache/spark/sql/Column.scala:525-536 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Column.scala"},"region":{"startLine":492}}}],"partialFingerprints":{"codehealthFindingId/v1":"870fe545d822353412052b38ae3f5a8357c014c8cb6bb9403c73dddba0e966ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala:521-527 | sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala:529-535 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8aaa1047c30112167d744cdbf5773443fffcb7b3d7475dd7a635530b3f4efbe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:886-898 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:984-999 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":886}}}],"partialFingerprints":{"codehealthFindingId/v1":"86d69b5c941ac49fafb27f8bb5c81554d26d38892996444fb530307d3224feda"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala:1558-1567 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala:1578-1587 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala"},"region":{"startLine":1558}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a1c3b1185cdd2f1ff613d6d1df93c380774098d1fe5e1694d42dc8f28938906"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala:542-552 | sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala:560-570 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f00d16e06d2a9eb390be83f480a8946dfc66bcdec7c6b6c26a44b32bddf5a43"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/resources.scala:92-102 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/resources.scala:114-124 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/resources.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e403383741c26f73324754766baaf0cd5d83148f5d68b0031b4a630711ce991"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala:1186-1197 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ViewInspectionExecs.scala:84-97 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1186}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef6d3d05efe1f3870d8d4aff84813ff95b6a9afc18de371c4a7b778c84d60a49"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:518-541 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:645-662 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"5948eb51f8c3f5d9a72b899a0fa9db01bbff0446a698abe59dc718f9561da581"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala:184-200 | sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala:205-219 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bd1b80206062c59a4d9c9d225bf5d4958b04607c98241eb4389ea77c287b073"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java:210-218 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java:222-230 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa9266fa01dc01d86eb172ce2bee05924596737bce3b45245dc955b8098eb427"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:799-805 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:826-834 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":799}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb1d12e09caaa4d1704fcdf4811313273417fc2f9e29ce11a18f7a635d89922f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1413-1429 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1431-1443 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1413}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e1449a44ccdfe3e70ad6b811379f67d0a8712575465bf702ef35724354087d0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:745-750 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:756-763 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":745}}}],"partialFingerprints":{"codehealthFindingId/v1":"f484594aaa742aded2a47b9470ca4b9b0e70278f6b854604343ac1bddbe32c03"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): core/src/main/scala/org/apache/spark/util/Utils.scala:3227-3235 | core/src/main/scala/org/apache/spark/util/Utils.scala:3307-3314 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":3227}}}],"partialFingerprints":{"codehealthFindingId/v1":"e926cf0ef9988c50d8630957412bba46bebdd9c367beccf3dad4ee42f1c9bda2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:774-787 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:281-293 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":774}}}],"partialFingerprints":{"codehealthFindingId/v1":"4be082d0eb01725c6ce40f06a72e953401d3a4c352cf2cf79b3fc8a322ad36ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/pandas/categorical.py:99-111 | python/pyspark/pandas/indexes/category.py:176-186 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/categorical.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3006f34d27ea108200f608c50f74cbe4bebabb6f14bd5d8373720148bc5dc2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): python/pyspark/sql/pandas/utils.py:110-136 | python/pyspark/sql/utils.py:114-142 \u2014 These two members are one piece of code written twice and then edited apart: 27 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/utils.py"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"64ee5a50c877b7d45ffbdf50f681d3738c0b5f3e8e78ab2caaefc67dcfb2faf0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala:120-137 | sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala:265-280 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7820d0e5a17c9f97949288252a94d0d851226091c5aceed2bf9e45c0c881f3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:5586-5599 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:7175-7187 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":5586}}}],"partialFingerprints":{"codehealthFindingId/v1":"5123ed4a2806859a4735140394d5dee2b90dc104b819d76dca71692ac166d48f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala:488-497 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala:499-509 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala:511-521 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala"},"region":{"startLine":488}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bf9f4ca29d8879a532a2709f6ba7a2da530d213298032337d111495378d3280"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java:530-538 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java:558-566 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":530}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d04f66277af2d3d424540e7dffd2afcf0ae5e8000123384695255d03215a34d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingSinkCommitRunner.scala:53-74 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:759-777 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingSinkCommitRunner.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"e25b7e2f0f6ab3e3e659dcc583353d095f8758f70f2453a18ed80cd5ee104222"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:540-548 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1020-1028 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39cf72ab3348ff4f1423fb31bd21ecc24dceee5a473e7580f314ddd39ab889d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala:50-57 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:100-106 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"9aca2d2f9098dbe76daca9a6b5b708ba390a7505e0dee64fe6721972357223f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java:544-550 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/AbstractFetchShuffleBlocks.java:51-57 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java"},"region":{"startLine":544}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4e393450039400bb8bd95a052690a4133596adb53fe599d515faaf66f7d293b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:55-64 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala:75-87 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f271170cad21556a3606b2126d5967db4664d7e156da10f1c2dc86ee797330c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:331-354 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:296-317 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"361e596df34816309448848de509a5279d1c62948451efa5b85514ebc71ea557"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/util/DatasetUtils.scala:37-43 | mllib/src/main/scala/org/apache/spark/ml/util/DatasetUtils.scala:72-78 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/DatasetUtils.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d036d3daed95e4e70fb3f610eee15665a685127fb5a2c881f90858984e1416e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala:73-80 | mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala:50-57 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"09d1baa71ab5189e3984a10e94d7546ff2e62ac69a97600519c2349a69082a4c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/core/files.py:150-160 | python/pyspark/resource/profile.py:323-335 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/files.py"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a3863c6072e8af3efdc11c4afa35bd05a59bb5546fea98e006aa94cff020c1d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:413-425 | python/pyspark/pandas/data_type_ops/boolean_ops.py:428-440 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9ceac942132591383d150c28201501dcdcfd882e6df45707234fde4ce24de42"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 16\u002B corresponding lines): python/pyspark/resource/profile.py:163-178 | python/pyspark/resource/profile.py:294-309 | python/pyspark/resource/requests.py:355-370 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 16 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/resource/profile.py"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"5056efa49b1ccb57a26ddd1b9431ce10e6bd01cc2c23582298ea31fbea87a8bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala:256-268 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala:99-110 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"50dde3e4e29ba0323cefa87e78d88fa5c92c6445aeca90bdbf5f402615b2ed9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 13\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala:66-78 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:301-313 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:339-351 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:367-379 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:403-415 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"6db86ae732f9458523a5dc42f233ed80fcfe077347d0abe89d13236d34e757f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowKeyOperations.scala:339-347 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowKeyOperations.scala:363-371 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowKeyOperations.scala"},"region":{"startLine":339}}}],"partialFingerprints":{"codehealthFindingId/v1":"e834d0da3628de5e628a1262227a236d377cb5c76403e562bf923e3c145ca034"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala:112-127 | sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala:143-158 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Util.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"d360955c055be967949852c7d9b0cb6c06d0cbeb928f419a34d45a35a1847cca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 8\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:2876-2883 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:2888-2895 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3645-3652 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3657-3664 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":2876}}}],"partialFingerprints":{"codehealthFindingId/v1":"c234a6ed3868f6fa695a29c39870ce8353c1f5bd2c18ac926d2ee5573cd1d1ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationMap.scala:69-80 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationMap.scala:110-123 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationMap.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"57658579ba3590174ab84aaae6e169881d584b6a079486bd0176c796846ef3a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/timers/TimerStateImpl.scala:181-192 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/timers/TimerStateImpl.scala:198-209 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/timers/TimerStateImpl.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aa9bd58697ecc3a9f5bacd87ce745d2e0dde2b191b2361fcf8a4a5a31709c8b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala:1574-1583 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala:1624-1634 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala:1648-1657 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala"},"region":{"startLine":1574}}}],"partialFingerprints":{"codehealthFindingId/v1":"31f080f887b1fece74caaeb0b1e21fbefeedfb7a7f9e002c9ef3d1dadd9f0684"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreRowChecksum.scala:237-249 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreRowChecksum.scala:463-474 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreRowChecksum.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cab65a7fbfb06af8636f586d38bb02e856a4b24b399b321ca579ab0dd7d2a0a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:1053-1075 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:1083-1104 \u2014 These two members are one piece of code written twice and then edited apart: 22 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":1053}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfec4d4eec08dcdca863cf69de4466df2ad18ba5784da8ac06b08b223d11ebac"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java:47-63 | common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java:157-171 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"4620eda38bc1b4f776eccfb59acc50f9b87c9254f84eb0a72e0909b6755fa568"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java:245-252 | common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java:254-261 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"f965ffc499cbd52cec8180250e6ebcd87342a4477fcc968ee42bd98938bc0f35"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:208-217 | mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala:320-329 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"2211f6708592e28916838f611e63340947c7ebc9060516fea1adc4ddf6ca9cd9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:475-488 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:504-519 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala"},"region":{"startLine":475}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a1c22c134d5221da3555a3e42b3d0c7b70a7529a5000c8cf9074fe017513770"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/ml/classification.py:1606-1626 | python/pyspark/ml/classification.py:2380-2400 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":1606}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfa975cbeca0e48dc049a9192275165b33a50a81f97ae3a76ba8cd426a1042e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 17\u002B corresponding lines): python/pyspark/ml/classification.py:2021-2038 | python/pyspark/ml/classification.py:2472-2490 | python/pyspark/ml/regression.py:1359-1375 | python/pyspark/ml/regression.py:1702-1720 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 17 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":2021}}}],"partialFingerprints":{"codehealthFindingId/v1":"1744b0d0beed504a785e449e3672a745d011e61f909abd6b4b2eaf277cbdbbbf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): python/pyspark/ml/param/__init__.py:492-503 | python/pyspark/ml/param/__init__.py:513-529 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/param/__init__.py"},"region":{"startLine":492}}}],"partialFingerprints":{"codehealthFindingId/v1":"987e7339c9905c07b5cadca2f41f4359e2dd3af27f7aab022a5ef6a64c8aec8a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (8 members, 7\u002B corresponding lines): python/pyspark/pandas/window.py:71-77 | python/pyspark/pandas/window.py:80-86 | python/pyspark/pandas/window.py:89-95 | python/pyspark/pandas/window.py:98-104 | python/pyspark/pandas/window.py:107-113 | python/pyspark/pandas/window.py:119-125 | python/pyspark/pandas/window.py:128-134 | python/pyspark/pandas/window.py:1612-1618 \u2014 These 8 members are one piece of code written 8 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 8 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd7fc9b0e6dc17669eb67d95a73f52e184c5d5741a958fd4fa00f2bc61adc280"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/pandas/window.py:156-162 | python/pyspark/pandas/window.py:165-171 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"636d493fd4c72122c835f8bb2161b1dc4e2186d2d97ff76f02bb1eacf2da925f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/types.py:753-767 | python/pyspark/sql/types.py:856-870 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":753}}}],"partialFingerprints":{"codehealthFindingId/v1":"f24971a9ac66c48983ef8775e9616b244d439604284323b62021a849ad77bea6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (8 members, 9\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:217-225 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:271-279 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:282-290 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:293-301 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:447-464 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:517-528 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:531-542 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:545-556 \u2014 These 8 members are one piece of code written 8 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 8 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"de0bc1919785d6a971210b616f1e35b56ba1f7ff827989b11ff781c27c4e10a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1588-1598 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1609-1619 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1588}}}],"partialFingerprints":{"codehealthFindingId/v1":"c64a1a7065a1af5088cb7fb55e3d4991042194fd037201bf42537ec17e1a939f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1499-1508 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1594-1603 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":1499}}}],"partialFingerprints":{"codehealthFindingId/v1":"b218b38d90c452226e94b80a05a5a13a58acdb2b34a8c886f649c6c6ec0600a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:3019-3029 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:3211-3222 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":3019}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fc0437cbe36bddbd5abd230b2ea3128cc52a05088da01acc7c6b43795d2a5c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:608-618 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:621-631 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":608}}}],"partialFingerprints":{"codehealthFindingId/v1":"cea67edc882733bfd940945f702da2a46f47156f0c24ea94da8f494cb7afdfe8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/Flow.scala:520-534 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/Flow.scala:541-555 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/Flow.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"381fea95492ad0c0df4fb23ccdd842f3d7c41c8da5f4d5c6db1245f9becd5980"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:371-377 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:395-401 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:420-426 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"0849e1b3992f5fc73abfbfbb550f9936f835ba1aaedd3794a9268c675c3c0ae5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:457-463 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:508-514 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"37a06c81c073c14f4f52c74d78ca2d6b43a701f5655252bcf244394a2cdf4d6f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:246-255 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:278-287 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc4960f3891104d7760c90de6d3318fe7457e5880045e85a1cd3fcb78ca01774"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:219-228 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:189-198 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e7b91eb9318e0e98cb6ae3bcbc82e6ad48b030706b28c37668c6d56de4f5da5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala:116-128 | mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala:134-146 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"57cd9cb0bab134efe0d76c74cb30dfad45b0211d0b8f324516ece2f0e9623b26"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): python/pyspark/core/rdd.py:5123-5136 | python/pyspark/sql/udf.py:54-71 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":5123}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d019134419d397708f8a95f2717456bee29e95386a60b1244050e72b67492ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 9\u002B corresponding lines): python/pyspark/pandas/data_type_ops/num_ops.py:146-154 | python/pyspark/pandas/data_type_ops/num_ops.py:157-165 | python/pyspark/pandas/data_type_ops/num_ops.py:195-203 | python/pyspark/pandas/data_type_ops/num_ops.py:206-214 | python/pyspark/pandas/data_type_ops/num_ops.py:217-225 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a03225d2e8b27b351884b094282897be7f884802edddcf9c788a5a9e9031679"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/pandas/spark/utils.py:180-192 | python/pyspark/pandas/typedef/typehints.py:943-955 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/spark/utils.py"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d26b09013aeac146c2dd89196f4300cf7d4721809acd022a9e06878e926f9ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/pandas/window.py:1028-1034 | python/pyspark/pandas/window.py:2252-2258 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":1028}}}],"partialFingerprints":{"codehealthFindingId/v1":"56d88735a0637f04fcc94d65473533b54d8b9d3f339478acf6e6a4770722a65f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/sql/connect/dataframe.py:818-828 | python/pyspark/sql/connect/dataframe.py:837-847 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":818}}}],"partialFingerprints":{"codehealthFindingId/v1":"012d7f797050dc0f046282f8d4b767a02e5c82d51b8959bee88432571d5d41f2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/RebaseDateTime.scala:403-414 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/RebaseDateTime.scala:525-536 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/RebaseDateTime.scala"},"region":{"startLine":403}}}],"partialFingerprints":{"codehealthFindingId/v1":"941b3b034e3d964f154d64462af11aa55cbfe1b28b07ccc49af434d4bdfec774"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:152-155 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:190-193 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"256783b23b9cc14a9ce8bd04fb90f2ba01e76d111e57141aa9aa1bbb14b9cc71"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:540-547 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:558-565 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"49de934a304d60646c93cd094ef3c02ec62b35f04a251a112bb8139cc531d320"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/AttributeScopeStack.scala:108-122 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/NameScope.scala:1429-1440 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/AttributeScopeStack.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"7638f0e566612553e6b0e62eea334e09767060ea46674849d04274db47d0c7cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/constraints.scala:351-360 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/constraints.scala:383-392 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/constraints.scala:421-433 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/constraints.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"d90c52d3a369bd7ffd1ef9ab7145d3722f2ad61bd4fc1be9361333d80e3e30a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/thetasketchesExpressions.scala:118-134 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/thetasketchesExpressions.scala:178-189 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/thetasketchesExpressions.scala:233-244 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/thetasketchesExpressions.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c4df7ae139b41a71d263f4d4d2584f93f845ca4c8163ff979d04cbc10027092"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 15\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala:291-305 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala:362-376 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala:459-473 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"99150d17e217fc36e41e804baa712fe9f103da0ebec2222cca3953a5d6a74a6d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4389-4403 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4405-4419 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":4389}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc0f5611c832ad4175864240d002e218758a6efcef687c66424eff2baa185e93"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala:118-130 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala:209-217 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectConfigHandler.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4fd541b7af8610479f9709d1f508119508f3189185a045e6b6c9f0ebf6211a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java:173-188 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java:191-204 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java:319-330 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaBinaryPackedReader.java"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"b23364bd194282460b7c2f2182429cfb7ec64fbe1c34e53e5e4518aeacc2b2da"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:593-601 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:604-612 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca573b42cbfd5eeb81f5597f38fd140d5bf5fecfea7dc4db4b38c830a946bdc2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SparkPlanGraphWrapperSerializer.scala:95-104 | sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SparkPlanGraphWrapperSerializer.scala:118-130 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SparkPlanGraphWrapperSerializer.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"ced9fe417aba2deb7e5b68a34452aa588a53c74f96e43aff98b6d204cf79dd19"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:313-320 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:327-334 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"199f5a9f4a5f20d7b8174d0c0eb449990ba826585a61ce92f9c47c9ac277de13"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:347-357 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:379-389 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":347}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1fd5b6d2225878d68e70059d109dfe2f85dbc36da85c5beff470db947542dc8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): common/network-common/src/main/java/org/apache/spark/network/client/TransportClient.java:198-211 | common/network-common/src/main/java/org/apache/spark/network/client/TransportClient.java:229-240 | common/network-common/src/main/java/org/apache/spark/network/client/TransportClient.java:256-268 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/client/TransportClient.java"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"612f8b98e3cfabbfee94536fb0217ffe4eefce19974586dd939d3e03bc0b6e30"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 8\u002B corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:225-232 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:382-389 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java:119-126 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:678-685 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b094d16060ec7267d87fa23b0ee6437dba7dc4232070d22b9c83a8e1fb9890b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): core/src/main/scala/org/apache/spark/MapOutputTracker.scala:1546-1567 | core/src/main/scala/org/apache/spark/MapOutputTracker.scala:1573-1589 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1546}}}],"partialFingerprints":{"codehealthFindingId/v1":"46b7540586cfe74ede0f82ff188138da0fec2165842f4efcbf236b1be74570c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:174-179 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:196-202 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbe95bf7688d729e299d03183d3154ddefa500bb78b8399a20c78389412bcd17"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:111-115 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:113-117 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"9eeb66e50d5e4e58870b61394dbc866b27fde2e5e0601e272dbb25b480db3cb6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:348-360 | mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:470-482 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"296826ecf6a6c346567a265c9fa255c825d10de5ed5a080705f4ff821d3ba087"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:121-127 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:164-172 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"43d4c8ba6b4a23fa694820fd94c72406225757be861e9908eb4aadbd64a6ceda"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (55 corresponding lines): python/pyspark/core/rdd.py:1858-1912 | python/pyspark/core/rdd.py:1917-1973 \u2014 These two members are one piece of code written twice and then edited apart: 55 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":1858}}}],"partialFingerprints":{"codehealthFindingId/v1":"23bd77d78ce7e6446f1508494fe1d861b86991f4e050ae40eafbc9bc202ec17b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/pandas/numpy_compat.py:226-230 | python/pyspark/pandas/numpy_compat.py:234-238 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/numpy_compat.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8ded3c86d9b16ef44e21e5973927fd63c7cb85470abae0bd5f4c85e8b9048e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/pandas/usage_logging/usage_logger.py:57-76 | python/pyspark/pandas/usage_logging/usage_logger.py:86-107 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/usage_logging/usage_logger.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4aece72e47133dab541ddc5eab92d7ef9bd25509592c2fce866153bd070a93e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/sql/classic/window.py:71-81 | python/pyspark/sql/classic/window.py:85-95 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/window.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d0f2fbc87e1686a616f5b28a1fc5edead5ad1450171fefd19ca4c4c6a0f5108"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (54 corresponding lines): python/pyspark/sql/functions/builtin.py:24028-24081 | python/pyspark/sql/functions/builtin.py:24086-24140 \u2014 These two members are one piece of code written twice and then edited apart: 54 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":24028}}}],"partialFingerprints":{"codehealthFindingId/v1":"b53a84f12ff65ecb461af6a8b8e4ad1869803959ca3704cc83f5e3351bf0e4f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): python/pyspark/sql/merge.py:128-137 | python/pyspark/sql/merge.py:168-177 | python/pyspark/sql/merge.py:205-214 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/merge.py"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f0da5cf96ab89109f2681719884ff58c202dc55db3352cb5ebb16c0586de4bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 26\u002B corresponding lines): python/pyspark/sql/readwriter.py:1508-1559 | python/pyspark/sql/readwriter.py:1754-1779 | python/pyspark/sql/streaming/readwriter.py:1204-1251 | python/pyspark/sql/streaming/readwriter.py:1260-1308 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 26 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":1508}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9f3462fac3ef6edc229c94bcb2e9c43cfd1a32cc808c1de1e9719528c1524b9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:384-391 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala:421-430 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd362a20c16fa63388b0bd9ce2262e0603be26667fd2113e20d37f39c55ec649"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java:54-58 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java:61-67 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/BitmapExpressionUtils.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"218c0a17a8263ae590b4809b9691275d52ba4067a911f7ba34047ef6c07c2c09"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/JoinLikeResolver.scala:89-105 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/SetOperationLikeResolver.scala:123-142 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/JoinLikeResolver.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"3406b4e06544be84647ee6e8d89356b2ee79fbdf007fd29c5bb1e40fe8d96311"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:119-128 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:136-145 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:153-159 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e50808a15894b44bd4e28f2645a07c09f1cb4a2eb5d47dbc77bb5a762fd1caa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6805-6812 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6845-6852 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6805}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca2b1277c4e505999c1903d44083120476249c3f83c2509b5a459356a74056e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedReaderBase.java:55-66 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedReaderBase.java:73-82 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedReaderBase.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"aaf9c53dec8fe26362e2c96b58230fcc41c3b67bd88b1df75b8d6a5fc3685181"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): common/unsafe/src/main/java/org/apache/spark/unsafe/bitset/BitSetMethods.java:40-46 | common/unsafe/src/main/java/org/apache/spark/unsafe/bitset/BitSetMethods.java:51-57 | common/unsafe/src/main/java/org/apache/spark/unsafe/bitset/BitSetMethods.java:62-68 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/bitset/BitSetMethods.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa3095ee4e2db6aaee79b35a1ac9f4c23a131a0b141f44e8b56803d139216bf4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java:302-311 | connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java:345-354 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"23eb5b61e898973c2684d72eda8768ae6248a840b03b5bc08f53feee831de3d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): dev/next_version_candidates.py:44-49 | dev/pr_merge_status.py:93-101 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/next_version_candidates.py"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7dab7ed9463a6e9bf45c77e720f578702ebf91010687734667a90ed70801caa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:268-280 | mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:431-442 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala"},"region":{"startLine":268}}}],"partialFingerprints":{"codehealthFindingId/v1":"7af2d1857b579088fd7de0f8c1e67cb93c073aefe6f1c11fff08525eea5bd299"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala:160-171 | mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala:174-186 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"09c5dc856022c1d15f1010803f3b7556e4e39d645b9db2488fa7e4cc5e8444ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:197-209 | mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala:65-76 | mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala:223-235 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"736a6d217568efd84eec75ed81fcbe3d9ece1af596c4991e6f3ec77f24208b68"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala:41-47 | mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala:65-72 | mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:64-70 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcb2af6227daa831ca5fb0eb678f6789729139d9b01a3d6e0c0e6704815e2467"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 8\u002B corresponding lines): python/pyspark/mllib/classification.py:623-634 | python/pyspark/mllib/regression.py:243-252 | python/pyspark/mllib/regression.py:454-461 | python/pyspark/mllib/regression.py:631-640 | python/pyspark/mllib/regression.py:842-850 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":623}}}],"partialFingerprints":{"codehealthFindingId/v1":"d800182fa402fbc053bb2fb809b6d02715c7edc6c534d344b251418d67ada0ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): python/pyspark/sql/classic/dataframe.py:419-438 | python/pyspark/sql/connect/dataframe.py:1104-1130 \u2014 These two members are one piece of code written twice and then edited apart: 20 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f01d153f4f126cc3b786919fb72a685cee92f28e75e66b8aeaeb9b6ff4625d2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 5\u002B corresponding lines): python/pyspark/sql/connect/dataframe.py:2231-2235 | python/pyspark/sql/connect/dataframe.py:2238-2242 | python/pyspark/sql/connect/dataframe.py:2245-2249 | python/pyspark/sql/connect/dataframe.py:2252-2256 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 5 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":2231}}}],"partialFingerprints":{"codehealthFindingId/v1":"9529fc8b02d82f42d1b84d12287539a6610dde85424ac65a4ddec53535828083"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala:560-570 | sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala:573-583 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/Decimal.scala"},"region":{"startLine":560}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a9ccde356610168e194f11431aaa3cc9b061d777adecd7376e7437f11b09489"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 6\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:44-49 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:77-84 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:44-50 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:78-84 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 6 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"830231f46740b819d6682a0c176dfa6c25661f0a8caec0afb13e24020a3f1414"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala:896-928 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala:999-1032 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala"},"region":{"startLine":896}}}],"partialFingerprints":{"codehealthFindingId/v1":"d53e3ece37079cf8bf25439fb6452a9272943188577177608d4f36b6436dbb9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 14\u002B corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:23-36 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:38-51 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:53-66 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:68-81 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:83-96 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala:98-111 \u2014 These 6 members are one piece of code written 6 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoSpecializedArray.scala"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"70c9c2854d290dd7bbc02798b43c44ff1709706c349a668994483753c862dd1e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:1300-1312 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:1314-1326 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":1300}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccd2976fb5b5fc0af1f91251a491cac6c6960989c2442580d95eebe46deb5b6a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:1214-1220 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:1223-1229 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":1214}}}],"partialFingerprints":{"codehealthFindingId/v1":"4244d3eba36b9d6b167cc90a32c25820fd7b8304bbe76b7e8a3a88bcedafdcf8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/connection/DB2ConnectionProvider.scala:35-46 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/connection/MSSQLConnectionProvider.scala:72-83 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/connection/OracleConnectionProvider.scala:35-46 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/connection/DB2ConnectionProvider.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f31ea65ce4de31e34f43306d75aadd8c627088e699badc893269cfc947d76a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 15\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:648-662 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:820-836 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1124-1138 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":648}}}],"partialFingerprints":{"codehealthFindingId/v1":"15b2a44cf1c4db10a8b687f851d56cd1be31c80395865613c428aa0cbd0f8dc3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:814-828 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:830-841 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":814}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab352a4fac53d0b60b675372dd48ca8ee12f842d16fd83cc654210a6f5c6a83b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:1304-1315 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:1319-1330 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1304}}}],"partialFingerprints":{"codehealthFindingId/v1":"e392bb4f4e6d41175967db3d69ba1f2c7cd57571d18c223e9202d5c61afff1df"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (7 members, 15\u002B corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:116-131 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:167-184 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:190-207 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:210-224 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:234-251 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:254-268 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:279-293 \u2014 These 7 members are one piece of code written 7 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 7 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b9aa2be76be4578b3868db07c58d6ebe15e9e7b01524e1f5523d761033b3c4c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/utils/src/main/scala/org/apache/spark/internal/config/ConfigBuilder.scala:238-244 | common/utils/src/main/scala/org/apache/spark/internal/config/ConfigBuilder.scala:250-256 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/internal/config/ConfigBuilder.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbe8e096f21cf1d342fc380ac8dbe153fd12ccc32086712a0e8b3208416ce468"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala:767-779 | core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala:781-796 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":767}}}],"partialFingerprints":{"codehealthFindingId/v1":"85456ee931ac2f3c491a1fba81c7aeac6a31686a089f8e1f8a75fe03a7b9aa5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala:153-162 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala:184-193 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"937bea8eae89aca720a693adb44aa373c6b0b7856940416cc1c8b2e2d97beea7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:157-166 | mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala:161-168 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"25857acff1b10b44219904a6f2b8c4ae216b55b8d00667e7a4a845f2c742f364"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala:215-226 | mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala:230-242 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f74850b87ccebf0f9d9862006baea40d60a1ab975a059a2cc3fb99c7341af63"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): python/pyspark/sql/classic/dataframe.py:1823-1838 | python/pyspark/sql/connect/dataframe.py:1839-1855 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1823}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0fbfba5a5363e160579c6c8a4ded89c18f45e1180564db69e064d09f75a0e5b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/sql/connect/plan.py:1476-1479 | python/pyspark/sql/connect/plan.py:1542-1551 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":1476}}}],"partialFingerprints":{"codehealthFindingId/v1":"8468b975b85845b6f73867f629645fc4f2368654894b3044c103a980b93c5806"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:149-155 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:157-163 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:165-173 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"77e2270f43fcf30c897526a02e8843e85a8bba053eea700ccdd16964ca61dc01"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:1000-1008 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/Statistics.scala:115-123 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":1000}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cdff17ef09ef6d940f5fa5feec4737ad1433d0929a70104d4cc836025745871"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/DescribeCommandSchema.scala:38-42 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/v2Commands.scala:1040-1044 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/DescribeCommandSchema.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"06077c35e31e64a1d6ed64a38d18d7c4801440344b2d1f0b7ebf1348de137313"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 11\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala:538-555 | sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala:557-568 | sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala:268-278 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonExec.scala:103-124 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowGroupLimitExec.scala:74-92 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala"},"region":{"startLine":538}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e840e73e1ee47a1492bba86d100fa15300175405b177b119cd5f26dce0a09e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 11\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:164-176 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:178-194 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:210-220 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:252-262 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"d84f3e3cb35ef89e45e1392113a70d61b83cd8288a26d685ee1e527e3064a011"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala:502-510 | sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala:693-701 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"037c30a63185e416a79fb86d9c30a56572f896b571ea91392a40f76cb40678d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala:392-397 | core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala:442-447 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5da84f78e8517a323572b824062e19e299a232a93c05f31a4c30ca2d2232bcf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): core/src/main/scala/org/apache/spark/util/io/ChunkedByteBuffer.scala:305-315 | core/src/main/scala/org/apache/spark/util/io/ChunkedByteBuffer.scala:317-329 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/io/ChunkedByteBuffer.scala"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"104de4130cc51270ae8ddc214bac7c5c8ebeda39aab2c4e40cd53c16d9ee70e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:308-318 | mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:400-410 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"fef856ab322ca46749d62900751412eed3fa7ea6aa1f242e57d556561d03f973"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala:844-854 | mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala:321-333 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala"},"region":{"startLine":844}}}],"partialFingerprints":{"codehealthFindingId/v1":"2393b44af5c1ad6f312c0fe3351f57e5c32d38c87abd983d4a589049b78f36aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:739-746 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:802-813 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":739}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e92e4499292681f8d1c43b2f2f1cf3a9d0d276571e4371ebf4a673a48d4be98"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/pandas/data_type_ops/boolean_ops.py:171-180 | python/pyspark/pandas/data_type_ops/boolean_ops.py:193-202 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ca109a1c13a782506fc8e240c9508b6d6eaa5531e265952281dde242ea996b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): python/pyspark/sql/connect/readwriter.py:771-780 | python/pyspark/sql/connect/readwriter.py:785-792 | python/pyspark/sql/connect/readwriter.py:804-814 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":771}}}],"partialFingerprints":{"codehealthFindingId/v1":"be2479b120f445ffb41bd6b5d64f3c0e907f971d0fd07367d281dce6b9e7cc3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (51 corresponding lines): python/pyspark/sql/readwriter.py:716-775 | python/pyspark/sql/readwriter.py:1113-1163 \u2014 These two members are one piece of code written twice and then edited apart: 51 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":716}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8c730efaba4dbd08ed7e8f4bf621c888b90bde1777dcfd33228327de4827ecd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SparkParserErrorStrategy.scala:91-101 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SparkParserErrorStrategy.scala:103-112 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SparkParserErrorStrategy.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"8aa1daf5873fc8e7909be91585eceef5af75946143a4c80746aafd236e6c86d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:1007-1021 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:1047-1066 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1007}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbe9c4a94010657ecbaa67e8ad8605eed8ce6a9016026001e4512097d676e037"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/errors/CompilationErrors.scala:73-82 | sql/api/src/main/scala/org/apache/spark/sql/errors/CompilationErrors.scala:84-93 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/CompilationErrors.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"549993666dc0a259b6d4b80c3c7317d201d42081b9c34d2784f6d8c7cb7bcbd5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala:66-74 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala:160-167 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlOptions.scala:60-69 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"e054610039547f03015068ec5d4aa6620e4e97825fde012ddb6ecc73868ac5d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:8116-8127 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:8132-8143 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":8116}}}],"partialFingerprints":{"codehealthFindingId/v1":"557ced136971c537e9708c36dbb43640ac9c33fed59ee64987f879f197e643e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/ParameterHandler.scala:225-234 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/ParameterHandler.scala:246-255 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/ParameterHandler.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b5ccbc227900e6c75a284b9a5d6dca5e0346835a9cd68fc7a74990aec3957f4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:366-373 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:375-382 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0cbcf0619755bef1c17afff5bfbd183b94831c1c2029ff5532e269d4c7f3f9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:768-776 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:899-906 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":768}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc773da998fe420618ac008e7f0378d8150ad47260fb7ef54a353ef999266ae5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala:246-258 | sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala:366-377 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ee096b634d0ed13136f9c98bf5e9641db3230287da22a820ba8c98f09185a69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/server/SparkSQLOperationManager.scala:91-100 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/server/SparkSQLOperationManager.scala:107-116 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/server/SparkSQLOperationManager.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7ca257d89d2dde4bf35d1545868224da888b91e1cd7e3df057fa1dced75349c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:77-92 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala:99-113 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"14e3754d025fc45127f78020377f51a20953db8ad0ae49b696d878c9b05f4f4f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:554-563 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java:353-363 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeSorterBoundedSpillMerger.java:243-256 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6e9776a7c1429c81d10301de55593e98580f69941d116c38fccf01c05b71829"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): core/src/main/scala/org/apache/spark/scheduler/cluster/StandaloneSchedulerBackend.scala:303-308 | core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:150-154 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/StandaloneSchedulerBackend.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"a04eecd18e39e70b6517ba3129dc782c4e83669e4cd87c0fefc5027956662ab3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala:224-233 | core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala:236-245 | core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala:248-259 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef645b139c613b4d23566c9d3c0a04ece7e960f9b34b59d96851d13030964748"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 50\u002B corresponding lines): python/pyspark/pandas/groupby.py:445-515 | python/pyspark/pandas/groupby.py:518-588 | python/pyspark/pandas/groupby.py:591-655 | python/pyspark/pandas/groupby.py:776-840 | python/pyspark/pandas/groupby.py:979-1028 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 50 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":445}}}],"partialFingerprints":{"codehealthFindingId/v1":"030c04ec5ae8703a8363f24290452a52d3313b0033134bb8a4788369159cdbde"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:2685-2695 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:2703-2715 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":2685}}}],"partialFingerprints":{"codehealthFindingId/v1":"83a66fbac3998650eade986b762152a8c8a553e07af0df8cc9aa6f20d9458430"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ApproxTopKExpressions.scala:89-103 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala:866-880 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ApproxTopKExpressions.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"2906e7b98f14b73023662757375dec12178c8addbd3b96cee44dc0eff83631cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 13\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/UnwrapUDT.scala:35-47 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/WrapUDT.scala:45-57 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ml/SparseVectorToArray.scala:49-61 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/nullExpressions.scala:245-257 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 13 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/UnwrapUDT.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"049d43eaff8d49fe249b6498c626469ba25a3eb6671de38012408619e877cd45"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:671-685 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:777-791 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ce2f0c9edea98a7b46369dda6ee0fa034afe47cf97cd10e4ddde019416c20ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:263-273 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:442-453 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"87bbf3bf6ca59346bbf648e036788d5eba1686f181dbf27b5de1e5274ea91a53"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala:137-155 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:989-1007 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4ad421bf9b71b19822dd45af146550a369e44b63b1df518dd6c7984c1bb91de"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 10\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:744-754 | mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:759-769 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:249-258 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:265-274 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":744}}}],"partialFingerprints":{"codehealthFindingId/v1":"3421e84832b4decd2c590e584b2a766a55577987dc547cbc9d841b4bc28a38b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4744-4756 | python/pyspark/sql/functions/builtin.py:15461-15531 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4744}}}],"partialFingerprints":{"codehealthFindingId/v1":"da991fa97088841a25c767bb2b76fe153e879f76cac32af1e13207aef4d81570"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:143-146 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:185-188 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8f32a323677474a449d7e515b21bf59ff0a13aaac70bb9aea0a4d4d2311d411"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 12\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ToJavaArray.scala:42-54 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:3472-3484 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:704-715 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala:356-368 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala:616-628 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xmlExpressions.scala:306-320 \u2014 These 6 members are one piece of code written 6 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ToJavaArray.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"38ec826dd9628958aa9c2ac5cdb1575cd1f0f4fc37f836e3592fef94b78741ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4350-4364 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4366-4380 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":4350}}}],"partialFingerprints":{"codehealthFindingId/v1":"5302465450bd397a5305e36047d9697d16947557faeab8f807a7e0664ee4debb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteEventsManager.scala:248-264 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteEventsManager.scala:272-291 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteEventsManager.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ff5986359a5d13e19c6645bd6df78e53d0fa6de3474fe4e108f2f554c42d553"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java:534-540 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java:920-926 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":534}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4221ff03c2065d51932038087891a35f0dedd457032a5982954f55333f56ae6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 11\u002B corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:80-90 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:97-109 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:332-342 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:349-359 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5b9d6e52b3c873ef1063d60c45a409275d5fa116dcaa26a6e367926d367a64f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:238-248 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:304-314 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff5081cd3cf241f1bda99cde106e1e232ef096f3116ca4521da607e4b9315382"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): core/src/main/scala/org/apache/spark/SparkContext.scala:2589-2603 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousExecution.scala:475-489 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2589}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a36240f4d194aca5b3fbffa4582c86ff18680c8854f7ab00e4c42c47bb8116d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala:390-399 | core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala:401-412 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/memory/MemoryStore.scala"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f8f18a7d2fe17a55f5edb44ef58500ee9e0a8bbd0087c4805beba68b5c11f07"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1505-1513 | mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala:372-380 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1505}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1e594acafc8a35584e2e0b991daccee4973719e83ea57ca332be9d9971c46f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala:167-175 | mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala:268-279 | mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala:801-813 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ca0501f0ebff364342744c47ab64d50e6c329a18d9d8f7bcbadde90dd5d2ae8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/pandas/data_type_ops/base.py:531-542 | python/pyspark/pandas/data_type_ops/num_ops.py:280-287 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":531}}}],"partialFingerprints":{"codehealthFindingId/v1":"95828aeec0208249c12532c3b7dadf9f98a065c3bb36d922ab3055c070808452"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/shuffle.py:616-623 | python/pyspark/shuffle.py:636-646 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":616}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b2476c2d70c8cecae89ca6eba5835f90fea5ad490e56f607678342563fcc1dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): python/pyspark/sql/classic/column.py:388-408 | python/pyspark/sql/connect/column.py:544-564 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d41979488fc9617c14cc40c7f0b8572577410600d24c5aebf9957844b06ca4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): python/pyspark/sql/streaming/readwriter.py:254-298 | python/pyspark/sql/connect/streaming/readwriter.py:110-128 \u2014 These two members are one piece of code written twice and then edited apart: 19 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"1040273d0d7ad137640f6e5acc7d3a9a1b5597ab32a4d09c74626b689ae8a187"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala:633-642 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala:659-666 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala"},"region":{"startLine":633}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb90beba8385365880c072481928416fb05deef919d58fb9a859791ed4a60487"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParserUtils.scala:69-78 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParserUtils.scala:88-98 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParserUtils.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"9127db0aaeb5ec1b42426ac05bc56a78b9091dd70f1fdd8f17906960b3c0d1ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:928-935 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java:941-948 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":928}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e7a8a51b3a71d49e5c526fb84e20d6738bb707a47cc9c0d860baa0ad21e4104"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:202-209 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:180-187 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"d43f7952d043d74f6a626f48b2149239a6d833d80a2d470fe7f9d620dcc9ebf3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala:45-54 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:41-49 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fb33d378303f7f747b7c6ced45b9f6202939281bf4f318e88821ec3f1594cfc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcScanBuilder.scala:77-94 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetScanBuilder.scala:97-114 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcScanBuilder.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"d80f536472fc7d9dd74d433d9d8f8219e017b907c09b8b28c88de37714b171bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala:85-92 | sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala:94-101 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:152-160 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"e46eb2321a1fe46fcf12bbbb00ca79c9bed667a1061e5364e80eb4a2926296bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/resource/ExecutorResourceRequest.scala:60-69 | core/src/main/scala/org/apache/spark/resource/ResourceUtils.scala:88-97 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ExecutorResourceRequest.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"eac0de7c9f485486156cc7af3acd591e4fac8c4d930dd33ef16d7d1af85907ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala:39-55 | mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala:37-50 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b6b633826a1de9e3b89039793b7798a8a91a7f3ebcdd19330870cef85b5a134"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): python/pyspark/ml/classification.py:1706-1719 | python/pyspark/ml/regression.py:1047-1059 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":1706}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4e451141b1cc2280c8f808d12a8285c7705650198191feec65ce5c64353ca2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/pandas/data_type_ops/binary_ops.py:87-98 | python/pyspark/pandas/data_type_ops/num_ops.py:73-80 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/binary_ops.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dc51e44ccd3bfc246e5ef2f88a9dcaffff7cd63a4a1b540868ceb6f06adaa85"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/pandas/frame.py:14508-14518 | python/pyspark/pandas/series.py:7604-7613 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14508}}}],"partialFingerprints":{"codehealthFindingId/v1":"b71e0add2bc2a23cf7a366c09ea655745523e95dbf868021e5c7a0e921af73f1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:5831-5841 | python/pyspark/sql/functions/builtin.py:34279-34455 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5831}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a4c32cd63931a542af284d19e6853438c66aa063cadcd35525a89559d904919"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingWrite.scala:53-65 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonWrite.scala:68-80 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingWrite.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"eda886429a07a2de7219903e4668469d0d0f149f48fa82715fc1cbee5f7b4830"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/ContinuousMemoryStream.scala:91-102 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala:136-153 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala:155-173 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 12 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/ContinuousMemoryStream.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4a8dd27b8cfac1d2659ffdaf2417c3df9ed7620e8dc02acee430886535551e4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 6\u002B corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:152-157 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:163-169 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:185-190 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:208-214 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:191-196 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:204-209 \u2014 These 6 members are one piece of code written 6 times and then edited apart: every two of them correspond over at least 6 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2701af337650686ae645fcfc41353f0f42d4236b2ebe0cfe00eba41ade94e73"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): python/pyspark/ml/base.py:235-260 | python/pyspark/ml/connect/base.py:82-113 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/base.py"},"region":{"startLine":235}}}],"partialFingerprints":{"codehealthFindingId/v1":"63bda53690473f570403ddb6d30428077b7201f7e33e4c0db38b2afec6f341b8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): python/pyspark/ml/classification.py:3836-3842 | python/pyspark/ml/tuning.py:527-536 | python/pyspark/ml/tuning.py:1196-1205 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":3836}}}],"partialFingerprints":{"codehealthFindingId/v1":"89e84ebeabc3ec0dafb006c99f32b00ae6648be55535631724b6bf6aeb13f8af"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/pandas/data_type_ops/num_ops.py:168-177 | python/pyspark/pandas/data_type_ops/num_ops.py:239-248 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc177362dcfe2c3f1a207d7d289c89df8e3f77994e7632529d4e1c1da58bc245"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrors.scala:256-266 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:81-91 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrors.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"187979fde2fd5b01655b3b4ce4d09ddcaa8e9bcbd2fbfb92c856ef6b59aec066"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 11\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/errors/ExecutionErrors.scala:112-122 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:110-120 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:125-135 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 11 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/ExecutionErrors.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bb48ef4cd5e4b460bd9fba4a6ce6780c7f28abb064e804990f92e091cf63cf1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala:236-250 | sql/api/src/main/scala/org/apache/spark/sql/types/GeometryType.scala:214-228 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala"},"region":{"startLine":236}}}],"partialFingerprints":{"codehealthFindingId/v1":"14995c5c70028544fae27554d159d4a825d462328b9188681bd4b65d7290e3bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:138-144 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geometry.java:138-144 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3b85063d9156b16d7063414b0e9091f203a33e49e7b77b51542548f1ca5902a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/SortResolver.scala:431-444 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/AggregateResolver.scala:265-278 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/SortResolver.scala"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"518400c4f4ae500616d14acdcc1b5faf811d47a883f9a48edede9e92b9c3be18"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala:165-176 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala:178-188 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d916251576049d13e156c05c21c43e931a7e5eca03ccd21e6271e2e9b9b3121"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala:1145-1156 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowCreateTableExec.scala:97-106 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1145}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6e8c71d60d19ac5b94e347231e01e4b237a69e4b34f352249765b8c9c932db3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:442-447 | core/src/main/scala/org/apache/spark/rdd/RDD.scala:1486-1490 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":442}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b95273add73e05b49eb8907c9324f171d4fa2a7e0724d59c649ad88360d0fa4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): core/src/main/scala/org/apache/spark/storage/BlockInfoManager.scala:352-364 | core/src/main/scala/org/apache/spark/storage/BlockInfoManager.scala:380-392 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockInfoManager.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"87695f737ddc605deb917045d19a8990b58cae24789d6c6651b68771c02f5482"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): core/src/main/scala/org/apache/spark/util/collection/Utils.scala:74-82 | core/src/main/scala/org/apache/spark/util/collection/Utils.scala:87-95 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/Utils.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"40fa9324fa07171e30cceac3545b6ac8720638755cc15e61f8287207e0206cb5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 9\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:400-408 | mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:539-548 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:565-574 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:418-427 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:366-375 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"52f9132d9fb78a63da49ed02a7a4bd51cec869ef8d099f5b54fdcdf82a59d742"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:872-883 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:552-559 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala"},"region":{"startLine":872}}}],"partialFingerprints":{"codehealthFindingId/v1":"dba1aafe94a3b30064a67b011fcd7e251b8a5e1115be84aeaa8e0942db8367be"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1592-1605 | mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:204-215 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala"},"region":{"startLine":1592}}}],"partialFingerprints":{"codehealthFindingId/v1":"764965d826a7ebc2d837b65f8c1306199f1c9e1e241d7816e09451516cf321bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 14\u002B corresponding lines): python/pyspark/resource/profile.py:145-159 | python/pyspark/resource/profile.py:277-290 | python/pyspark/resource/requests.py:543-556 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/resource/profile.py"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc755cd6c834cd0cc61da7f7b5ad2c68302af7032403aee6f6f08446608d0d45"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1326-1337 | python/pyspark/sql/functions/partitioning.py:180-229 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1326}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3565cd665e74e1695151d633ae2d8c32a8457fd5ce3becebcb609cb8f3c6d49"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): python/pyspark/sql/connect/streaming/readwriter.py:546-552 | python/pyspark/sql/streaming/readwriter.py:1039-1081 | python/pyspark/sql/streaming/readwriter.py:1311-1344 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"91a0e329df4fe7e0b345f95c71e472bf4d15244336179e29921cedf003f0f77c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 10\u002B corresponding lines): sql/api/src/main/java/org/apache/spark/sql/types/Geography.java:65-74 | sql/api/src/main/java/org/apache/spark/sql/types/Geometry.java:65-74 | sql/catalyst/src/main/java/org/apache/spark/sql/util/CaseInsensitiveStringMap.java:190-199 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/java/org/apache/spark/sql/types/Geography.java"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"70b86c600f74f0f6e541c4588414764ca3bdd21fedd5c9a22c14dbb803234c2d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:246-256 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18176-18185 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"dec27f2d5c18e51b1f849ad08a7e6ca633ecc7847c3c786c3aae1e690c0c91fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:731-743 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1613-1625 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":731}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6620157bae19fa045ee693586b22b7b895fd54034ea77a2a8150428ee383c25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PandasAggregate.scala:28-34 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:615-621 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PandasAggregate.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"eef5bddecb0baad69aa508dbee27b49cab4a41826e44c2da52bc89814129fbc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala:579-584 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala:1002-1007 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":579}}}],"partialFingerprints":{"codehealthFindingId/v1":"030af5556b13761d10e1ba035549d64587c6a125e7d19c0689afd050896d5954"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:188-196 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:164-172 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2994be6a20d84c1c6fee8d827aa333a5b264ffc3934f16e6b4bb4c9bdc18c1c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala:686-697 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala:725-736 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala"},"region":{"startLine":686}}}],"partialFingerprints":{"codehealthFindingId/v1":"329ca432a38f894576120c15723612cacbdbe0765b0a25cc8021c8fb26cb8a80"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 15\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:152-167 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:181-195 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:209-223 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:238-253 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:268-283 \u2014 These 5 members are one piece of code written 5 times and then edited apart: every two of them correspond over at least 15 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"54479c7bbc569e3338c5772e5cc535b7ed1528c42096da18c2f9a1f915f1d5cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/connect/dataframe.py:609-626 | python/pyspark/sql/connect/dataframe.py:1657-1671 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"9944a9ae68e47d4151e708f453b4ca73913139b5938de87fae2609fb0905fa03"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala:144-155 | sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala:356-366 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"96d3a0d15db7efae626af6f5317e1d0e751c0163de9cb0e722cd5e470cbc97e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/protocol/EncryptedMessageWithHeader.java:62-71 | common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java:74-82 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/EncryptedMessageWithHeader.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"a21f16c9210f3ab1c25a7942a43bbf0731a62a821a81c5b0721be6bd2ae65ce2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/java/org/apache/spark/util/BestEffortLazyVal.java:63-76 | core/src/main/java/org/apache/spark/util/TransientBestEffortLazyVal.java:69-78 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/BestEffortLazyVal.java"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1e578deaab31373dfb28478e3b7b9d3139dfeb726fd3618970b5344e938b961"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): python/pyspark/pandas/frame.py:7418-7451 | python/pyspark/pandas/indexes/multi.py:365-390 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7418}}}],"partialFingerprints":{"codehealthFindingId/v1":"162c36286bbcb10d6806b039cf99d7c7283cab15324cd2316aa3f32076adddf5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/classic/column.py:424-432 | python/pyspark/sql/connect/column.py:606-614 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":424}}}],"partialFingerprints":{"codehealthFindingId/v1":"f712a1f2ebd67be8c2602e0ac58e89573ee19eefcd101562384ddb81a5cc5462"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 14\u002B corresponding lines): python/pyspark/sql/connect/functions/builtin.py:5806-5819 | python/pyspark/sql/connect/functions/partitioning.py:34-48 | python/pyspark/sql/functions/builtin.py:29916-30012 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 14 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5806}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2ce88872faece07f8181d5500a5af402b6e40e67b16ed6c817232330083f89a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:135-138 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:180-183 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"f93c317f0726644a0ad258065abbfb6f6579ee42f05c35dc4e7d08c5ec2abdc8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java:79-90 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:76-86 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"90fc244c8901329c79223b4b8e94164cdbabf1959eb1064701d8862bcd9ca2bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java:66-74 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java:66-74 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8f70011d632d0499335c01ce475fba09c6516cd0a5e41ccd2ff71b08ed31f61"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:125-128 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:171-174 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a38e5cbeee4588d4bba54ac921d6f7294294866675b262365e22fd0083f1440"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:294-300 | mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:424-430 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc55df1e9d530ac6003e629d963084be286dc8d65aec5a1a1f5fc772ba91ea8f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala:381-386 | mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala:498-503 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e7ff3b2f789e40a0657e94583fb55f0664ea4226ffe0a583569bc55ce196045"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): python/pyspark/mllib/stat/_statistics.py:313-379 | python/pyspark/mllib/clustering.py:1197-1212 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/stat/_statistics.py"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bb8050c51f1cac663f783f687915d9e99ab9a37e1b899085d0ffb680ec94ab6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:97-105 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/StatefulSetPodsAllocator.scala:86-94 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a2f55ecea2cbd833037ff163ea036c396d5a3ba4d68f3dee5721fb346186945"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SourceProgressSerializer.scala:41-50 | sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/StateOperatorProgressSerializer.scala:47-56 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SourceProgressSerializer.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff1a12d68828f6736157b40a80c255e71db8ed31c338d804d7d5e46c3917a2da"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDD.scala:101-106 | streaming/src/main/scala/org/apache/spark/streaming/rdd/WriteAheadLogBackedBlockRDD.scala:103-109 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDD.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"ada0502952579797497242c8a89ecb885f5715433ba0eabd1211de8cf4b76b58"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfCollatedStringsSerDe.java:59-65 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java:483-489 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfCollatedStringsSerDe.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"b80a0aa017fc64dec48b1621fb05e0a0293cae380a30d263aef9fad4bf4b0129"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/VariableManager.scala:126-135 | sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingLocalVariableManager.scala:38-49 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/VariableManager.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d2e9bceeaf4d93300e1b349c11e43603b2346917a67fd993e30a4c279b8d790"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowCreateTableExec.scala:80-87 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala:1311-1317 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowCreateTableExec.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"f311d2ea135f1c56871715ac64c02523d5637d883d049811970a4baffe2f438d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala:79-87 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:174-182 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"8faa2248bac0ca9311b322e8d382329fdbf0ac50a4b6d3fdb9738d70ccccecba"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/MapStateImplWithTTL.scala:185-195 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/ValueStateImplWithTTL.scala:121-131 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/MapStateImplWithTTL.scala"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab3f756e7536f81ac36df96dc65885956d7b8246c4c915f5c9f73a085f59b400"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:412-429 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:1398-1415 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":412}}}],"partialFingerprints":{"codehealthFindingId/v1":"e00edf500febc561beb5a753bd6faf569a96c4d81735db07f59ce3ffc2384d74"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala:102-110 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala:627-634 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"d08ea29405cc2f7b90f629246689cfda4f17d77de3d60606fda0932c1c88d34a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java:93-103 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlocks.java:105-115 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"88c9f85adeb96861f3befce61f4f850e8dc7f4fe8b522dbc4db4deed4d9dac86"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/FetchedDataPool.scala:62-71 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/producer/InternalKafkaProducerPool.scala:57-67 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/FetchedDataPool.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"53e120ff75a64215917f7ae4e1363c2c47c35861a46f0f76458a8cd92b5f7597"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): core/src/main/scala/org/apache/spark/deploy/history/BasicEventFilterBuilder.scala:61-65 | sql/core/src/main/scala/org/apache/spark/sql/execution/history/SQLEventFilterBuilder.scala:68-74 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/BasicEventFilterBuilder.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"f53c35b19b915c35410674a694fe810f8d0a5ca105c289b652ad16a252c55a6e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:303-309 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:322-328 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab68bdc2d5e041ab018b0b7e2f203f35971d106347ca8f02dbf199aa92bf1ff8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:3039-3053 | python/pyspark/sql/functions/builtin.py:17944-18027 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":3039}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f8c6f0557116c5311aa80bf8a57e88a8c69e088c9ce4896aa3cb87eeecdd828"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 8\u002B corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/GeometryCollection.java:51-58 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/LineString.java:51-58 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/Polygon.java:59-66 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/Ring.java:64-73 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/geo/GeometryCollection.java"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"b017a3a00d7102488d11ae0246a49c291d9939baf4ed42e48df53393df322469"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala:106-121 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/RowBasedHashMapGenerator.scala:103-118 \u2014 These two members are one piece of code written twice and then edited apart: 16 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"6bc12982bf3d2575ffd71eb81505070ff4ff1cdbf5a356cd68b45beb469f1dce"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCrossReferenceOperation.java:108-117 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetColumnsOperation.java:123-130 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCrossReferenceOperation.java"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"db203248c07b8305196ccc8bf04c8d3c16e2f819021ada91c87af3564f5f05d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/pandas/data_type_ops/binary_ops.py:59-68 | python/pyspark/pandas/data_type_ops/string_ops.py:86-95 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/binary_ops.py"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"e06ebd54a1c3ee3e855fa80b791c2a0f64a9d18060554a7e1cf3dea19c0c894d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala:150-156 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:324-332 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"e629bb0b3f3a9ae023225251aef62678d0df26168b3c9cc5f049455d59bfeccf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala:76-82 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala:169-174 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"cea6cdfd172305c98b8689ecee79ebc55710550a4a2cd44164d302130d7cbdfd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala:509-515 | mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala:342-347 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala"},"region":{"startLine":509}}}],"partialFingerprints":{"codehealthFindingId/v1":"aed799dcc53b6361547003a5418c39c810b874a44b6fcde5867241d545328dd5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): python/pyspark/sql/connect/table_arg.py:41-43 | python/pyspark/sql/connect/window.py:36-38 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/table_arg.py"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"53283918c176ba24692222956073645bde9035661a776ae22d68751b893982d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala:180-187 | sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala:749-756 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c95822d4f9d1a1961b480b0ea5fb59b34deb0314e9a95e3eaf96b0b28e18d98"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): core/src/main/scala/org/apache/spark/rdd/RDD.scala:1027-1034 | core/src/main/scala/org/apache/spark/rdd/RDDBarrier.scala:69-77 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":1027}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc65c97f79e9dcb020ec3c75de40aeda9427471bab6b9d2670e01f1aa8ffefc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/core/rdd.py:4681-4711 | python/pyspark/sql/classic/dataframe.py:578-586 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":4681}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea487be00feb351f1492bce1c242bac67cf47271aca51401d4adc2233fa8ef5e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1625-1630 | python/pyspark/sql/functions/builtin.py:9572-9614 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1625}}}],"partialFingerprints":{"codehealthFindingId/v1":"5004d1262c8f8c15287747aa5c4aa2229d7abfbe331a007106cbc2db4a0bd5d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1637-1642 | python/pyspark/sql/functions/builtin.py:9619-9670 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1637}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f347365f5c38d66d81e5b9063789f7df452d01a6b4ae9e52616ffb53d73b426"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1649-1654 | python/pyspark/sql/functions/builtin.py:9675-9726 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1649}}}],"partialFingerprints":{"codehealthFindingId/v1":"7fc2a1ac9c67f23884e1a97c0e7637a69bf40b03b4043e33d3669304f4c693e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4522-4529 | python/pyspark/sql/functions/builtin.py:28882-28981 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4522}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc6e4ec08bd770debe33b0aa6cdc2c4fd401cbbd0b3996c816cb30624291e5bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4544-4551 | python/pyspark/sql/functions/builtin.py:28994-29106 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4544}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0f79f07073283eb209479be25a22fe1db038e0ac78c742a2bc2a162eb6decbe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4967-4971 | python/pyspark/sql/functions/builtin.py:30498-30544 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4967}}}],"partialFingerprints":{"codehealthFindingId/v1":"540e7b69f7594feb36742c2a2a90585a561ff106b64419cce975f653d664a205"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4982-4986 | python/pyspark/sql/functions/builtin.py:30553-30599 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4982}}}],"partialFingerprints":{"codehealthFindingId/v1":"e16c8ab087cf1b40084e1a17cef65e0c76e0d49c9638b42a181f00227a81b91c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:227-236 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18156-18164 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"23a31ec5e0eeedf4424fe9c43f9b518cb33f2bbcce00e63544f6ed4b805d537a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:127-130 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:175-178 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"51217363cd18cf3fa5094351a0e11f51a97dcfc8dd8bfec8f1a971928d89a619"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala:191-199 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleUnion.scala:223-231 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"f609355601283d1114b3a54d353b776a33b72118157ef2d300b595ac85ec03a5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala:252-260 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleUnion.scala:293-301 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5e4306bb2e242499d643f3dfe07b5d51369004fbc4f0cccaa7aef5fa308e12f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:2009-2018 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingErrors.scala:79-89 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":2009}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ffcff469bed4a9afe2f6882eafed3f86a3df34adaeada390b91243383060246"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala:138-147 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala:91-100 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"7aa570f26294670516fdb41288ce37e2b686f7718465ef8b657ff6ff115086df"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:116-119 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaDStreamLike.scala:162-165 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"34d17b7ebbbd0e4bb7298d2190888fbbd7adb484e3c35cd3fc407d60b668802f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala:189-197 | sql/api/src/main/scala/org/apache/spark/sql/types/GeometryType.scala:181-189 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/GeographyType.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3302bf7ab11438a9d071f4e1c584d720e83ab887cb1edb5eec8ee72c8b1412e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala:171-178 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:3387-3397 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/timeExpressions.scala:212-219 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"8df1da97d1a05024dadf7475bf3d09735c9c1b15ee5ff882245941a31f272f1e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala:74-84 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:99-110 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"936a3d2775033619038653eade69eb5d12f78868aec3ddf76cf7dc593523e500"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:385-390 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanHelper.scala:116-121 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":385}}}],"partialFingerprints":{"codehealthFindingId/v1":"341797608301298a0366537d8f32652eafa78472a9134cbc10e550144978cb6d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:312-318 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala:248-253 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"895026c818db9eb522a3c34280886d276517cee8246b6f4253a5737e227e777f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:872-878 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/streamingLimits.scala:53-58 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":872}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2e98dfcd8768a5e119da94c44ac53d87f65e9b0171e049ff6d25299c156f581"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:420-426 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaRDD.scala:145-150 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"4adc00be7f2bee8c4fba7e29cae1f0763c51ee55caeabd015f682b2722820bcd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4763-4773 | python/pyspark/sql/functions/builtin.py:15536-15578 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4763}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa8d44f0a146ce1e480c1c7213031700a5c97a08d8d834f32bcb59c23d907e25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 6\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/columnNodes.scala:81-86 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala:367-372 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanHelper.scala:83-88 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 6 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/columnNodes.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb9eabec30ad69d7f2b2177529370a0dec2912d404cfbaefe1169d7becb0c7bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:169-174 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geometry.java:172-177 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bde1a63cc294180c72117601a306c96fb42ce3286f5350cbd6cb5821382057d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSchemaEvolution.scala:92-101 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AlterTableExec.scala:39-48 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSchemaEvolution.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ed57aa1da8d5e5eb5d1d9a32c3009591f8b307d46fc6b92b99b04068397a7a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala:297-306 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:261-267 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala"},"region":{"startLine":297}}}],"partialFingerprints":{"codehealthFindingId/v1":"b371f40addbe7cf06925b62620ae427a9f012575e485abb7ff257317b758796e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala:76-83 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:162-170 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1a5368fa55d2c1efcea287828d9b2823624f67a62fef6c10f51aefa7d020c67"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java:106-113 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnVector.java:184-190 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"807e9d6309be2b43143ebc314f9980ad798fb15cf2d901d8341ef543a71b4828"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/core/rdd.py:622-661 | python/pyspark/streaming/dstream.py:121-129 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"68ff72d98235a14a2a87636a84be0a03114ddd3b9d037d4e3f2aba9ccab096aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/sql/connect/readwriter.py:829-838 | python/pyspark/sql/readwriter.py:1982-2041 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":829}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5b17a4ae0223016487f0b1a62c22ea9faa4bfea586b1856a39e48eaef0ac233"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:194-205 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/StatefulSetPodsAllocator.scala:203-215 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"9792802f3d96c7b05c3782f57ddb6300400f7ab6fddeae11605cc0c16805b738"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:251-255 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:491-498 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"3eff871769cb872d499277e32976b31938d4e12e6d8bcfbee7afb250f3ec94b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:258-262 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:501-508 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a80beb62ecec9896b88ad959528b875aab2bf4dba486c377c2df8e18452af6b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeColumnCommand.scala:139-147 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala:370-378 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeColumnCommand.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f34efab9f32ef7f3ee9d32ecdbc3cb47d827334205e5e5296565acf5cbf54ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala:168-178 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVTable.scala:61-69 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"de6a93333a7648f8418b370ea2f79c332cd1a13669154c5f19dcafb83fc6f03e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonUtils.scala:58-66 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlUtils.scala:57-65 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonUtils.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"387e3b6b4259f14f9bc6de222e200fdfe3bcf10f17e61fc6c5424b5d19c3590d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/ClassicTableTypeMapping.java:91-97 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/HiveTableTypeMapping.java:43-49 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/ClassicTableTypeMapping.java"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8e2c1412c0fd21da04ee029b35cb3bdce30428ada56f55a729408bfb8f6baa7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:325-333 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:357-365 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5bbfa6bca5d29077edf503c3f497a549b2aa0c4f8a5d22c04e6df57a209fbc9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala:526-531 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala:750-756 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala"},"region":{"startLine":526}}}],"partialFingerprints":{"codehealthFindingId/v1":"1df7a8f8b2b43e1fd2525a46b50c77013d9abdd89c3cb8cd49a6a437e35e21c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala:652-657 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala:734-740 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala"},"region":{"startLine":652}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ce4397e27ea55594a02b9f6ebae5ef409bd4ec597966fa88cc278ded659a152"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1708-1712 | python/pyspark/sql/functions/builtin.py:26915-26984 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1708}}}],"partialFingerprints":{"codehealthFindingId/v1":"de5cb09fb8451f244876adb13f803a8edee01f7a0dd322b2520c7e6495ea1f34"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1724-1728 | python/pyspark/sql/functions/builtin.py:26994-27060 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1724}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b3bb16723142998e5c8a8397cb283872fe2baad45f3bd72fffc38b8424eba9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:4829-4837 | python/pyspark/sql/functions/builtin.py:15296-15348 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4829}}}],"partialFingerprints":{"codehealthFindingId/v1":"facaa84974ff042314d2682460a6db0834485d6742201cb98cab56d769aaf170"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala:156-163 | sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala:738-745 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"03086e60a7efd0fe9fbe79d5f983124dcf57257f0dc0bde5350022716623db5f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala:67-75 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:77-87 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3d8afb4a79c62ca9240ffc0567599a504770d39a04c2da91fa4538edef22f8d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:563-567 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:500-504 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":563}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae11382cf0196a7de52cdbbe44dff0c30e964fa7984c8eaf9ab451ae92b129fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:577-581 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:514-518 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":577}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae4ad641dd2e145a8cf55407eb44c4cf14b4593ce6759ed811347309b832e8c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/Transformer.scala:117-122 | mllib/src/main/scala/org/apache/spark/ml/feature/LSH.scala:104-108 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/Transformer.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"2453084ddfcd020e7dda850614bdb8dcb0631343b4d122c3865775b5fd52ccc8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/attribute/AttributeGroup.scala:175-181 | mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:545-551 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/attribute/AttributeGroup.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ad507b6f779d0f30af6c3850892f65a6af3be5d0a54be18dc535960c0951fdb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/errors/exceptions/connect.py:397-408 | python/pyspark/sql/connect/client/retries.py:358-367 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/connect.py"},"region":{"startLine":397}}}],"partialFingerprints":{"codehealthFindingId/v1":"641288a2e42815cfddd5530903d3b073e5eeb71a8b8136d19c4ecf67e93a4d6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/ml/linalg/__init__.py:1356-1365 | python/pyspark/mllib/linalg/__init__.py:1626-1637 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1356}}}],"partialFingerprints":{"codehealthFindingId/v1":"f962f75511f2592a996f38a82e4bb83e7aeb6267062660f69444073a3bbfe2f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:155-162 | python/pyspark/sql/functions/builtin.py:159-170 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9144f45086e271f6bfc3f6e30a11e122bb41de47ee49b6d304f4beb26134cea"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (2 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1348-1349 | python/pyspark/sql/functions/builtin.py:8030-8081 \u2014 These two members are one piece of code written twice and then edited apart: 2 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1348}}}],"partialFingerprints":{"codehealthFindingId/v1":"e34bc4c3d52e4db51df4d5fa5f38c6b45fef269303232310e5126f1a139b1ae6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (2 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:1360-1361 | python/pyspark/sql/functions/builtin.py:8090-8152 \u2014 These two members are one piece of code written twice and then edited apart: 2 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":1360}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bc867696a7f71882430571b6b761c062ec5f9c2968605842f2773f7686c1923"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/UserDefinedScalarFunc.java:62-67 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/UserDefinedAggregateFunc.java:70-76 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/UserDefinedScalarFunc.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"d09c7ca42a34682c2e69a269ce8d4da5ac1122846dc52f1c36937e6a2e047d2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala:143-148 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala:176-181 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbe5a8083f6bc837375dc19f44eaad6a30bccf7347ff7b7db2c4f3cf3e654590"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala:91-99 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3756-3764 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fc089c4c27da5db99744c27350e4110bbdc76bf72732950d2e2429f7845b7df"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala:195-200 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala:212-218 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e41a6b4c68745cdcf4ee3479a8734a35a1cd171b671c34f390ae7f64a16fb71"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVUtils.scala:115-123 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonUtils.scala:33-41 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlUtils.scala:34-42 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVUtils.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"54dc01b5e3b275368e75e6b5a113bdd428551cde1a924bbedaddd8abefd75c7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVUtils.scala:128-136 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonUtils.scala:48-56 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlUtils.scala:47-55 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVUtils.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"55d88a1e5c470e9dc6e6144397184af38210e560ed4ec92f5c453e67570dfd4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/types/ops/TimeTypeParquetOps.scala:213-219 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/types/ops/TimestampNanosParquetOps.scala:262-267 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/types/ops/TimeTypeParquetOps.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dfb82bbe399d7e268220169a9469308c2da72530dfd360367e1be12939d3edd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStatePartitionReader.scala:234-240 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/utils/SchemaUtil.scala:91-97 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStatePartitionReader.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"837fb851366455fadefaa4ec967f3faabc2a3e17e56fb0674efc4ed59332fc32"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala:636-641 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala:718-724 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala"},"region":{"startLine":636}}}],"partialFingerprints":{"codehealthFindingId/v1":"ade2731ff917e1c3a1d810ea6e3f3d722e53783718b75201cb808b7a22562bc7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/Predictor.scala:176-182 | mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala:296-302 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/Predictor.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"60a91c76c6dbf1dc2d244b0c9ccd48d2113676e043466c460cbc571213be489a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/ml/linalg/__init__.py:1054-1057 | python/pyspark/mllib/linalg/__init__.py:1237-1240 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1054}}}],"partialFingerprints":{"codehealthFindingId/v1":"1db31ef8604a14619f69959090cd8dc01822a3a1607803826757e3e329e78501"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:5741-5745 | python/pyspark/sql/functions/builtin.py:29564-29610 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5741}}}],"partialFingerprints":{"codehealthFindingId/v1":"97980e22824c32eedceae12e21266afaf9b06c9efc7aa7c3a30b28ce1d9df4b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/DataFrameReader.scala:183-190 | sql/api/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala:340-349 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameReader.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e77a2d04d5968ec50675aceb8362894a4df5f68627019e67b67df7aede120a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:120-122 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:171-173 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"0036fbabfd5e8c92305961c960d6b58fb37aae9a964f10d210c07d6ea1f4a22e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java:86-93 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDeleteV2.java:95-102 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"499b0d2bf8cb1a0772012137e01570aa1651a63e4286fc60e3cf7eee4645505d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala:67-77 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3732-3740 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"51267671a461e6b46f3bb43865229e89f76cd0217d1923e763dca1c3b440365d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala:79-89 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3744-3752 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"34d14f6bfbb55d2f7df9ad58612a33347507dc6d30a2657c27869f9e05d3c522"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:2590-2598 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1992-2005 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":2590}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8aacc4aa9c71ab6ec4dc22c7fdc86d4a068956ea27c8303f2fb947c228be723"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:1224-1232 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:1797-1805 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":1224}}}],"partialFingerprints":{"codehealthFindingId/v1":"29f89409abf91fc2f444f7339221ad20dd8a13bfc6bf3f0a972a91d532c668e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): core/src/main/scala/org/apache/spark/MapOutputTracker.scala:660-668 | core/src/main/scala/org/apache/spark/StreamingShuffleOutputTracker.scala:158-166 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"76fb31f0c083e7ebd7d6ae7aa2e68163fc6232cd82066577c003e5f3860ca3d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 4\u002B corresponding lines): core/src/main/scala/org/apache/spark/ui/scope/RDDOperationGraph.scala:110-113 | mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala:113-116 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala:239-242 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 4 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/scope/RDDOperationGraph.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"95cc045bb5e417ce08544a5fc188c5f35f36944f8aec5f0a57e4cd86bc68ba50"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:5853-5856 | python/pyspark/sql/functions/builtin.py:34465-34624 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5853}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0b1e65b933c5e1b1b1589a2b7dea45106d96567c4579f43f0a60a470f6814af"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): python/pyspark/sql/connect/readwriter.py:171-177 | python/pyspark/sql/connect/streaming/readwriter.py:464-470 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"f63a289ca471d819221bda645ac1d7087cf97958be07b31b945108891e13ee65"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/StorageFilterPlanning.scala:99-103 | sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:126-129 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/StorageFilterPlanning.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"5137c528d12cd58ebe3e3e65af6745260f4b21aa15e4a68ab473b68eb06a71e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/protocol/ChunkFetchSuccess.java:62-67 | common/network-common/src/main/java/org/apache/spark/network/protocol/MergedBlockMetaSuccess.java:78-84 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/ChunkFetchSuccess.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"b719150e4cf7e8c3922857ff146dd0cf84ed1eb3c7ae26cebe4818e3b2541f16"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:116-119 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:110-113 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"43b23190824070c1eaeb816976713435ff6ee816e00051cfef21a2933fa64f40"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/ProtobufOptions.scala:271-276 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala:218-224 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/ProtobufOptions.scala"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"f49d5ced057ae3039a3235f0895b66d1a5fa4fc7390b4c5a052688924ef60d15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala:1129-1133 | streaming/src/main/scala/org/apache/spark/streaming/StreamingSource.scala:40-44 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":1129}}}],"partialFingerprints":{"codehealthFindingId/v1":"f25bc84c3631d7a6a69abec8d1f05999e2e8b8c5f677a60de3f8a259e177b69f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1364-1373 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:500-509 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1364}}}],"partialFingerprints":{"codehealthFindingId/v1":"379600f7c583ce04519bf93e417cc30f20f78c9076d0972fb6e24d824640277d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:182-194 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:216-230 \u2014 These two members are one piece of code written twice and then edited apart: 13 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"30a319f722375d16bed10097119e85a6b3b24ecc005335ec00c7091678589a85"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:295-300 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:314-319 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fb4876cc57503085a99b55886e5b165eaed630796fd72a9e5fc664544b82bfc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala:333-337 | mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala:155-159 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b497f16c7dfce6d25af2d5976f45e2d349ac5e39d1a25ab9b662fb2bc2256e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala:230-234 | mllib/src/main/scala/org/apache/spark/mllib/tree/RandomForest.scala:193-197 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ec206023d5896d8897c21abb87c2bce7355aae0f9ec53de9adcfa1121732650"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/session.py:405-413 | python/pyspark/sql/session.py:804-823 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"4abc55e1fd7f3017a68a10ffe6fb71f1db90245547186184f139916aea3ea368"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:209-217 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18137-18144 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":209}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b69efc5340c5cac772f2de396ba5d48e83c273e51c21ec8975ec8a3f6a97c83"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/StagingTableCatalog.java:116-119 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableCatalog.java:392-395 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/StagingTableCatalog.java"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"d27f7dc4dfdd99fe86b0402af42aad47c5c06fab6acd1aef50927c207209086e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala:221-227 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:2415-2421 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"a52d94f3acfed20a38da17252fcc1c6de86605375778dd457352f0671390cc5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:109-117 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/urlExpressions.scala:247-255 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"878ad2fa179c96e60669e2bef4b9f9c4ea6039d6d482f5e9ecb72c096d907acc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameReader.scala:200-208 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataStreamReader.scala:118-127 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameReader.scala"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"14fcfd02a24e61a0f9a0aebf7484b33c24b9f5745c5acb12e2d839966f6f306b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/classic/DataStreamReader.scala:94-100 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataStreamWriter.scala:134-140 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataStreamReader.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fe5546b0af6eea0360c88a1b996d0c2ee1ba135a2d72bfb6586b06985a72966"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:433-436 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:435-438 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":433}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8183c650dafbb008ebda78f51ff35ea8bc7c0aa1fed8c0a841f8c4014563011"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java:75-79 | common/network-common/src/main/java/org/apache/spark/network/server/TransportChannelHandler.java:89-95 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"5102808c24354abef03baae9d1e8e726456e37e95a20f121822adbdb89954506"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 2\u002B corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaHadoopRDD.scala:39-42 | core/src/main/scala/org/apache/spark/api/java/JavaNewHadoopRDD.scala:39-42 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:103-104 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 2 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaHadoopRDD.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b0f1a3ddd5c1dfb6aaf81adf290e82a2b7a98206387e2722a3e9900c91b4461"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala:104-109 | core/src/main/scala/org/apache/spark/rdd/SortedMergeCoalescedRDD.scala:78-83 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbc70a698a418e423e0317bede9c5fd38e413e68ea4bd6a08e4035243fc91240"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:126-138 | core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala:94-103 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"6746fb9c414666d312efdb0f94123cb5c82ce2318298b76f248e0fcfc66b3c23"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:533-537 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:470-474 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":533}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea6ba389c05d3a63aaa089141c162649a3659f1e39b388e3d7d41ecaea51f235"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:968-970 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:829-831 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":968}}}],"partialFingerprints":{"codehealthFindingId/v1":"d527c6d5fd3a64211b08f9601a624387e74b3ff3846ac54b0f07bbb543971882"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (8 members, 8\u002B corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala:88-95 | mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:169-176 | mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala:145-152 | mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala:231-238 | mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala:171-178 | mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala:270-277 | mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:189-196 | mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala:368-375 \u2014 These 8 members are one piece of code written 8 times and then edited apart: every two of them correspond over at least 8 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 8 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"23cbcbcef7336a524d7fa8b4fe738b9673969533f7e24e5e588c6f1504a487cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/ml/classification.py:629-639 | python/pyspark/ml/regression.py:193-201 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":629}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e3c256bd5edb7afdc6d0261c65f1ba9f4536a24e663125dd4f52d9d31f1a24b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): python/pyspark/pandas/datetimes.py:41-45 | python/pyspark/pandas/strings.py:64-66 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/datetimes.py"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac6023b0a149c40906365a9444972dff01759dc5ea4d74c0f81309c73bbb45cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:8641-8645 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:4738-4742 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":8641}}}],"partialFingerprints":{"codehealthFindingId/v1":"81016f07412d5ba2d0ebb316a0312da3f9ec1746ff43addb81e58e528dcd534b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (2 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/ExternalLookupJoin.scala:380-382 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ExternalLookupJoinExec.scala:127-128 \u2014 These two members are one piece of code written twice and then edited apart: 2 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/ExternalLookupJoin.scala"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbafe36c57f24ce8834d9855b186fc570a343ec9961ba45880032a060e57e827"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimeTypeConnectOps.scala:58-63 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimestampNanosTypeConnectOps.scala:113-119 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimeTypeConnectOps.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"36d8e85d1aec2f30434a4248ea02e2914eb3b91466f0d6b9664311a0497972c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 6\u002B corresponding lines): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectExecutionManager.scala:290-301 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectSessionManager.scala:269-278 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamingQueryCache.scala:243-248 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 6 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectExecutionManager.scala"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"55237fd41984bd15b0b684fa38af3a6931a7506fbc558c5be03fb811d2dd27ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (7 members, 10\u002B corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:79-88 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:271-280 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala:571-580 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala:143-152 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala:134-143 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala:170-179 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:366-375 \u2014 These 7 members are one piece of code written 7 times and then edited apart: every two of them correspond over at least 10 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 7 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"9350235af70f367da9b5fd6446f792d29e4f25b844881c3766ef63a4663b4917"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): common/network-common/src/main/java/org/apache/spark/network/protocol/StreamFailure.java:50-54 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RegisterExecutor.java:85-90 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/StreamFailure.java"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a8b8dde78360081dec2b55124e8e28ca741fb4a9448846512af2c8c92dcf56a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:520-524 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:457-461 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"20efa163e7a28419b47ebe656f57d77bc22be68215b52fac0cd64a228612df00"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala:273-277 | mllib/src/main/scala/org/apache/spark/mllib/tree/RandomForest.scala:279-283 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"44a95cab15ccd18f45a9e6b5342e4b829ee09aea4c6e1292a031943c5a222f7f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/core/rdd.py:666-705 | python/pyspark/streaming/dstream.py:148-156 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":666}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5fe8d36595153599973ad9dc9e5b4805e48326f0b58e6ae37dddc79b0ecdacd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): python/pyspark/ml/connect/tuning.py:404-406 | python/pyspark/ml/tuning.py:831-833 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc0c5bd352a6578d945bd74f381832113bf6ff99d9be505bef160a77f62809e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/ml/linalg/__init__.py:144-147 | python/pyspark/mllib/linalg/__init__.py:155-158 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"466fee5a5cf8d9449f79f6a610d1e7bee41f916c2a24b5cefb33b3a5ae16b54e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:372-377 | python/pyspark/sql/functions/builtin.py:8874-8915 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"4004e5573a9802d8942ba3009374f823a04a761280ade6bbf700991cba52ffc0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:391-396 | python/pyspark/sql/functions/builtin.py:8920-8961 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"8495b9e89f8c3df44f73ebcf24cb6765de7b16265cf6564f3e0c1b3e3bdee30b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:815-817 | python/pyspark/sql/functions/builtin.py:6722-6771 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcc4adea8714b8946a67df20959594fc3e0996a0f54ea5a0014aaa735c726516"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/catalyst/analysis/alreadyExistException.scala:81-88 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/analysis/noSuchItemsExceptions.scala:122-130 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/analysis/alreadyExistException.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9ae88acaf955491223da197855d4941f045b7a46c9ecab96d6016635d914546"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 9\u002B corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala:1006-1014 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:266-274 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:3687-3696 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 9 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala"},"region":{"startLine":1006}}}],"partialFingerprints":{"codehealthFindingId/v1":"88d9f64caa580d0bd831fc15a177d5f836f2058b9edeff50f02d7b2f58e17a9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:532-537 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java:139-143 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":532}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ec37881d13ab5e4461e4efc1d1634882c530345feb839947f1b51d304cdcef1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:550-555 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java:155-159 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0696ec1dde582fecbc814c155782cba67afe135ea8e501cf85fb07f13dd2430"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:2011-2017 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:2074-2080 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":2011}}}],"partialFingerprints":{"codehealthFindingId/v1":"f84b8fdba429c1abd3f05e1628724378631252d84b1683bff59fbe0b9014f391"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala:228-244 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala:163-177 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"82502ceecf41c4c923c1f86a71c22f28d5c70d44a054cde5840e2581ac13d854"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:135-138 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:168-171 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"501681d62cddb3d6664788658f5a163337d1bb94e7e9ec5f990903a7da0c0647"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/core/rdd.py:820-849 | python/pyspark/streaming/dstream.py:107-114 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":820}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b9a033b40c5c1a2d1cf16570217d1c683893e76faddd9f5ac062a6d8cbdd89c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/ml/linalg/__init__.py:155-158 | python/pyspark/mllib/linalg/__init__.py:166-169 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"c46ededf303cd1bb47ef2cdab8de93f75c5a44a1760c320029e3c504e7b55868"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:2113-2118 | python/pyspark/sql/connect/tvf.py:68-73 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2113}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2149e8d13356760249268215adb83311e4f9c96f12e8c7525e1de3a00958e92"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:2907-2910 | python/pyspark/sql/functions/builtin.py:17010-17063 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2907}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd586750ac04d303e9a40bfa946a094ad7a0ccac9d578fc46056f2fd4c780c4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): python/pyspark/sql/connect/udf.py:127-135 | python/pyspark/sql/udf.py:82-92 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"8564a0da608963872c928ff630dd0feeff1aa2360a489b271327a85fb74a50e4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/Row.scala:468-476 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/InternalRow.scala:84-92 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":468}}}],"partialFingerprints":{"codehealthFindingId/v1":"6393d2dbbbd83be45a98f0fc80b5bfc4011e5a2dede430a4048b8fce5e18c676"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/PlanRewriter.scala:62-72 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ResolutionCheckRunner.scala:50-60 \u2014 These two members are one piece of code written twice and then edited apart: 11 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/PlanRewriter.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c8e539f29e6f58640278b1f4d7e0f90b40d4de252d4341fb48524277a395077"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala:473-478 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:324-331 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":473}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d453a40b87ccbf9a7303aed2fcda397f6802325917fb40cedbe3d3edf3f4c22"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala:90-93 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala:95-98 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd589a8dea08c034304854987a465f1a7ecc71ad23045126d385ad96029c08c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/maskExpressions.scala:101-104 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1599-1602 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/maskExpressions.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cd750093b0b33da9269aa2c81fa0ee5ee57a2e75fb7850e24e611e6434a29ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala:11058-11063 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/RuntimeConfig.scala:42-46 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":11058}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a341a9b20ded4278888f3da6f27499a44ae560a00a426dcee5b64d8045605ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:254-260 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:217-223 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"72bb0d7d2c4fd758e97672271f45cf34f6f81d3aeccd90d8de293a990e840e0f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:338-344 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:296-302 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ef37c37bef07fb28c8dbde9d2065789dcb566ccc39445c456acc62a98845f25"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/command/DescribeProcedureCommand.scala:106-109 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/functions.scala:115-118 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/DescribeProcedureCommand.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"84edac30ea82c7676d5fd064512d0691bb205567a4173936c0eb245e2d842932"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:95-98 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:92-95 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"0743eb877a4f205cb29295b0ef053a11959be88254a5ffde124db132fc77362a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): common/utils/src/main/scala/org/apache/spark/SparkException.scala:73-78 | sql/api/src/main/scala/org/apache/spark/sql/AnalysisException.scala:147-153 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/SparkException.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"988cad88322d7060111a66f7e52bd56293c5ad2ceab1387e0acb47f471d6b280"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): core/src/main/scala/org/apache/spark/status/protobuf/RDDOperationGraphWrapperSerializer.scala:108-113 | sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SparkPlanGraphWrapperSerializer.scala:80-85 \u2014 These two members are one piece of code written twice and then edited apart: 6 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/RDDOperationGraphWrapperSerializer.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5424767ff688c9f08b190f852c58714c8bda5f799eb727385f8277f971bec6e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): core/src/main/scala/org/apache/spark/ui/GraphUIData.scala:170-181 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:109-121 \u2014 These two members are one piece of code written twice and then edited apart: 12 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/GraphUIData.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"77f74c0cb06376cb185eb339fd8c95efd3b7490745e58fc8015dfe6773d8521c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/readwriter.py:849-853 | python/pyspark/sql/readwriter.py:2050-2104 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":849}}}],"partialFingerprints":{"codehealthFindingId/v1":"3974188739e866320579ed934cf98f29312046deb7c8e4fd6d4e7cb218c8ce2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): python/pyspark/sql/connect/readwriter.py:952-956 | python/pyspark/sql/readwriter.py:2335-2389 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":952}}}],"partialFingerprints":{"codehealthFindingId/v1":"6220554ef92c0101cbf954d2ee492521cf59e39214372091c1dc7bbc86fd4428"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:113-115 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:167-169 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8ca5a90b989f462319666168021b94b867022da59965ae80ad45a2e47f3d4c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/SubqueryAdaptiveBroadcastExec.scala:51-54 | sql/core/src/main/scala/org/apache/spark/sql/execution/SubqueryBroadcastExec.scala:72-75 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SubqueryAdaptiveBroadcastExec.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"17cacaeddd17f74bb5ee9dd0fedcaf6e9d487493fa99d49fce8e7575be2d84de"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/ApplyInPandasWithStatePythonRunner.scala:128-131 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkPythonRunner.scala:256-259 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/ApplyInPandasWithStatePythonRunner.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"b95fe041bf9c0a02fcb27cfb12154259e136018174abc1b50c2eb9919df6c66b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:290-293 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:322-325 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdb3332976ef3bad3b3eff2872074fa053bb8c6deae581cf1cca0f55d6cfb174"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:364-370 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:396-402 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":364}}}],"partialFingerprints":{"codehealthFindingId/v1":"19383541157bd9b5ae1f5ae997221128c588ada8133ecd0c273134821df6e616"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (1 corresponding lines): core/src/main/scala/org/apache/spark/deploy/master/ui/EnvironmentPage.scala:164-164 | sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala:557-557 \u2014 These two members are one piece of code written twice and then edited apart: 1 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/EnvironmentPage.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c8b6484402704ea2adfbb9ad3819ae4664263534dc0ba7f8979c69e6374661b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:81-84 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:83-86 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"276a0048ce319586be291e347b7d27517b04eac8b9b751d75a476a765ac94c1d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala:62-65 | mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala:106-109 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"32e2f179eeb6e40cada395c05da0554c15e6c94933faf3eced5b737ef34c3e4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala:597-601 | sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala:373-378 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":597}}}],"partialFingerprints":{"codehealthFindingId/v1":"2da3ecad04f3a10f2b602eec68436ebe53fe3bbfc3deaa6d6846e01ae66f932e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:46-51 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:718-722 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"3880e265b525f4e77cbc48d0a992982aa823739108a0236f518dd874dfdf2bda"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:140-143 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:173-176 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"69810b6d7c8a078829881a13204f100f4864a0bf930fc44cddb863fda1630423"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroScanBuilder.scala:48-54 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScanBuilder.scala:49-55 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonScanBuilder.scala:47-53 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 7 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroScanBuilder.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"da16b1b0dc46f507ab6ba26bf41b550ba093a7677ea51cfe8fd9fea4f6f3a958"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:428-430 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaRDD.scala:155-159 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"acc53b5fd9465e28699d2456c79558ae83b6e88c64c8034e8c2260a525471c93"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:3024-3027 | python/pyspark/sql/functions/builtin.py:17865-17934 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":3024}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9400f4b0353f9125e19e4da39fa7ccd899c0ff96ef813c44a6be52ea6f47bb3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): python/pyspark/sql/connect/functions/builtin.py:3069-3072 | python/pyspark/sql/functions/builtin.py:18104-18176 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":3069}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb9696bfb32e30b86274b82238d979bd67cd1ae85acc85850814cb6b4b14bded"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:2097-2101 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/FunctionResolverUtils.scala:108-112 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":2097}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9957b5f45f99904049542446ef75dd96772afe11844bad2b0526e623c53ee27"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:390-396 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:802-808 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e116d9b51f3fcfc16a2379046e09e54156102cdaa32a2a3de1f8e728066916a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:518-531 | sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala:611-627 \u2014 These two members are one piece of code written twice and then edited apart: 14 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c9acff8673f09b457e061b5d2e840369411e123ca3f7184bd4a133cb2be4834"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala:47-53 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/ApplyInPandasWithStateWriter.scala:163-170 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"30e9d586ae24c4b4aacef9ae0a4729bcd1d50fc9a9d5efe34302ea30415744c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:118-124 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedReaderBase.java:38-44 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"da4d88788a58c3b08b2c4e3fdd845dbce0670fc1a821508d5a29815b13fc8c9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java:220-226 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/SessionManager.java:300-306 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"60c4b08b9f22f6483630cd2667f920133951947f9675e4c4065e9b35af919fe6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala:864-867 | core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala:643-646 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala"},"region":{"startLine":864}}}],"partialFingerprints":{"codehealthFindingId/v1":"103034ae6c1e99a8ef96d1e52c3f6a4d52f80b0895a61d89f2a0161ac9dafb62"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala:40-43 | mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala:38-41 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd91e6ed92af277e1239ff46bf39c911f568d252894af10111b59990b83a1608"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:107-110 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:150-153 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"8328bf4f6425ab247d632575a6b30e67e5fbc3e63d1e74a874878e5cb99817f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): python/pyspark/sql/classic/column.py:671-678 | python/pyspark/sql/connect/column.py:623-630 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"5236a48f7410dc1951cf12d9ddada3a7ad3155ed2f31567c21e1e03f270d7a5e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DeserializerBuildHelper.scala:85-92 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala:67-74 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DeserializerBuildHelper.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"de968a3b19a7fa3eb222550eaa0dc380da87c11f7a3ac471b9b2fddde6060684"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DeserializerBuildHelper.scala:94-101 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala:76-83 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DeserializerBuildHelper.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"193b1c70713a0cebb62d82d110845c544e9c02668701136df5a50bc9d5ba6a0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateMetricsImpl.scala:58-66 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/TTLState.scala:454-461 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateMetricsImpl.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcc8e72adbdb42ecfc31058a731716b5075e44f620f78bf17c7b94ab7b3a1ae8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java:168-174 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/SessionManager.java:308-314 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2c9e4781b8e51b811605a89bb2f9358c97f76ea63add580d3d5dc6efefc7ccc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/AbstractFetchShuffleBlocks.java:75-79 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RegisterExecutor.java:79-83 \u2014 These two members are one piece of code written twice and then edited apart: 5 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/AbstractFetchShuffleBlocks.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3d3b0466e649ffc4a27ebeceffa13b9d392a7ea5af721c9f7032e1b0a0797d9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala:58-67 | resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/SparkRackResolver.scala:102-111 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbb67fd9d24ec460adae9a08da71a97e41d8dc1cbca5dc64b655e6b5d6662fce"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): python/pyspark/sql/connect/dataframe.py:340-349 | python/pyspark/sql/connect/session.py:418-428 \u2014 These two members are one piece of code written twice and then edited apart: 10 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3fdd2bc52480f3163024085b74d26fe7b9f7d955bbf70a69190a9793b00b458"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:192-199 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18119-18125 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"2922d00bd4cbb93f7eb93e785ef32c598e269408a708cd04b146ff370fc5cd67"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala:877-883 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:143-150 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/QueryParsingErrors.scala"},"region":{"startLine":877}}}],"partialFingerprints":{"codehealthFindingId/v1":"d24fbb315cb89bcf2fd633655c8e6fb019c4f4b0b61574c3e81a78ea3cb90b14"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:296-304 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:340-359 \u2014 These two members are one piece of code written twice and then edited apart: 9 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7f6076fd5d1440ad6497b6e8fee7af6427d0b29f1e46bf5f74f1a13a7944deb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ExecutePlanResponseReattachableIterator.scala:95-97 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/GrpcExceptionConverter.scala:63-65 \u2014 These two members are one piece of code written twice and then edited apart: 3 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ExecutePlanResponseReattachableIterator.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d323d4dc95c3271fda2564d104ba27aa6fdce03e1b2f56acd2dc377db539701"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (63\u201364 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:393-456 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:431-493 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":393}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ba6c8702f84a836b0198f956bb0d6cd87241a9b1f33954bda2db66d0bf8ef3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (62 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:1110-1171 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala:257-318 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:1110\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1110}}}],"partialFingerprints":{"codehealthFindingId/v1":"516e9044e2cfab236be630d1b0cfaa71d2b41df66fa3ab1619131a1613e19ce7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (51 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:389-439 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:536-586 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e5e44cf57e786fd04f01115bc7424e6a99e981046eabbb91a12bd8947e8bd67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (45 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:736-780 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:892-936 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:890\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:733\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"4165d92a7b0a39842f827cb65b55808fad0b90fcba98a579df64daa0445ab3bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:128-171 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:108-151 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:128\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"0350ca455280249055a7fd6eb16b448fbd0d7caf98563a7c5baab6f1370550b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:539-582 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:455-498 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:539\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":539}}}],"partialFingerprints":{"codehealthFindingId/v1":"feb3e1348c955a8b657639f4f039f64b983a41b98aa5a9f93eae8ab48055f8bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:791-834 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:668-711 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:791\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":791}}}],"partialFingerprints":{"codehealthFindingId/v1":"425d5bff06f5563bbba8a454aefd02d66fbdeab31fc1dcecdf8174f11004cc6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/AsyncCommitLog.scala:107-150 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/AsyncOffsetSeqLog.scala:137-180 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/AsyncCommitLog.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fbef9b0f3860080f192dca78ac176b6d16da48e56c9e15a692f6b9e2dc68a8a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (42 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1306-1347 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1169-1210 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1306\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1306}}}],"partialFingerprints":{"codehealthFindingId/v1":"1940a16a735d6416d12242ea338ddc955bfd7cd8508ef8c5dda502717dfbf197"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (41\u201342 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:806-847 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1285-1325 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:806\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"580907900581bb1fc0aa1f4b9bdd3a2cd07658226ed73523f49ce378c6048462"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (41 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:920-960 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:781-821 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a53d4ec20f2d1e27b29de406a9d9b831ef8438c7796fa63edc995242fc66946"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201340 lines \u00D7 16): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284-300 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:325-342 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:369-403 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:432-467 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:498-534 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:567-604 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:640-678 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:716-755 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:279-295 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:300-317 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:323-357 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:364-399 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:407-443 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:452-489 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:499-537 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:549-588 \u2014 before extracting anything, compare \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala\u0060 and \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 144 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f201676b477c3510fe6c390bc20c6d98e4119b092269f1b495be1eba206cdad"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (40 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:398-437 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:1693-1732 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala:398\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"dac9a41aa612437cce5e1b06b29adfc01bb4224df6c0138bd546c0de79b5dc8e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (37 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:591-627 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:506-542 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:591\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cb91980b9b98b0bfca5119e494ca8f616f430061d1d042dd7878e468660064a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (36 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:733-768 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:610-645 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":733}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0a92e3f4e7ba31d011e65bd02d4f9ab95aa8f226b0b40e468c12ed597deabab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:338-372 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:492-526 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"622ae1de8c7296224e3ae761873902f2b93a3cc385b20cee017c291e46e7ac9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (34 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:223-256 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:225-258 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"4642593ba1a95a7bcee21091a1ef5d35fc0a7de9dd41d74e4e1bad724b8f7c47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29\u201333 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala:87-115 | sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala:171-203 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"cabe98fcd122e3e02bdbf1c8f61a11e43108b701075e471964c4a1cf40744d60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (32 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:811-842 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:851-882 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:811\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":811}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b78b0d73b4f18cb97b3d71df894361fc9882b1a784ccf19606d412ac3201f4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (38 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:988-1025 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:849-886 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:988\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":988}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5d1f252e30b57ad24bbb40313d5b0dbe49019902f421cfd9202dd3356a018d2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala:322-352 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala:116-146 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala:322\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab1b175f71e7ce841aff1290653c73af7ea0033f9e3701cad2192a395b86f439"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 2): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:211-240 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:191-220 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:211\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"e746565c8ea302a15dba9e40d8b01702bf1bf05e82e063ac5baae30b48d5d093"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:841-870 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:727-756 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":841}}}],"partialFingerprints":{"codehealthFindingId/v1":"557526ae3cee1ae88e493e7fc1fae45ccb2de0639f0513a669d0f5cde55b1a96"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4842-4871 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5032-5061 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4842\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":4842}}}],"partialFingerprints":{"codehealthFindingId/v1":"c31c9ba4ff29fecdc5caf1dfec744b3cc8f917163c461cf419e47ed898c0fb89"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5064-5093 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5302-5331 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5064\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":5064}}}],"partialFingerprints":{"codehealthFindingId/v1":"c929d2c27a924162b6d83e30a6fbfaf5d15fd9073573a390f1a186fbf6704199"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201329 lines \u00D7 18): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:245-258 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284-297 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:325-338 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:370-398 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:433-461 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:499-527 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:568-596 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:641-669 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:717-745 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:259-272 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:279-292 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:300-313 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:324-352 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:365-393 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:408-436 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:453-481 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:500-528 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:550-578 \u2014 before extracting anything, compare \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala\u0060 and \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 144 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:245\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"212f8e75bff48e0bf48741386fcf347e7bcfafd1c2f1ca912efc7745c8e1f820"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:322-350 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:359-387 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:322\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"741c945ff69554b64db5041131c4cd6f92045dcaa959d7542350037ce4c85021"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26\u201329 lines \u00D7 2): connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:94-122 | connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:151-176 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala:94\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"aebc658a23428930592acacce6ebb5b139833b18a91bbc038a168b1f5935d751"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 3): core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:38-65 | core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala:37-64 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:52-79 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 69 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"68804d219d8b79d96e0c3e95b44fc74f877a3627b6fe26dd0674ccda1a210251"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1511-1538 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1606-1633 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":1511}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ea66bbb731a9fd12203a0165d7488ffb0351f5581ddc22a569bdd1ef0cae34a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:892-919 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:1046-1073 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:892\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:921\u0060 calls \u0060close\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:1074\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":892}}}],"partialFingerprints":{"codehealthFindingId/v1":"08a89f9855ba9c69f14aff2e06903422459c5f54ba9e8ae6c532dcf248633cae"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201327 lines \u00D7 20): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:222-234 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:245-257 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284-296 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:325-337 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:371-397 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:434-460 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:500-526 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:569-595 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:642-668 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:718-744 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:240-252 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:259-271 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:279-291 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:300-312 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:325-351 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:366-392 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:409-435 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:454-480 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:501-527 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:551-577 \u2014 before extracting anything, compare \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala\u0060 and \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 144 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:222\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"486608345bce04c264a0229776fe8644fd9225884c79d2cfece636bc2f317525"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18\u201327 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1949-1975 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2636-2653 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1949}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e0aa3ec1a014bb9143ea89842692b5a91907f6831dc27859d7fce59aa944d72"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26\u201327 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala:280-306 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala:77-102 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb4684f16b3f6eaf6e752864e172d4f7cf6a63470a9628985dd2eedb5a1e443c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:394-419 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:362-387 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":394}}}],"partialFingerprints":{"codehealthFindingId/v1":"01329c3f786a0290422b66f6d4768c0a9c3b90772d82f50aa672071e4cdf9e36"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2258-2283 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2295-2320 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2258\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2258}}}],"partialFingerprints":{"codehealthFindingId/v1":"34a034a436e9ea82ad7f825f521ddfdcf9f4301ed8b01b6f32c0eee7f21d6377"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:352-377 | sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:399-424 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:352\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"42b059756c9a7597ce5911af873e5c3dae5df9d12ee6c4bcc9ce6ce5086bcee8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201325 lines \u00D7 22): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:201-212 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:222-233 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:245-256 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284-295 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:325-336 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:372-396 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:435-459 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:501-525 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:570-594 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:643-667 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:719-743 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:223-234 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:240-251 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:259-270 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:279-290 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:300-311 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:326-350 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:367-391 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:410-434 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:455-479 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:502-526 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:552-576 \u2014 before extracting anything, compare \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala\u0060 and \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 144 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:201\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"c96cd333fce84804c9af13b8556447213f512d3d9d939c2e27e5d433ad07a50b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:752-776 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:684-708 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":752}}}],"partialFingerprints":{"codehealthFindingId/v1":"b43e5f55cc388e3b27b2148d4946d97dcb69db49e9f1425e73b7d4dfcf1b6c65"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24\u201325 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:321-344 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:318-342 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:321\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":321}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8d50d443d966ce58b7f5cea1eb759adf0686a42955e36dba5275a60fba49814"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:84-108 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcWrite.scala:48-72 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:84\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcWrite.scala:46\u0060 calls \u0060set\u0060, \u0060getOrcSchemaString\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:82\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e24d48fb5bb6d8de8c98459a0ff6c00c338b4a6408c8be5b0b8b3d659d0832d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:186-210 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:221-245 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:186\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e9e8aef28195f9c2f00a4a95c11efd98438d3adc2a60b1eb5fb2b2bdc87cf15"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201324 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala:188-211 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:2388-2410 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xmlExpressions.scala:217-240 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"f90d8a39e9b121b79697d3848b65aed62d5c93ed0a4e07b7c537707d617ece91"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:583-606 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:198-221 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:583\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":583}}}],"partialFingerprints":{"codehealthFindingId/v1":"b396947c71930272ae04655304d1ecc41928b9c91f26d2215f42c894c7dc278f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201324 lines \u00D7 2): graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala:192-214 | graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala:283-306 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala:192\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cc64811244c733a3d371c9e57f861d61047bd9f5c7259ed05f681bf896616ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:168-191 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:170-193 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"7258e71c8903f0319e39b9ee692adfa0cea2c902bd8449a43d23afa38e79419b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:445-468 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:592-615 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":445}}}],"partialFingerprints":{"codehealthFindingId/v1":"57f6e89e9830d0f8a5f25a0c8610ab528e38cbe179fea62ae59418bc4afaf6c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201324 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala:453-476 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala:173-195 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala:453\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"18f40d786af51d81f519e5abe1af393652a3a7ab50b3e8ba174a31a8ca9dc617"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201323 lines \u00D7 24): sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:181-191 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:201-211 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:222-232 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:245-255 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:284-294 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:325-335 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:373-395 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:436-458 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:502-524 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:571-593 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:644-666 | sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:720-742 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:207-217 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:223-233 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:240-250 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:259-269 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:279-289 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:300-310 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:327-349 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:368-390 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:411-433 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:456-478 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:503-525 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala:553-575 \u2014 before extracting anything, compare \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala\u0060 and \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 144 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala:181\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a0cb41c40a9de62ec1fa8bfa961e77e8808f66d50629b53d4bf4a82bc5fbe19"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:834-856 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:977-999 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":834}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7477dd1986282cba395336b9efdfb275d4b8313f857dcd0a482825378c8fa76"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201323 lines \u00D7 2): resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala:36-58 | resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala:38-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala:36\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1fb11e11bfc180c34054aea1bd714fb8e46edd7c37e98438fb2d464c43058e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:398-420 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:444-466 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:398\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"a17b8e2f1afa96de37d939f8542cfcc595dadb5cb68567ce977e20c355db5cf3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201323 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6633-6655 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6732-6750 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6633\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6731\u0060 calls \u0060replaceTableHeader\u0060, \u0060identifierReference\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6631\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6633}}}],"partialFingerprints":{"codehealthFindingId/v1":"670368d470de4f7c8df9cf6fdcb90c54330adc69579bb1f70348cb7ab65ad6a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1764-1786 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1851-1873 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1764\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1764}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a295d09156bb838c813e36a72c2af88ddc6078ed4fe8ea043fb66cdc7c3ac46"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201322 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:315-333 | core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala:254-275 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 50 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:315\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":315}}}],"partialFingerprints":{"codehealthFindingId/v1":"bff2ca9f81c2401087f8b294654ca662f670d19b262f058bef06c4fc40197cf5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala:33-54 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:201-222 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b7f6887cf1a8aef9b4be8e9033548c6307e9c4f849b3648e97be2fd66598a8e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala:205-226 | mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala:403-424 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"db560adc5f0176da6875314e076a2687b901b579f14df4ded28a8efd8a62418e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201322 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:152-173 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:322-342 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:152\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6db1c6ab3512320008f6f63f37b0dfd16576fdf7b997278d3db8a27e0193d47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201322 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:2060-2081 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:2390-2408 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:2060\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":2060}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaa89b218333552d22bc1d56339970a80e8cd21076b8c8d475ecc4005d69b7f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:145-166 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:355-376 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:145\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"f973706d7c9489468e471770adc473292aac3baf2cd90e051b4493f22096e481"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:1044-1065 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala:208-229 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:1044\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1044}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fc50715f2dfe13d40159cdd14769ca92208644e9e43bbeffb869b623d00a5d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/plugin/SparkConnectPluginRegistry.scala:173-194 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectInterceptorRegistry.scala:99-120 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/plugin/SparkConnectPluginRegistry.scala"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"182a7def6ea99c16164872db04710a05fbe26775e5d0bc0ef0b749746d054411"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:403-424 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:250-271 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":403}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e681e378d7708d47af7c29babfd23d0aab12d03d8dc963ef0f2921a01337e0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala:84-105 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextWrite.scala:46-67 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ae7007c1731c3e3f3af67d88cd157129176ede5038bbc2d4370c5e9865170c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateScanBuilder.scala:166-187 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateTable.scala:65-86 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateScanBuilder.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"156542318aaf560fc0c366b8393016f31a8d874ba69834b92f98188387222d80"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1326-1347 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1447-1468 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1326}}}],"partialFingerprints":{"codehealthFindingId/v1":"a332384eb3463425da9eb247b736289890a8d23be3c40edc80c566d153be4431"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala:68-88 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala:132-152 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala:196-216 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b3924d02abf8f98b314ab9d49895fa20120f1ecae84282700a648a363c98fcb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala:65-85 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala:120-140 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala:65\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"e505ce1baab24dd5381104becb52579dc32755066f447466ed7bbd291a5e00f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:167-187 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:124-144 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 63 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:167\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7f274245d51ce89d37d8e226e35536d982c96088f909c344f9a240003bcfd1f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:433-453 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:401-421 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:433\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":433}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cd45a4aab045874f2ca62d204626095792920b479ba4c5c3bfa7731285447df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:108-136 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1453-1481 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"c77d6e606491b516f3e983caebac2d2d53130c00a40033a83579a2c5dce95d00"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/HadoopConfDriverFeatureStep.scala:85-105 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/HadoopConfExecutorFeatureStep.scala:42-62 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/HadoopConfDriverFeatureStep.scala:85\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/HadoopConfDriverFeatureStep.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"7122785778f5d266a423f8fc831c5f660e9d159808abdf2f28627fe0f24b5e8c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala:267-287 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala:340-360 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/vectorExpressions.scala"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"fed76decfc6688d131678777611d293162b1f31b319010e9bce1daf9fba071d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:245-265 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:124-144 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a2fb1bcfb9100168b7880446627955922bab66fbf228733b337db42309370e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201321 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:154-174 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:171-190 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:154\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"d082abeb31faa33ce4a21b04827f97f538f38093e03585b64c79d42f9daad3be"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala:213-233 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala:106-126 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8072fd318fb8ac9503fec8bfcfdbf558f6d5a6b863cc4cd48368cc328cce037"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 6): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:115-133 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:165-184 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerSessionPage.scala:111-129 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:89-107 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:136-155 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala:91-109 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:115\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"6235486c8bc67d91b70e55655719239dac511a9c621b7c73d1803f9fdf3b3f6d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 4): core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:38-57 | core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala:37-56 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:92-111 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:52-71 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 69 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6e20f88615458394cc972daa639ca38ab79946d0d3fd7595dc3ad8998faf0ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2519-2538 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2557-2576 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2593-2612 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2519\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2519}}}],"partialFingerprints":{"codehealthFindingId/v1":"c32ed2f2f23e8ff9319c1077f7e843ab6b73bd72e5663e2b58b96eb956e436b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:473-492 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:392-411 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:473\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":473}}}],"partialFingerprints":{"codehealthFindingId/v1":"4818de4c906f4a8ca81f31c70a45d2052c80e2fddef6998e044253c4d169049c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:465-484 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:106-125 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":465}}}],"partialFingerprints":{"codehealthFindingId/v1":"041534c92044feec038e9e6564a264c0e25da1fc1e2e1ff7276ea005411e6137"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala:237-256 | core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala:322-341 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala:237\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d7fa873ce6b4bbb11b58899f89829fd17b70140ad3d4c5cd3831172851b9039"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:370-389 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:452-471 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 81 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":370}}}],"partialFingerprints":{"codehealthFindingId/v1":"125a1a64984365e6b2e824a186ebb238cea2457dd982db0fcbd96b8d801f1caa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:188-207 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:359-378 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:188\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"92d3ff7885a88cb11e657e7de29fef8d6e1b2a1f37f5d330f0a3128c1fbd8560"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2372-2391 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2399-2418 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2372}}}],"partialFingerprints":{"codehealthFindingId/v1":"4558d8c80b9476df9e211b1b970ff65bea56caee7a3fe709249cdcbeb98c58b5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala:164-182 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/percentiles.scala:109-128 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala:164\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"df4d453df8f3af56b98c55cd99812d5840c7a35a7551cee835dae68a3664d32a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18\u201320 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:113-132 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:377-394 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:113\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:394\u0060 calls \u0060Some\u0060, \u0060TypeCheckFailure\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:132\u0060 does not \u2014 after which the two agree again for 5 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab2423802c7383822fae3ecdd9b6650337170d630ddffb9954535d5add5839dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala:64-83 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala:324-343 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala:344\u0060 calls \u0060forall\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala:85\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"80f38768371c00a4c19c3b6acd116374586da0f5da93edfc1784958ef8d19273"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:106-125 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:304-323 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"29a76c14506794659ba3bacd7aa2d08998b7148ab4d17e949c19ac948ccab757"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:578-597 | sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AQEOptimizer.scala:53-72 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:578\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":578}}}],"partialFingerprints":{"codehealthFindingId/v1":"0939c45c4e4be23bd4dda4b56d1c1c2e16fb5aeb6845809d3fc3912210fc7cda"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:408-427 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:229-248 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala"},"region":{"startLine":408}}}],"partialFingerprints":{"codehealthFindingId/v1":"910b1437787b76ecc48245d340167763a988f30f38c786f84da753a6e7657116"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:127-146 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:149-168 \u2014 before extracting anything, compare \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 38 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"bae6f78df05702cf2fcdf22e0ecc7cb131ba7629697fd7f0801ac9016fb2bb8b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:452-470 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:371-389 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":452}}}],"partialFingerprints":{"codehealthFindingId/v1":"94307bd30fc4f6fd16493782626be4c46bb09197009439d455b5e4aff3c25599"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:133-151 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:141-159 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:133\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"932dd3c11949a4d952c2d71aa31bde7a32efa69c3e097ae7b2b77c84d73567d0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:492-510 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala:522-540 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala"},"region":{"startLine":492}}}],"partialFingerprints":{"codehealthFindingId/v1":"a218461c341037d23d91afc3e1e1f6bda62829e9e3acde4fd200c2a8ab46d4f3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:90-108 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:92-110 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1c9b6d6092c207c6ac165233e0d6f659932adb7f210a00ffff9543caf5d418b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:320-338 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:402-420 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 81 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"983770a737bb7301e09137ed15d6fbf1143009aee6b32af568227b413671dca3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala:57-75 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:225-243 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/MatrixUDT.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"08516aaedfb74b78dbeb1844dc07c9b6ae358aece549dc618accb5e8fe71c42a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala:33-51 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:286-304 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"0174445393724d0d6171bc84d5a762201f1857bf820af391daeff1d5f41c7114"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4200-4218 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4278-4294 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:4200\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":4200}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f198569f1c8022506a1bd65aac31fbbcbafa5891e23d20ea3efc351aa8dbb74"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:396-414 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1291-1309 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:396\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":396}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbe2440bb3a1f1893a3b7f608b5ecda38eea8bc831f285ae6a66310c282acf80"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala:66-84 | sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala:105-123 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala:66\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a053e1611eb49ce3b4969e68d5b79f47c2b4621d04885f1545e5e491bb9aa34"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:767-785 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:810-828 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:767\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:829\u0060 calls \u0060verifyHiveSerdeDataColumnTypes\u0060 and \u0060sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala:786\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":767}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3969eb5368ec7095f50c30c91eb72ccbc90cf6e49cdc9606c66cd150e0030be"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1623-1640 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1761-1778 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1848-1865 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1623\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1623}}}],"partialFingerprints":{"codehealthFindingId/v1":"8938290179b069b2a717e0de8fcb7c60fe8b981e91eb50801684eccc851519a6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:403-420 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:259-276 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:403\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:277\u0060 calls \u0060logDebug\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:422\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":403}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0cf343040000350fd4f7a5405adcc6541e7bc8a50b50fe512fce0ead27f89e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:352-369 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:390-407 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:352\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"57efdc009c77f1d11cee06fd0be3570b927acc838c476317f15f05ca6a466b60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): core/src/main/scala/org/apache/spark/SparkContext.scala:1124-1141 | sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala:939-956 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/SparkContext.scala:1124\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1124}}}],"partialFingerprints":{"codehealthFindingId/v1":"182d936e8f24cfd5d8b9b54d8788aeebdf2486d0499addc6a7d81b98334efd18"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:375-392 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:358-375 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"357841c1fff38f548e1d9c2ff393eaecdf4bcfbfa774bd5c5527b1a24ec4251f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:674-691 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:564-581 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:674\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:563\u0060 calls \u0060logDebug\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:672\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":674}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7c670c90c5f86a894bc1aa7c0e32f260b9be9edeb9997160262eb54fe8c4e07"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1247-1264 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1110-1127 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1247\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1247}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b5518283247956676dd682f88f92fb465eaa5ad0b013bc79b44267bd963e931"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:478-495 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:625-642 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"195cd956f7b1bb29f181e22145f8acf8b0eac7d2ea7aa2055853862b4db1b6e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201318 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:102-117 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala:98-115 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:102\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"c83c3c3d828bf9ff9eada86244dd1405ad873d26137b13f03855a82700c1c944"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:212-230 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:342-360 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:212\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"83159977f7cbb655988a16e3f077f48ff5c2a821c0a7923be4f894939f94cc50"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2617-2634 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2695-2712 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":2617}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d0b1cc8e870362192a244edfd6c53b80eed1f75692cc4fa372ad6c27509e027"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala:145-162 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala:147-164 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala:145\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d79b6ba968ca95533af4a1727c9699b3899c1f83ff39df340c9701ca4901638"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:154-171 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:496-513 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:154\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdb0f7fe9aef8c67c453db82fc88f96bccf235d20ad63df62f8fc072f80f5766"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201318 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:90-107 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:146-162 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:90\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"588ee1cc1b62bd33be1efb3476ef207b188bea1e31bac6aee356759c37922a45"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201317 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:331-341 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:999-1015 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:328-339 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"70311faf1f180a1084168315ebad05bd4ec7eb7d00f5eb0f35aff2e56a0f9103"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:553-569 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:615-631 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:682-698 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:553\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":553}}}],"partialFingerprints":{"codehealthFindingId/v1":"f00cfc829d6256229757d874c03829f5dd9ac9598a9e4309f087880fae33cbab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala:150-166 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala:123-139 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala:150\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"de3e053b478dec7b30fd329f7f0d05ba36f385fcc7da2dffeef4d2bc892617a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala:174-190 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala:228-244 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"98a8971e435f236f475d8b0f4237ebbe2c87542c4762dbd929cf96ea84673c65"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:567-583 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:179-195 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":567}}}],"partialFingerprints":{"codehealthFindingId/v1":"08832daf4800f3f7ff09ec2a5ef64363066b476acae2ee46f51ccad802a54cc9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:60-76 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:62-78 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dbe671a4c859da8e5b8be6e00970ce6dbd9f87cc14e00f6fad6b653bf88576e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:79-95 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:87-103 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"74a37543c13935cb768dd807d9c013f7343adc188679ef38cb4cfe0f6de8e669"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:312-328 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:466-482 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"362cb5755b63f205f06e2dba9825d05e5751a43c5c6281ec745ba6f71079769f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:689-705 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:842-858 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":689}}}],"partialFingerprints":{"codehealthFindingId/v1":"8555a184f9479bc361e3ef72d7d3545f399a43d808dd114bfd6321af78e9e869"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala:54-70 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:307-323 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/VectorUDT.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"44c6dd36117c8bce38afa2e1e8267e0d19708d649264d970c75a33d88a53bb2e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:383-399 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:402-418 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"023ac6754d5c57028de506708a3496374de3a8b5cead746ba8286a587b298564"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:112-129 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:279-296 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:112\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cabc92b7d1cc910d14668f07f159df78aac6840af8c54b3c6eb1743fcac138c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201317 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:96-112 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:72-87 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:96\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"63a5d7b573c214634bf14dfbb838c28b1e7c4787de21ac80bc1b3bf75d6e1ac3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:245-261 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:301-317 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:245\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6785e4aa5c865094fee8459800b2ae6f7f5955adc624a6e8b6cb1f1119b08e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201317 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:244-260 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:515-530 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:244\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"138b5ba8d2c90719af66703e5939531b85fba888d9c814f2e855b1e6ab4b7b8f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 4): core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:124-139 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:153-168 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:182-197 | core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:211-226 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala:124\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c39e1815836286ae8d9d6130ad448bb3ef0a42ca568c91ca58b565039416cdd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201316 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:126-141 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/ColumnarArrowEvalPythonEvaluatorFactory.scala:218-233 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonEvaluatorFactory.scala:102-117 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala:355-368 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:126\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"39447f24a3c554b0b3811a7dbee4f2465a211d796131303fee579034de3854b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:377-392 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:459-474 | mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala:90-105 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 81 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:377\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc2529e834d0fb1ee9fd36d0fa66983660665e5f34004a331e32397a0c832249"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala:115-130 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala:292-307 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala:115\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"9be7d3fdcc1c1ff56c8586ef0c5e2947ca40de2e5ee9b8bd8338353287a4b8ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:121-136 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:123-138 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7b57d4e7f4a0f0e7315aecf815654a56a7ead7816652e083da82699f0943ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:305-320 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:289-304 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:305\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:321\u0060 calls \u0060indices\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:305\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba579fae304d0b05078eff3bc877a976706859cb55dfcd998a3def98e299510e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:357-372 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:340-355 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"244623277f2fd727cdd590437e03e79d1bf5b381b9f9f7e9d2a50c2b1c4d7825"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:864-879 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:730-745 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:864\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":864}}}],"partialFingerprints":{"codehealthFindingId/v1":"9126f12e1f30e508a712c2b123db3dd30e63bb7b07ded42993dd1e9e934e7ea3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:545-560 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:688-703 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"bacd32bae22679d84c0857a8b5ec54c8c2668f17392ef28964f33dcdb6ec680f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:588-603 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:734-749 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:732\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:585\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":588}}}],"partialFingerprints":{"codehealthFindingId/v1":"b865d419a1c4f120ae64bc68a9ac6c81cbac6656c11f046a366b4d294801614c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:349-364 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:431-446 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 81 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":349}}}],"partialFingerprints":{"codehealthFindingId/v1":"2405fdd1c8a4ac511c4c118353b6e21b967228405a3c941c5a55b7efd660c673"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201316 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/AFTBlockAggregator.scala:123-137 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala:144-159 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/AFTBlockAggregator.scala:123\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/AFTBlockAggregator.scala"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba930107f5d9528a85ad9d2e096a19d07c21c778c162129fbce7a2bc122e9f55"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:71-88 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1416-1433 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"02bd3930dab6c43ee566452ee0fefb0aa923f4d214b239e83a4a5b3494b52532"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:183-198 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1528-1543 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a672341ce3a569a8ab5a752692907d8cffb9b4d1ab3c82f494dca591edcc2a5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201316 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:702-716 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:202-217 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 46 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060n\u0060 to \u0060s\u0022Nothing has been added to this summarizer.\u0022) val realSum = Array.ofDim[Double](n) var i = 0 while (i \u003C\u0060 in one and \u0060s\u0022Nothing has been added to this summarizer.\u0022) val realMean = Array.ofDim[Double](n) var i = 0 while (i \u003C\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":702}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff8c62d1e06a50f84c1a785f228c307a42a0ad2b7723d474cc0e6836845176b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1482-1497 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1577-1592 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":1482}}}],"partialFingerprints":{"codehealthFindingId/v1":"a87fade2ed2c81aad826d3db23aed4fa24cf1485158bde902660b4f0f0fcf3b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1378-1394 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1742-1758 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:1378\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":1378}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1754cfdc74e3a24d3753ce0ff403a879c55224f898dee0775110821091f17cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:478-493 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:564-579 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f254cb912b8bc9a3a9e035c7c73936b4349dcb4e943b3eb046593b394812bfd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:147-162 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:119-134 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:147\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7a87e7c55a2d80d843f128aa8f8c76dba3ad230949ba058fc51ece40474d8ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerSessionPage.scala:93-108 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala:74-89 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerSessionPage.scala:93\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerSessionPage.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1361e800b367f1c4f92075420b0c5c6f139b77927f5a0ac25b6f1dac1b6aa4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala:66-81 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala:60-75 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6062bf1ac6c99e16d93ca26ddc566d7570d034e9517944f83b13ce7b524d5d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201316 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:925-935 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:946-961 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:925\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":925}}}],"partialFingerprints":{"codehealthFindingId/v1":"81eae80afe6315e612478c658af434462630afd0c011a311592ad67f89daa52d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201316 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala:142-155 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala:803-818 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala:803\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a5c70611ca772808d87171006eefa8b84ff1fd2f96a8cc49755188054fb9831"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:343-358 | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:390-405 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"b791ed76e886b9883c0e7d23de68491220fa92008a92fe9cea31064372de5a58"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:344-359 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:389-404 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala:344\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/FlowExecution.scala"},"region":{"startLine":344}}}],"partialFingerprints":{"codehealthFindingId/v1":"120ed791fa12bd99b895a660943c65c0519be565ce0c5729112a372f8f549431"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:86-99 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala:83-96 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala:85-98 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/LeastSquaresBlockAggregator.scala:91-105 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:86\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"a46c8a4dec0fce8a0f123c88bcb26bb4ca1c97440ec4807c425a7bf0d3cc6e24"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:830-844 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:870-884 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:916-930 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:963-977 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala:830\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":830}}}],"partialFingerprints":{"codehealthFindingId/v1":"87b9d1e49ee58c7e15ef82f3567f29438d389aa55bc7f4541382df1f80472072"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1566-1580 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1704-1718 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2792-2806 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1566\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":1566}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ea3f21ad0f7ce0ef3fcf2f51d9629716ddc303b44f43a024f9441168fb4651e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:200-214 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:244-258 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:300-314 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:200\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:299\u0060 calls \u0060GenericInternalRow\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:199\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"f69488784a88385959c011fa3d5844566480f2efe9517e4f7a129408e0da1128"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:193-207 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:237-251 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cdd5d4f2c327aa458849ac18c88701483f12c7ad465e87ff70ca5fb186c7208"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:234-247 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:277-291 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:234\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbfb8c862b02f827eb09120174bd1b01c6c7a631a4a5a273dcdfb3d8fe3e4fb4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201315 lines \u00D7 2): core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala:286-298 | core/src/main/scala/org/apache/spark/storage/BlockManager.scala:962-976 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala:286\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6dbf72d39a1ead3d83849b5ea221ddb76dea93367a896796a320f0c81c9877f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201315 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveFetchCursor.scala:46-57 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSetVariable.scala:43-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveFetchCursor.scala:46\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveFetchCursor.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"32bc590a825808bacf229bd992c8534606e57304d74a92dd34680d2a24acc0ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:288-302 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:494-508 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:288\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"30fe50123e28531bae3554bf29a5030cab204a7fd2e6917088cfe8d56d68d845"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:1751-1765 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:1776-1789 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:1751\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala"},"region":{"startLine":1751}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dd351714a2a5f77fb7e2e5325e38386ff0a5bf08e0a972fc9d24f9650bfc65f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:308-321 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1568-1582 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala:308\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionEvalUtils.scala"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6495091fab68af6cce22081dae1ce933aea6361bc1089c023b40f007dadbc45"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:207-228 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:417-438 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:207\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala"},"region":{"startLine":207}}}],"partialFingerprints":{"codehealthFindingId/v1":"7bbbdd824d46ade4e9c7dacf1028b0990e3c39652640e78e9ef1653990938328"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala:112-126 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala:252-266 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b0be23e65791eba81b858ab947b15bd273c70f462797bbf20b4beaa5a9bbafb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:320-333 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:336-350 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:320\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e23c63696d0f0b5e91dc6a54edc1b65dd5c80248a7356785b769aec859ec7a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala:87-101 | sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala:125-139 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4cc6fb4351a019270bcb102105a226fbc10b597b1bed9b1ac6c726188d7ad0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:802-816 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:829-843 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:802\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":802}}}],"partialFingerprints":{"codehealthFindingId/v1":"45fa5cbd18f930cb98f4a37b86a227ca61bd7b491718427ca7fb9a51d3418553"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala:88-101 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala:222-236 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"acef892d9ea13d8849bbd1062b597376146b262a9547ccdf4075879a43e9ea4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201314 lines \u00D7 4): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:131-144 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:502-515 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:601-612 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala:699-710 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitmapExpressions.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"820bcc7a5bb083ff630058d93ace9c0aa81b1c7b5f42ae2b123ec15ced9bb79c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 4): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1574-1587 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1712-1725 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2800-2813 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4529-4542 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1574\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":1574}}}],"partialFingerprints":{"codehealthFindingId/v1":"4361fed221cf500e2c919838dde9d23d4157b250acee55cb2d0f4f1fc963360f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3): sql/api/src/main/scala/org/apache/spark/sql/Row.scala:496-509 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala:110-123 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala:113-126 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/Row.scala:496\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":496}}}],"partialFingerprints":{"codehealthFindingId/v1":"a86782434388eef9d9d6b56058b72e2ef37ac9f023e9050316492a58d0483983"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatch.scala:49-62 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaRelation.scala:59-72 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaRelation.scala:74\u0060 calls \u0060logInfo\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatch.scala:64\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatch.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"d573504751d97fbd144a01837090a025ac9ffafe824b4a8ba28f6150660cc5b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201314 lines \u00D7 2): core/src/main/scala/org/apache/spark/SparkContext.scala:1107-1118 | sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala:916-929 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1107}}}],"partialFingerprints":{"codehealthFindingId/v1":"f69ddc98a9424e43c926294c35bd54a5604db5ef6a2f1acfdbda96b3d8512b88"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201314 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:343-354 | core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala:285-298 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 50 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:343\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8d7883d9a03b9216fb062a65234c1a2bfb76104618043448c2d789a9c3c333e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:365-378 | core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala:325-338 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 50 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala:365\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"0097aa0373bca284cd813c49b2d323c5dad04959bb1824c38d1aac9872d0fb66"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1280-1293 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1143-1156 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1280\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1280}}}],"partialFingerprints":{"codehealthFindingId/v1":"24a180141d2618cca365d461bcaa1388536fcc2afd64c93ae367e6e08c98376d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1349-1362 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1212-1225 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1349\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1349}}}],"partialFingerprints":{"codehealthFindingId/v1":"e460dbb7dd1534cb2c18e7ff66558f7a2ba43413f18d8e08e3acac3c4d0c73de"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:720-733 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:875-888 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:890\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:735\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":720}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc5e82cd2b8adae9573dc4d700f38f80f35afa960edc4cb264f06400a273a418"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:311-324 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:311-324 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":311}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3623b4dc2bcc0887d75133314badb4c2b9d34b8dbd325982c8077a6c3b8f38a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:420-433 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:383-396 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"07bbc3a1fd05b709c4a663fc8e02719090568cdee4c09e6d428ad81357516f41"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:124-137 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/StatefulSetPodsAllocator.scala:113-126 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:124\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"87976fe50ac83ba9d5dfd6fb260d5ea606c359d7c0d7b12a91d0cd0fbd5370e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SubstituteParmsAstBuilder.scala:83-96 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SubstituteParmsAstBuilder.scala:120-133 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SubstituteParmsAstBuilder.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"3be0623c5d8755f3ea48832e7046ef7725279b654d7b3cd1e03f6761dc70fe1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201314 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:271-284 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:463-472 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:271\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ca7a38e4385acac6749121f4524f26761b99592455eb548b8eeffb9066f9375"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:191-204 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:277-290 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:191\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:190\u0060 calls \u0060handleXmlErrorsByParseMode\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:276\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"84cd1e8bc132d312f75a8ae014ff589812ad40847937a4e8384ebd9e4ab18972"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingForeachBatchHelper.scala:307-320 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingQueryListenerHelper.scala:95-107 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingForeachBatchHelper.scala:307\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingForeachBatchHelper.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f66ce1aa4005a81ba020ad08cf675400344be0d56bcddaf22f819be68c7ab18"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:357-369 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:565-578 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"5528b673b2ee6d9511b0d662dfc94a03aca6c245ae0141d286c74759da02859f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:369-382 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:446-459 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e9ad0880e16eaa77b75b6bce8ec689bafb5d68f8727db0ffe26b537efe4d9f2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:290-303 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:589-602 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala:290\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"c48e09a53965702fb61b86447e1c4098e9f8cc459d1a9a18f2dc24bc80a77ba7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:146-159 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala:220-233 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"067aba18b14518869734f0b21fd76373abf22e6b338490b5cb5127cc91977cfa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 9): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:602-614 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:626-638 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:650-662 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:674-686 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:698-710 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:723-735 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:748-760 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:911-923 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:960-972 \u2014 all 9 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:602\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala"},"region":{"startLine":602}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a9a9828db445c70b7368ebbfae194ffa3f42f9d6710e16a40b598018b398324"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 4): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:786-798 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:859-871 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:663-675 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:725-737 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:786\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":786}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d3b308730280b6bc4dd5f6b72a01903e4aec5254dc8021a594e13cbf2906e06"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:464-475 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:479-491 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:585-597 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:649-661 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:479\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":464}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1ac38e456eae9c428a5cf57f3af8f9379e9adf57ed5bd3e277311c9d0a302ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): core/src/main/scala/org/apache/spark/deploy/Utils.scala:81-93 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:165-177 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:122-134 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 63 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Utils.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"bec87eb584a4fe4b21ef6afe82aaaae3afea76ea4fa2baf5429fb1abde17defd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala:147-159 | mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala:133-145 | mllib/src/main/scala/org/apache/spark/ml/r/LogisticRegressionWrapper.scala:188-200 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"4dfe65a4aaaaabe2196ab63026ad1d7d061205f4badf79f4fec101cf2cc4a18a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala:67-79 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala:160-172 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala:67\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"cef97d203ead3f070d9ea250000579b41c283fdc04cfed3c646944638214f579"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:713-725 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala:85-97 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 37 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":713}}}],"partialFingerprints":{"codehealthFindingId/v1":"bef504f3a1a97d5ea7383bbb9a8c6d4ba0dabcdfa4318157e795b09336d6b2a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1443-1455 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala:217-229 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 37 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1443\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1443}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6528e8b2ddb2f32cf11114eb5b8b76d0473cf0003733dd52da3f6d6b85240a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:553-565 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:164-176 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:553\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":553}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd9a5824bb43b2a80a24ec80be515ab6c9205023891b96118522612931896d2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:150-162 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:152-164 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"066874d5650ca5d211e70eaa9a2c25c6a87f3806247ff1e35c6faec51b9cd606"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:322-334 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:305-317 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:322\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:321\u0060 calls \u0060indices\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:304\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"379278e5dbac0265dfc7c335dfb6262edf2c0fb327bd9ab5c7fa83534d1fd27c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:882-894 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:748-760 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:882\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":882}}}],"partialFingerprints":{"codehealthFindingId/v1":"385635110bee15395ccb390d53714bff0973ab2977007e71f6279cc7515fadf4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1266-1278 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:1129-1141 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1266\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1266}}}],"partialFingerprints":{"codehealthFindingId/v1":"f704c170498a29dd2e52e11330dc5bfa74df3288748bb9ce82e65fd902bfa645"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:129-140 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:152-164 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 30 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:129\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"811740063822b85e87d6496c652c9f64d8174a7641e22dcd7f4d14ccfc4ad7df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala:189-200 | mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala:179-191 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala:189\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala:192\u0060 calls \u0060checkNumericType\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala:201\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9069e1903d7ed79c272d086e233818dffdf39b23cd0004854d638f6e73be6b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:163-180 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1508-1525 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae6b9432159fe32c0b69807688df5a5f9debf11c8697a6e37c459b062797240c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:115-127 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:118-130 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"939a83951b32d8ca38cc96e067417d21fa65dcda174ba0c160410c9474d7156b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:85-97 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:81-93 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 40 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"447c7a0d0c51a29afd074f6ecefe132cac620bbcccdabe6429b7b49de815468f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:1838-1850 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:1878-1890 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060target\u0060 to \u0060updateCondition) =\u003E // Expand star to top level source columns. If source has less columns than\u0060 in one and \u0060includeLastResort = canResolveLastResort)) // Expand star to top level source columns. If source has less columns than\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1838}}}],"partialFingerprints":{"codehealthFindingId/v1":"7172e773e735bffb23071a34408f827acbd60594713813dab2b6913b389f83a9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:425-437 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:475-487 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f721b548a2bb949c6ba417545e00496dbf877e05d1674b19981bc59a99d5113"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1835-1847 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:1924-1936 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1835}}}],"partialFingerprints":{"codehealthFindingId/v1":"a56fd99b79a3489225756dd50a4d746b73c37211a049e2d96b6508a2b32fdcb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala:159-170 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala:181-193 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fdff3d2557842195e5e7eeac05d10136dd736fa0599b22be531026e29a99933"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:182-194 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:654-666 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:182\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"d22909bb342037a4bad79b97a7c584d674715d8b9efeae88fb10003ed8f31538"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1202-1214 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1220-1232 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":1202}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb68e9a175a41fdbbd043cddc3d8e5fdb5b1ce8b2d73bcab86b5212bcfd556e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala:432-444 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:3854-3865 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala:432\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala:431\u0060 calls \u0060replaceGenerator\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:3853\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c136949732318ff30ce0b24e7593a89e707b112ea9c25742096713b80050b4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:1386-1398 | sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala:1745-1757 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:1386\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1386}}}],"partialFingerprints":{"codehealthFindingId/v1":"9efa900ede5db649beac13327fa1ceaa7662725c8bfcfff6bf80b3b01656d52e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:3927-3939 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:3949-3961 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:3927\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":3927}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a1f211c7fb23faae0771e0bf0eb6a0b3869ff38a6d09c5d698612a80c1b0d94"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:461-473 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:495-507 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:461\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":461}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf7fd61344110ec58301a0f2762ae7b68d0ed64baca912614514224c7fb0ec36"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:887-899 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:906-918 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:887\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":887}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf51a4a7c726d4ee8eb29794b45460c4925e8970a169258154d0e0c1325efd19"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala:183-195 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala:205-219 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala:183\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectGetStatusHandler.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"8160323ce49df2121d3a716dfad233518b3fe49a43d31fc9f91dd02a17d9525d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:285-297 | sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:319-331 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala:285\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"4400fa32d45c83f41ebb76a9e85a8dfe43af4fe3499315e61d1afd6f1635c087"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:70-82 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonWrite.scala:49-61 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:70\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"685a529c47ffb8f4c6e86e053d68942e2a9e803bf0515d01fb75eb3671bc30f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:95-107 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:143-155 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9eb59f386282c1385f75f40db66d8438b57c68775f47b1152c1cabc52162b8c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201313 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ColumnarArrowEvalPythonEvaluatorFactory.scala:189-201 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonEvaluatorFactory.scala:80-89 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ColumnarArrowEvalPythonEvaluatorFactory.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"05c73f71ff9131ebeb1adc3945fb934726b008f7545effe993e44d753af5a974"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:961-973 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:994-1006 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:961\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":961}}}],"partialFingerprints":{"codehealthFindingId/v1":"e60659b7275eb242b13739300261ace40d15cb083735aee2e816a1f79a2106df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:192-204 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala:366-377 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:192\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1d041dc6fe96b1a5e3d1c7ad2a31d62d0502264763a3cfa00cbae67eb469490"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:241-253 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:418-431 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:241\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b8322dec6817414522704a42f03f17ef8b71887f63951d7f18310889f4acb5e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:333-343 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1007-1017 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:331-341 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:600-611 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"17cba532497eca445a01b19c200b7bbc8c678ac2ae39c3992af2384783ec59a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala:126-137 | mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:129-140 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:96-107 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:124-135 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 40 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"41eee94845203f298804194cf458c8e5f2f6fe55010a2587a074eea70bb954df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/AFTBlockAggregator.scala:86-97 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala:90-101 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala:92-103 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 36 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/AFTBlockAggregator.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"77f802fb9c85ff5446f365e61617d58bab73543b4803d2aeaba290a8036ba274"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:204-215 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:239-250 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:416-427 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:204\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"65fbed881538435782b641ace3830a6d101ec3aa8304bfd01cb0fbe2475e2779"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:166-177 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:174-185 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff5335ac429cc55fcc2468607f2807190c3bf4eb980a21ca16468542d50a74aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala:82-93 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala:175-186 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"c20076cd90f6c81c371da49ac2b765ad13813efe3a667140d0baffb20f0c4203"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:67-78 | core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala:66-77 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 69 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:67\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"8193e91b85466adfa03c94953fa78b83ce8c25a1528b3bfc8f2a169c3d8c102a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:453-464 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:87-98 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"6840540c370f7cfea4a3e0bd06f46d16b42e646096e6f53e9189c65fd70061f3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala:39-50 | core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala:42-53 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d26f0a86ae247648b352be0d82f9433e3f72fae03d0e1efcfd93dc7f44b76c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): core/src/main/scala/org/apache/spark/ui/UIUtils.scala:300-311 | core/src/main/scala/org/apache/spark/ui/UIUtils.scala:375-386 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":300}}}],"partialFingerprints":{"codehealthFindingId/v1":"56dde87a3ed6d9e5aa98d52d79d7d2e4cea8a24fa18e01a52cd6801f730649b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:343-354 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:326-337 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"57a708cde4e5578aa3773c6f990a5a3ef8369da0df7285adbf356d83ad6db475"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:472-483 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:425-436 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":472}}}],"partialFingerprints":{"codehealthFindingId/v1":"e42b35e5f714fb31d2aee2a6a8ded2887942d378ab7bd99ca1bfd79b2152bf31"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:203-214 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:190-201 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":203}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9fcf3df8b5010fe2f445559cfa6fb916604947a40683907542dd59866b68729"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:215-225 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:557-568 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"f36168a9624579f6416d4df7c8ec157342f2d12b3aea201d00523c57fc70a684"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala:93-104 | mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala:106-117 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala:104\u0060 calls \u0060Since\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala:90\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b09a042d8c1643f68ed53586a5d2fc0504036228524f669e05f3366968ace6a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:40-51 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1384-1395 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1398\u0060 calls \u0060require\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:54\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a699914999fbc08b17df10588c46c55f9bdcdffc993b28cec429947c5e4599b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:97-108 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:88-99 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:97\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"329413aa16ec1734e9ece50aa7525eb91e83db144f09de62159ed40a03a467e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:98-109 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:89-100 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 37 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:98\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:110\u0060 calls \u0060setLabelCol\u0060, \u0060setPredictionCol\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:101\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"26883f20d2f8200cf96b82fd82add5af35ffcc17602f63eb6c4f35a92ea045cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:300-311 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:263-274 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:300\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":300}}}],"partialFingerprints":{"codehealthFindingId/v1":"5932fe6b92675fc4eaba2aee917cc6f2d5f039cbeca8fda91b0a34d70813b9b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:776-787 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:282-293 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 46 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:776\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":776}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6ce60f1ca7d5efd1caccb7ac8d7878ef7c7560814d03dde313fdb0e7af76e38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:107-117 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:205-216 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:107\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e4602015994d17a07add677728c52a2d3435b98abf49e99a6819d0e16f5060a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:225-235 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:257-268 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:257\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"90c69a40efce6167cc38809a8cbe8e6bcdea570e2cd7ecd111ddf738cd840517"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala:132-143 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/percentiles.scala:98-109 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala:132\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"28a2d478634402463a150704d58f7888931b94e55ee61e670fc7732a2f4defde"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1662-1673 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1693-1704 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:1662\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":1662}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa1ec6c6b2868c4d96551d511b637f3844e3363354b1b71f01b552ab1479b4cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala:484-495 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala:772-783 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala:484\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala"},"region":{"startLine":484}}}],"partialFingerprints":{"codehealthFindingId/v1":"f426860faa641b161ca389ef03da0120e8a9f07a4f4ea95e7c5ea5588273ca22"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201312 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala:481-490 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala:509-520 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala:481\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"56842f652f6a6810f49c0189e084feacca4ebc84c4fcbfdcd1c9192c8f167b6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:514-525 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala:329-340 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:514\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccf8432cdabb3c7ac1d747ae80d6bedd548e46d086dfbefd466b599872b50002"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala:192-203 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextPartitionReaderFactory.scala:59-70 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala:192\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextPartitionReaderFactory.scala:72\u0060 calls \u0060PartitionReaderWithPartitionValues\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala:204\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb1e0c3a33386404318495a31ef71e7b8fd5c4d077b165b38906d76bf840123a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:887-898 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:926-937 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:887\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":887}}}],"partialFingerprints":{"codehealthFindingId/v1":"83a98d6a2842e2eb69dfa69819ca5f2766cad11d4bc774099b2499e68142827b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:1011-1022 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:1065-1076 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:1011\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":1011}}}],"partialFingerprints":{"codehealthFindingId/v1":"139724eb0329e5fed6710988c68746dc8a21028a2abf9017216e319210b7b903"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:255-265 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:304-315 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala:255\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd12c7e4686733603251a0f89f76234d3db68c09829741c7245b88d5454ba3ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201312 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:370-381 | sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:401-410 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:370\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala"},"region":{"startLine":370}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d634f1b3d5436ca854bca6efaaa9b3e261e8f15bf913e15391cd313634d8bde"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala:349-360 | sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala:376-387 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala"},"region":{"startLine":349}}}],"partialFingerprints":{"codehealthFindingId/v1":"aae722b02a558abcf1d32542ba8a2bcb725908816c3d316d069813feb97c0d73"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:347-357 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:389-399 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:431-441 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:473-483 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:347\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala"},"region":{"startLine":347}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae8c0838686c6f89fc15efd8110bdab0b4ea39a5a5b92bda8c1258d788a4c2fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): common/utils/src/main/scala/org/apache/spark/util/SparkTestUtils.scala:144-154 | common/utils/src/main/scala/org/apache/spark/util/SparkTestUtils.scala:200-210 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkTestUtils.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"edee4293455248afe7a83bc36efcdfa26d27ae6213d922452f9c25b86b0dafe3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:115-125 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:141-151 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e59e1abb0eb20ba67c98f6b5a5288533787ff503552f5b41429b0823c878a84"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:188-198 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala:214-224 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 153 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala:188\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e486345fa385ab915676d34846b8691a9c9286cd55613cf8ccd3e988d6fd13e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:740-750 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala:101-111 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 37 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":740}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb56b92cfb06b2e2ba661a69f5ec9dda191e64a7edc4f651c6577c8586c7dfcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): core/src/main/scala/org/apache/spark/status/protobuf/CachedQuantileSerializer.scala:104-114 | core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:455-465 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/CachedQuantileSerializer.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9b53c06fb8f9c1a6058c9672bb9cc95236be1ddafb7f4f349345237de09a141"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:412-422 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:395-405 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:412\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:394\u0060 calls \u0060logDebug\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:410\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":412}}}],"partialFingerprints":{"codehealthFindingId/v1":"27e68925bfa4b5e385dc8cfbebbb95fbf09169f72318ea9bd55b3adc1c53236a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:470-480 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:489-499 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:470\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c266f984a83825c7d9862b73eeb23cd97e7e90fc97d5a1b7e03b550ea8e6476"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:54-64 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1399-1409 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1399\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1398\u0060 calls \u0060require\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:53\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdf062862e9a983af627a191d0ac6bdbd8c4b4cf48b460acabec9d8a3234f961"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala:189-199 | mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala:38-48 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"f591fda055b931aa9d7af462200ed04c69c1fa55e74a6ec63d3ee40076b53296"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala:231-241 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala:257-266 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala:231\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala"},"region":{"startLine":231}}}],"partialFingerprints":{"codehealthFindingId/v1":"332a527e10338ab74b3a905ac07da3580d3e03c0f63634990b5abcaa2260f078"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:779-789 | sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:791-801 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:779\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":779}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dd6f932ad69c964f2b1c06933257faff7a2ca77d148d0f4a89b138ac5e7f5b9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:169-179 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:198-208 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe78448a64a1de8612e29717719d265cab1624a2b2319dc8bbb71b206d1c5c20"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:583-593 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala:647-657 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":583}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0d0293e6516ec431119009cd16ce0d17f8322f0de8baf613bd895fadff5a5ec"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala:110-120 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlOptions.scala:81-91 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"74e373e47476ce5ee6f7564a5a33b05a102823edaae262ddcd77800f48ec3f3e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1090-1100 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1217-1227 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1090\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1090}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b03a4aa755800bfe86e6c026a5ae5f79dcf60d1b85553c2ffa9b7ad1466dfe9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201311 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:752-762 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1127-1135 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:752\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":752}}}],"partialFingerprints":{"codehealthFindingId/v1":"c08f39ea841ec540535fcd806ff66ea7cc2d5ab984c7a0219b4a3cdcac25945d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:583-593 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:648-658 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala"},"region":{"startLine":583}}}],"partialFingerprints":{"codehealthFindingId/v1":"22480fe7daa8d2d20c5a01a88a2081da1d1b68c535c05032a0638b316df6d284"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:220-230 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:270-280 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:220\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"febcfd1fe9f0fc3107639568420a655bc38d968840dc2a0118a3ab4b7debd86c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala:396-406 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:914-924 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":396}}}],"partialFingerprints":{"codehealthFindingId/v1":"1610ca870fdfa258bdc25984bb196f553ad260045236618a5f46269211af411a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala:694-704 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala:756-766 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala:694\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala"},"region":{"startLine":694}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0facfce91a6478867e462ca84e2d8d168c329c9e2b8d08dd8e5b04a50a14e3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AbstractSqlParser.scala:105-115 | sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala:88-98 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AbstractSqlParser.scala:105\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AbstractSqlParser.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"b76a3b774324ff7bb2995aaca584acd670a3be53667bbc59854a0e19f31fc3e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala:510-520 | sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala:984-994 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala:510\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":510}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ab708ea0dafe05a4b187e5ace1ef843503a8d2a1efcde396aabb955c6b4eee8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:767-777 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:433-443 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:767\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:432\u0060 calls \u0060by\u0060 and \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:766\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":767}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2d167e5e7996149ccd39fcbdd4dd8bc145af7057f83227fe3795b1647beadb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:131-141 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonTable.scala:66-76 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:131\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"18c5e2a96d484e612abfefbf0e02dcc883c9dde1a88751de596afb9789149570"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:372-382 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:390-400 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:372\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:386\u0060 calls \u0060StateStoreRestoreExec\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala:369\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggUtils.scala"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2ec6b434cbb778ad91a7d9fbedfa20c94f42f738e4be0fd2a52b8e812d6e18d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala:132-141 | sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala:325-335 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"b798660be98af9b4a76cfb66769b2202a8319a632a9b8711ce909634d83b98ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonPartitionReaderFactory.scala:57-67 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingPartitionReaderFactory.scala:81-91 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonPartitionReaderFactory.scala:57\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonPartitionReaderFactory.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"200a5ee5a6bb38c9db9a2ca5e2f3b9e77b14868349c1e219cfd55487b1644ad5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala:113-123 | sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala:143-152 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a4bd881ee1bd7652760b0415abc59f73bca4a096c30d16694f37e0e8b2fdb38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:859-869 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:1021-1031 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala:859\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":859}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba6254b84bb450be6fe999510142b246586ec8043df4345c42568767a8ba0f10"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:182-192 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala:261-271 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:182\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"108cc5116cf89aa9f2c952dd968dbe717e0dc452df6c82ea99690f25fdc7e6c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala:74-84 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala:91-101 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"e525c3ed0106cbbbddb7ed5d33a32b9033cb5caa027ab82e680545cc0b17f0b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreter.scala:179-189 | sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreter.scala:194-204 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreter.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"264c4dd6c900cde9ad2743ce1a8505f08dc8cb3fcbced4296358e27de9c212ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:79-88 | streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:191-201 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:79\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"95eefd81d1eb85de1448db3f91efbdf4aee02f59dca5006c451d10606e3f4d53"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 5): core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:220-228 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:262-270 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:480-488 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:502-510 | streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala:524-533 \u2014 there are 5 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 5 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"54a7addfa8d6fb584f0d59d416012e3dd6f3bdfe338bb8d3caab9f0497bb84c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 4): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:576-585 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:723-732 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:721-730 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:878-887 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:723\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:732\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:587\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":576}}}],"partialFingerprints":{"codehealthFindingId/v1":"73577b952091adabdbf312fa73a630ad1cfe335d1fd1894bace51db961761d36"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:77-86 | mllib/src/main/scala/org/apache/spark/ml/r/GaussianMixtureWrapper.scala:72-81 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:61-70 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:79-88 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"09f97d4b59ed61b092bb39368d75c8fe4f2a9af0c0e3e5c2a01446a844caffc5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:127-136 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonTable.scala:62-71 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcTable.scala:56-65 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetTable.scala:58-67 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 4 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 4 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala:127\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"3373a5547d043926ae91e8d348056e804f417ea64a2013427963bad042b95c52"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:130-139 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:275-284 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:152-161 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala:204-212 \u2014 before extracting anything, compare \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 38 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:130\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"32e492e4658cbecfa745a6abe1d1fd48946940c9e1f1cec417f5e1b21b0388ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5013-5022 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5238-5247 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5462-5471 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5013\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5023\u0060 calls \u0060freshName\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5472\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":5013}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b102ecba5b4ad22a89519402a1efe17ad139e1b68275eddc3bdc9a3cc7f41a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:82-91 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:58-67 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala:59-68 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"8544ce8fe5a0c69ab3755d444abca1247009eb5f0f47effb7f03f049a348aaeb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala:220-229 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala:521-530 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala:553-562 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala:216\u0060 calls \u0060extractIdentifier\u0060, \u0060getTableProviderCatalog\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala:549\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"f56410f98450cb2b6a258336c499e3a50ad16bf92590c082a58876e2660f6db2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1797-1806 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonUDFRunner.scala:121-130 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1797\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonUDFRunner.scala:132\u0060 calls \u0060pythonMetrics\u0060 and \u0060core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1808\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1797}}}],"partialFingerprints":{"codehealthFindingId/v1":"d25d3a6036d9021fcbbc6f40332729c9b91703d640eecbeaa7fafde5d67d7807"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala:117-126 | core/src/main/scala/org/apache/spark/rdd/SubtractedRDD.scala:76-85 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala:117\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbcaadcecc1411822e8feb97c32c9e3306a6e31429adfdd1f222bc82b3aa310b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:433-442 | core/src/main/scala/org/apache/spark/status/protobuf/TaskDataWrapperSerializer.scala:104-113 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":433}}}],"partialFingerprints":{"codehealthFindingId/v1":"1629b221b89df8ff3980ab9c7369d6c3ce9fa8205614efb0ad418ead3c436f67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala:125-135 | mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala:115-125 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f65f005265f8feebb388e3ffa8eaeca4753615b02d17e35a4b791b47f6be5f2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:234-243 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:231-240 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 81 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala:234\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"eab743244ae0d9587131a4eeae122a26835134f85ce34cc3592fd90b449606b5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:111-120 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:113-122 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:112\u0060 calls \u0060setBootstrap\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:110\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf219f08b1ae00a3662aa7a12f52196ed891ab542b28cf20aed8a4df45040718"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:652-661 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:183-192 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 46 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:652\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":652}}}],"partialFingerprints":{"codehealthFindingId/v1":"9453a9d994768415c62d11173fe45d60e55867a6b6ccff21f7d29697caed57ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala:99-108 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala:112-121 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"a868ce3dccd566219409a508efdaba3ee7993fd7ea8b508fbdf686aaec9c9efc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala:195-204 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala:209-218 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala:195\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c64ba0a2cb203437cd1ed7a2c6461754a437a04ad45f54718501294cc181c7f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:158-167 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:421-430 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:158\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a10bb2468f5b37d8025fb7326dd9f75d5456f154f1d82c0ec659d70207dad1c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:812-821 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:1352-1361 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:812\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala"},"region":{"startLine":812}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e29d81a48e95c681527dc0005c626c88955182b7b2c6a68542e653311151fb0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:300-311 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:626-637 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060child\u0060 to \u0060Expression) extends UnaryMathExpression(math.cbrt\u0060 in one and \u0060Expression) extends UnaryMathExpression(StrictMath.expm1\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala"},"region":{"startLine":300}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4057fe4bcb47b0dd498072bd2520e16423ce530a4e9a33f24197d54294eadeb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala:613-622 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala:644-653 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala:613\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"949ae1601bdf2d2ce7e49d67d34490422392b4a4f56c9cecf015aca6df6e0bee"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala:245-254 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala:290-299 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala:239\u0060 calls \u0060max\u0060, \u0060BigDecimal\u0060, \u0060Some\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala:289\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"f03da11ca910c48e79f1157b6f22819cec38d9e756c9b646f50115db520d0f54"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/v2Commands.scala:429-438 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/v2Commands.scala:532-541 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/v2Commands.scala"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b24feb9d8d7767dc76ddf06b58e2d674f0190f7bdd3347968cc4c8c6f8383fd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:78-87 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:134-143 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:78\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd0a31ff2cf095becb8af4f0a13d45691edb0a232129e7d8eab7d8e981c450c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u201310 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:363-372 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala:291-298 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:363\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4a31fb377100fefac6ff52067a2306e08d9913580ff914d91746a9030e84c0e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:365-374 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:229-238 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"85ee6b147457792eaa75a48111e76e19e68b68f4f02832160870e08afa8ed64e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala:418-427 | sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala:560-568 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala:418\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":418}}}],"partialFingerprints":{"codehealthFindingId/v1":"513d64e8dcb2c208fff082df152259c7a2b6346931e37616f7fe9a9bff91815c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala:546-555 | sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowGroupLimitExec.scala:82-92 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala:546\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1227ff2ec469b525cc13aadc081bfafb35debf14e4c58881086646697425d99"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala:800-809 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala:850-859 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala"},"region":{"startLine":800}}}],"partialFingerprints":{"codehealthFindingId/v1":"786fedebcec42bd5a78e17ca8ffe6af3e98b04c85ac774cdb70325b4093e8cc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala:490-499 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala:514-523 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":490}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6f21af07bf9d7a853a3cf74bd10ce89994b129ae5212173eb802a77def9a81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u201310 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PushVariantIntoScan.scala:410-419 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala:597-604 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PushVariantIntoScan.scala:410\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PushVariantIntoScan.scala"},"region":{"startLine":410}}}],"partialFingerprints":{"codehealthFindingId/v1":"370376e1bb46e68009806981e0b4990813fd4320471b99eb98d6669b725c3cf6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala:332-340 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala:398-407 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala:398\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala"},"region":{"startLine":332}}}],"partialFingerprints":{"codehealthFindingId/v1":"f686784611fb9d8efbbf09b7c7a9ce32a376958b89518274d6f248d25a6b47bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala:89-98 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala:112-121 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala:89\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTable.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"b027fc2ea15e3dab76608ccbf63df7eaddf099ddd42f5b7d0b6b9f8ee5cf2a87"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:101-110 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala:76-85 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"7413ccdb7c941fee743696b83be799b288e3dc8d976281fd30348428aa4414dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:189-197 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:228-237 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:189\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"b08b270cd893fbc25347910a15e3d431dc4106ee44c9d95d97b77992b07aa3c2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:628-637 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala:646-655 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExec.scala"},"region":{"startLine":628}}}],"partialFingerprints":{"codehealthFindingId/v1":"db711ca147ee516e5d60ace290b91896c186b909bb45f525f3c1ce7f700c1394"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:352-361 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:371-382 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e922e7eaa43ab513b33e38ef092ef7b8378494856dd2d9c44b61ab067f28ff2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala:496-505 | sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala:537-546 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala:496\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala"},"region":{"startLine":496}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a68bbdfe02de02549fb39d6cbdf0966744eaf974bac1f33e41b24378cc6040d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:122-133 | streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:179-188 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala:122\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8c81881d2125b9d30cb6d3e7b811c6eaf1bce87d98360e2f53aed4b44045d93"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 17): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:274-282 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:303-311 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:334-342 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:367-375 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:402-410 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:439-447 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:479-487 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:521-529 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:565-573 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:611-619 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:659-667 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:726-734 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:796-804 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:869-877 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:945-953 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1024-1032 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1106-1114 \u2014 all 17 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:274\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd67715b7f1bd4c2e166f3dda1cac6b536611e3a08e1c1866d8b8c55f77473bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 5): mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala:84-91 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala:81-88 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala:83-90 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/LeastSquaresBlockAggregator.scala:89-97 | mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/MultinomialLogisticBlockAggregator.scala:104-111 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"dffd9f97cd79fef8369b75346859d2de75653036cb577e4b9ffaeb5235e3c5b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 5): mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:130-138 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:113-121 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:121-129 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:140-149 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:123-132 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:130\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"881c1e43fdee620d125447e03bf05a7415fff832a01045b60db705cd4fe221d9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:67-75 | core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala:66-74 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:121-129 | core/src/main/scala/org/apache/spark/ui/DriverLogPage.scala:81-89 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala\u0060 and \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/LogPage.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 69 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"6510a25eddc8095bc80b4683714792ea8776144b652313023fd25552c82282ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18233-18241 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18264-18272 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18297-18305 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18333-18341 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18233\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":18233}}}],"partialFingerprints":{"codehealthFindingId/v1":"906ce680a91c1a702f45aacca1e8ef5396f011d97f8b5e7703c8a5bac1b4eeb2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 4): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:168-176 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:431-437 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:213-219 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:423-429 \u2014 there are 4 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala:168\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb19a237127b941734f6e0dceff2cb8597850fb347a8f089c585d55502ce27d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 3): core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:203-210 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:240-248 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:284-292 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala"},"region":{"startLine":203}}}],"partialFingerprints":{"codehealthFindingId/v1":"c784082d762412cf4a4508c8db83f3f4161d0a2cce70267db21a97e7f852226e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:70-78 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:75-83 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:76-84 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f309a01f0a5a6b9a75847f7c8d1f79fae2f3358d6d55f138d0470d6e10f6015"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala:167-175 | mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala:153-161 | mllib/src/main/scala/org/apache/spark/ml/r/LogisticRegressionWrapper.scala:208-216 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1d2268873e91e18ec152329cdc9a48853cc7af4ebea29c72ef53bb83d58ed43"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201314 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala:191-204 | mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala:69-82 | mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala:40-50 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala:191\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"e19477201ee3fb9688c63b0bd3f85868eeb29a72acea4b4bb9b38d4eec06ed23"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:1075-1083 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:1108-1116 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala:1119-1127 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":1075}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce5ef760b02e42b99a2135f87d9de190773f3e733821a9e2d41e51b6f843abc9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:1775-1783 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:2775-2783 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4517-4525 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":1775}}}],"partialFingerprints":{"codehealthFindingId/v1":"fef970e825483f21816dc4a788431e61eb0c480c9b33bc588f7cc1671a59051c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:281-289 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:564-572 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala:209-217 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:281\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"a01f20eb8e80a2ea28d0c9e7d6587988f3773f2bd0361397ec3a8e823a01702c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:187-195 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala:266-274 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala:384-392 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:187\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bc541fc8d6e81855f5112b7d127efd1998aa9be3ef3500cced3cbb07bbdf24b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala:272-280 | core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala:349-357 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f53bc166e1bc6ab04f0fd316aef99ad0885c009d90d9e6b6a2b97dd53e472c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala:543-551 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala:153-161 \u2014 before extracting anything, compare \u0060core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala\u0060 and \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 95 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaed306a635d5670d55440ffba07eab61b9204e58227dde844e6c41d799930e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 2): core/src/main/scala/org/apache/spark/ui/exec/ExecutorThreadDumpPage.scala:54-60 | core/src/main/scala/org/apache/spark/ui/jobs/TaskThreadDumpPage.scala:62-70 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/ui/exec/ExecutorThreadDumpPage.scala:54\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/exec/ExecutorThreadDumpPage.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"33838b7d33c2e19bf44962f3f3439e4c041201b76357ff34d1ac74c76f7edfff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:506-514 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:442-450 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":506}}}],"partialFingerprints":{"codehealthFindingId/v1":"483698b5c39c85dc9cdb0e7a9befda7f118e0f04f405276ce208c276f8391c09"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:312-320 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:514-522 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:312\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ab55924301080cd601b56f93dc70d92c29926a3ed1d8a32cf75307f1109e51b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:139-156 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1484-1501 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"8291f268b3f933a75b24f78e7b7271ce6db297c36bb1f8cb9b2db66df60ad693"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:435-443 | mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:398-406 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:435\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala:445\u0060 calls \u0060Path\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala:407\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":435}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5f5ca3063dd1bb9be6a7f1593f33b04263a2abaf94590f0590a3b0f34d7c334"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala:175-183 | mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala:98-104 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala:175\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"910a0be865ba048ef45fb22af1c173510e1ac0b514456fdada34d3d13799dc81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala:371-380 | resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala:386-394 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala:371\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa5a39cbaa7f709a10f2a341583e62314aa3dbdf824b898946b40c3c8cb48c0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:259-267 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:443-451 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:259\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a544e3e8c7b622ed71857a1175c395abab37a26cce6365acd6b80a5b3c49614"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:92-100 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:255-263 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:92\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"77a3a4d143f717af76f7f8fce2885171e15616e8450908de39472b4d1b977664"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1257-1265 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1321-1329 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1257\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1257}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ac0d233a131e36a72b1bb5023faed36a2c43908da425c4afaa502b14c5ee485"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1159-1167 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/maskExpressions.scala:255-261 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1159\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1159}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d1a0cd489fb61228c60b0d0fc65b59601307f41089b2012f31f7ee320bfdc9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:706-714 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:1222-1230 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala:706\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":706}}}],"partialFingerprints":{"codehealthFindingId/v1":"0175843248891ee9bb18ca6792dc25646300fea4da509a3836d4e89dcf409812"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:194-202 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:406-414 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala:194\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"04d611edfa3934b0a16777097bec837d93a7cf9894cc5e8d9c1400184aca8ee4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala:897-905 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala:916-924 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala:897\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":897}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a2ac46c0c76178cae72548b95987a1c7ef18cf363448146a4fa688b57238b29"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:589-597 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:623-631 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":589}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e58b76411800564b28261e615fe785fcd2fef3303f327ec6d9a7d6d51e5502e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:1905-1913 | sql/core/src/main/scala/org/apache/spark/sql/api/python/PythonSQLUtils.scala:187-195 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:1905\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":1905}}}],"partialFingerprints":{"codehealthFindingId/v1":"65167d469333beed6dc3f4d06fc195050f4d7af18faf5883c6135f4b27d7a8da"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:124-132 | sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:144-152 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:124\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:142\u0060 calls \u0060castToImpl\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:123\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"53d5738590c333b7933928d69fe8b958f75cdd55b754caa44531396c76c3857c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveSubqueries.scala:38-46 | sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:476-484 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveSubqueries.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"8580597e9e0c76c19eb6d842bb22997270675ca1745ef93dab96b3748838eeb9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/CloseCursorExec.scala:39-47 | sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/FetchCursorExec.scala:51-59 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/CloseCursorExec.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"7798f421236082c2f6b789d47d4f11314c4ce9cb5181232a87ec48eb3117aa54"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:219-228 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:236-245 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b45ac633210ba421735bc885aea126bfcb186430a466b81475f8e1c422a94c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala:74-82 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala:138-146 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"812696b9ad83940e4c891db2d6b34fe0e567137e08561e067462ac220ccdd69e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateTableExec.scala:46-54 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ReplaceTableExec.scala:100-108 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateTableExec.scala:46\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateTableExec.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b36ee70d5c67b4107d39927b774d959f4b3b5b01cb68044b03c99dbc9383f64"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:351-359 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:369-377 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala:351\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCTableCatalog.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"982dee8f2d682805abd7cb45cb255a9a5dcfdf1d03c0f42417d6eed6bfb1c020"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1750-1759 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1838-1846 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala:1750\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1750}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8d0cb5ff1daa12c5bd17797e751436cae9ceaee4778f07a2dbbfab41507c7a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala:196-205 | streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala:218-227 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala:196\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"391a3ea854613fb619a8c2e02b41b66221a3a639e6f6f085d3384833cf659d68"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 9): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:133-140 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:144-151 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:127-134 | mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:151-158 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:135-142 | mllib/src/main/scala/org/apache/spark/ml/r/GaussianMixtureWrapper.scala:126-133 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:136-143 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:155-162 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:138-145 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"be323a9ccf90fd62f8a927612f3336b7606caf0a49a40c5c2bfbf4a045a39831"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 7): mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:80-87 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:72-79 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:77-84 | mllib/src/main/scala/org/apache/spark/ml/r/GaussianMixtureWrapper.scala:75-82 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:64-71 | mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala:82-89 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:78-85 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/KMeansWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala:79\u0060 calls \u0060setFeaturesCol\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:71\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/BisectingKMeansWrapper.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"898d7f939d63ba280c67e6fa91042334dcd026d44216bf2716737864ef9411b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 6): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:134-141 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala:279-286 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala:562-569 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala:156-163 | sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveFileFormat.scala:133-140 | sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala:207-214 \u2014 before extracting anything, compare \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 38 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala:134\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d6f4208e551bd9c5511f4d91fb3dd2e1639a2142123a989e207ab699ebfe3d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 5): sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18204-18211 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18233-18240 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18264-18271 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18297-18304 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18333-18340 \u2014 all 5 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18204\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":18204}}}],"partialFingerprints":{"codehealthFindingId/v1":"47828f6fb5fb138b9859d04f7223dcb9478fa4696a6ba6b37ce6e35324c01ebf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 5): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:466-473 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:481-488 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:527-534 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:587-594 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:651-658 \u2014 all 5 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:466\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala"},"region":{"startLine":466}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e9dec35f45d744edb686915642d64278b59256af21f1e3f5c0f3fe9888b5043"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala:145-152 | mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:148-155 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:115-122 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:143-150 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 40 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c092f33da39943920281c0054a503010c7d7030977ab559d656f6c9a4d784a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:482-489 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:492-499 | sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala:502-509 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"947a5253ec7e3af101e69cdab5e6fcdd25b8e7c962074a83e43a3377209b49a9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:618-625 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:728-735 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:834-841 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala:618\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala"},"region":{"startLine":618}}}],"partialFingerprints":{"codehealthFindingId/v1":"62fb676c6edff6a5dce2a08a040a6bc3d90abf3e5919960adcab5a6bf60c9b27"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala:89-96 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala:111-118 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b8b13fd422d38ccf8687753a67667d518919d399c40f1fc009c048ac0d161c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala:78-85 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:103-109 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala:78\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala:87\u0060 calls \u0060put\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/PythonStreamingSourceRunner.scala:110\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a66f5115b394ca9c4f8a61c83082941d6fc6f8c22a49d28c3c8a946b5f18b1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala:325-333 | core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala:385-392 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala:325\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"16def5fd204b5b8d7707959148ae5d5db21759d653cb47b1c9bc61ed2e09f549"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/scala/org/apache/spark/partial/MeanEvaluator.scala:48-57 | core/src/main/scala/org/apache/spark/partial/SumEvaluator.scala:73-80 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/partial/MeanEvaluator.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"47a01456bd16eb82164e952b1d6e875ab88c6d9656e398f110a26ea771b3dedf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala:618-626 | core/src/main/scala/org/apache/spark/storage/FallbackStorage.scala:180-188 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala"},"region":{"startLine":618}}}],"partialFingerprints":{"codehealthFindingId/v1":"8143c7eddb2909bc88b8254b39266bc36d075ded9cdde11616db65110599e443"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:657-664 | sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala:443-449 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":657}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee94412a01077a9e7e93f4c8067675bc39a6dcc42e05f4542ad597385c2fbf7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:712-719 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:642-649 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":712}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd40797e8a60d607efb48a1b552e8ef1451b355dd94cda4c2f6a78cd35de9465"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:367-374 | mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:320-327 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:367\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":367}}}],"partialFingerprints":{"codehealthFindingId/v1":"51c1f7a807a83bded5657c5a548651665f27482d8be66bf1cbb9fbffcb3312f3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:516-523 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:397-405 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1f78681f3bde237a6824529f0dd2208689f9c41b52558d0c827a2cc9d6bc6c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:507-514 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:656-663 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala"},"region":{"startLine":507}}}],"partialFingerprints":{"codehealthFindingId/v1":"190da2538f6cc6efd009fa3cf1878e50c1d5d5f61d25c16e11168e1713da5db7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala:91-101 | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala:1436-1446 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 133 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3e3dbf1a32b11cf71d6f6d029587e52284ec60f223aeeb92975523d3d36de3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:122-129 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:142-149 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:122\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a13aec41faa5296d3dcebc3d7f0112906adfdac0392cdde0171f3bb91923fc4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:591-598 | mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala:130-137 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 46 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala:591\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"55307ef2680ccd86e2f75733a27c14e2ec6106e0c757861bdf2b83db6e0b5baf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala:145-152 | mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala:180-187 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala:145\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"22d4084892f4e5f0476b7e6796847577b16204de3c612db9cc24d2c68b335af9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:307-314 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18236-18243 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:307\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"16d981b3e9eccdc334d487c497283429520bf0ab8f8aa94a55aee35b9b8b67ba"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:339-346 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18268-18275 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:339\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":339}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea749e5d8c3b844b32f45d6ed25d8846e7e88b4ddea4ac7d71d8d3b7091bef71"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:373-380 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18302-18309 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:373\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"57337651bf01f242472171fc622ac4f1b70773a66cf63656d450d41afbf907a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:409-416 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18339-18346 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:409\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":409}}}],"partialFingerprints":{"codehealthFindingId/v1":"dff70841320298be1613b4bfb61404a9b77561342cf34d138bc310a6f912ca65"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala:230-237 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala:404-411 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e34c58e411690b07436e2751a52918610fa3b9a5b40c9efd1c548fea0f0c6f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:121-128 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:138-145 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala:121\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/v1CommandExtractors.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cc0cc9627a6e40226e16cf419eee43a10d8d23118b9efd34eb4f6f8fdae2ac3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:1766-1773 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:2891-2898 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":1766}}}],"partialFingerprints":{"codehealthFindingId/v1":"f15df0977c30d9b9e07013a4f40257dc4d14a12479c44930470ca31be9b88d3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala:351-358 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala:279-286 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"7dd1e2bb1a0a709ca58e09c3ba61f441dbd1a98eb19ef5226a0a01c096ba55ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:339-346 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:352-358 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":339}}}],"partialFingerprints":{"codehealthFindingId/v1":"e51117720ccdfd54304bdd3c077e4a04eb9fe50e45c99e2f239f58d09dbbe0c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:106-114 | sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:123-131 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala:106\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fe3faef0f21116a662a6d970476740d514fba2eb4fb93ffa436b964fb83971d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:103-109 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:218-225 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala:103\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Exec.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"daecc6bf0dc1cd3088a36ebf39d499597a9beaad75a99e0e82fb950e3f0c8171"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:541-548 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala:1021-1028 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RangeRelation.scala"},"region":{"startLine":541}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8b99c4347cc5451db1022d871202693962d86228558ba1f18685c764ba6a59a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:723-731 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:738-746 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:723\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":723}}}],"partialFingerprints":{"codehealthFindingId/v1":"5abe8a45f58cceb7e47461cf1dccb2238b0038b17845fb76bba02e5a77a284a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1248-1255 | sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala:1468-1475 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":1248}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a775f101e251d6f94c06c3439f443b7f432ece4ec9232c877abda6a1cefa39e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:304-310 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:362-369 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala:304\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SqlGraphRegistrationContext.scala"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1a5412f0f3536df98a9fb4610466a238758decc33cfbb22b9a18bc255a10f7c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 20): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:306-312 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:337-343 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:370-376 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:405-411 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:442-448 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:482-488 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:524-530 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:568-574 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:614-620 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:662-668 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:729-735 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:799-805 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:872-878 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:948-954 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1027-1033 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1109-1115 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18235-18241 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18266-18272 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18299-18305 | sql/api/src/main/scala/org/apache/spark/sql/functions.scala:18335-18341 \u2014 there are 20 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 20 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"66099d7de33c2bac6a63d02e0b5d55a3ad49b5850cc662a74973b5701fee6403"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 9): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:575-581 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:621-627 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:669-675 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:736-742 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:806-812 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:879-885 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:955-961 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1034-1040 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1116-1122 \u2014 all 9 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":575}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0068d1ee792a34fab1a33c1331cfecd8643c2dc35aabc4251a5c7e82c8d2f98"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 8): core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:423-429 | core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:438-444 | core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:453-459 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:462-468 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:477-483 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:492-498 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:507-513 | core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala:522-528 \u2014 there are 8 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 8 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"96c6948daff19ef4246606c98f27ef615a2e9d7fffa1224e6be48f2ac5a52f52"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 7): mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala:144-150 | mllib/src/main/scala/org/apache/spark/ml/r/FMClassifierWrapper.scala:166-172 | mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala:147-153 | mllib/src/main/scala/org/apache/spark/ml/r/IsotonicRegressionWrapper.scala:114-120 | mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala:142-148 | mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala:152-158 | mllib/src/main/scala/org/apache/spark/ml/r/LogisticRegressionWrapper.scala:207-213 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/FMRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/LinearRegressionWrapper.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 40 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb1794d3a243d1c87b6486f0b601c73516682804c33a7071dbe688337dbdf0da"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 6): mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala:126-132 | mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala:109-115 | mllib/src/main/scala/org/apache/spark/ml/r/GBTClassifierWrapper.scala:133-139 | mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala:117-123 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestClassifierWrapper.scala:136-142 | mllib/src/main/scala/org/apache/spark/ml/r/RandomForestRegressorWrapper.scala:119-125 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeRegressorWrapper.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/r/GBTRegressorWrapper.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 42 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/DecisionTreeClassifierWrapper.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d96b0cf9c97ba2164053f1e46c142c19ac9210740317be5657c44c76dca6a32"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 5): core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala:115-121 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:204-210 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:241-248 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:285-292 | core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerPage.scala:102-108 \u2014 there are 5 copies across 3 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 5 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"47820e3a497c7bd83b0eda0ecaa5792034d09538aec5b7ab8abf677b9d0d3521"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala:60-66 | mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala:60-66 | mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala:60-66 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala:60\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"1037bf41b9b4ae49f2abc64a2dc81296743eea05ab7a927f9fb7b7dc6d071221"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1222-1228 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1260-1266 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1324-1330 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1222\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1222}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fe540b3d1cfadf399bc39b22e78f2ac7a2522d99e21aeb33a6b0e14825e48f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala:90-96 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:56-62 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledJoin.scala:243-249 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala:90\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala:98\u0060 calls \u0060withNullability\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:63\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"134f2ed0bd3f8923f7549023e551dc8b1599a8beafa24d3fa58b169f7c779844"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:160-166 | connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala:201-207 \u2014 before extracting anything, compare \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala\u0060 and \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 90 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:160\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a4ea04acf42816e5b9bec713b544c13c0f7c69e8d5b0f52b6e2188c6b5aabcf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/Utils.scala:72-78 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:156-162 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/Utils.scala:72\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060core/src/main/scala/org/apache/spark/deploy/Utils.scala:70\u0060 calls \u0060File\u0060, \u0060normalize\u0060 and \u0060core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:155\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Utils.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"eedd51ec860432f6e51ffc255f8e11ee49ef6854210352b710b14810a31f1db2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:340-346 | core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:411-417 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala:340\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"84fdd34a5edc29c2c4bc41fcfccfc5b8523aabbcc28c4186ec698ff7c2fc2eac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:156-162 | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:206-213 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala:156\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"c50390e09b6ad5dda1cf2bec0dda0679c7d98f6e3b0ec2c943bb78968acbe42a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:470-477 | core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:487-494 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:470\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:495\u0060 calls \u0060setClassLoader\u0060 and \u0060core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala:478\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"d277b223d4542ae1e779f8fcad579165ae7f79876e14c0f7773875dfb53e7c75"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:210-216 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:433-439 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:210\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"b08344c0fbc223f3e975446767729dbde833585fb472a76745a3dc8181db07e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala:204-210 | mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala:279-285 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala:204\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"e20a5a7370353e72d890d51378c66eefb739a3721ac463767589d01ed094efdd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:291-297 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:254-260 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:291\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"88e64b9bea2aa9df115807ac07db06cd7b3141916f6f8c287a0da59570a48ee8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:419-425 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:367-373 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"158cda9e9810397bec138855d327f1272d0fbfc0bdc6bf12656f3a5c5dff8f9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:175-181 | mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:210-216 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:175\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa3896a6219c687ec9b058ec4b92df580810b5d33b68dd8e5718c0d6354dbf6e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala:74-80 | mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala:51-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala:74\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"45b962a376ef2958f0ffefae6a6c7f7a847e41737e051798afbdeb649eb9b179"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1041-1047 | sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala:1123-1129 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":1041}}}],"partialFingerprints":{"codehealthFindingId/v1":"98c5cc7f87fe761450d4d2e9dd5fab9860166416441b657a6b16ac40104f3132"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6\u20137 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:123-128 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:148-154 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:148\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3c664f55e73b382edbb9c7972bfc7e8661de16499375fa6db7b598123d69a7a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:4825-4831 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:5470-5476 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala"},"region":{"startLine":4825}}}],"partialFingerprints":{"codehealthFindingId/v1":"9386de2705bff330d2dbf0ab0b7d7ad04fdb75d4b85f26f7212537247ed4a3e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:285-291 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:417-423 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:285\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"277b0c16bae50bf54112a175274d6f1afb956fb95263de4740acbf04af1acd3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:2877-2883 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:2889-2895 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":2877}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cd5d0a3c8c1fe6087c2ffd519955df04f2cced68c88f6068770fdb6c8e0ebe4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3646-3652 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:3658-3664 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala"},"region":{"startLine":3646}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e287f33d685870bf09f7ba6a1f27bcb476e9d543d0fa63c99618718822772bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStateHelper.scala:111-117 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStateHelper.scala:127-133 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStateHelper.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce3925d5b27a16072c390ec7a84410c38777022e0f690dab07cb4f6fe00717c2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:256-262 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:292-298 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala:256\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"6334f66f2585d22352a5da429a38e1412a4e4d646d26e36d786e880eb8d9d705"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala:71-77 | sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala:134-140 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala:71\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"eab6999ed72d89f2da13c55f9db963ad3aaa6a3d1ed3744a93b644491feaa280"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala:801-807 | sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala:1212-1218 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala"},"region":{"startLine":801}}}],"partialFingerprints":{"codehealthFindingId/v1":"aca608b2db966cc71d75aa3ac4f72bceaad054830366c549042b7ee3aaede64a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2518-2523 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2556-2561 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2592-2597 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2629-2634 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:2518\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":2518}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbfe0a24226f0b7c20cf4444ece9d3cc633abcf5d197b87320625a2a5581a1b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:421-426 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:490-495 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:421\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"89a2a17cc43783d3fbed73162f51a6c184dbf211f9a9dbdd5d7516f302282726"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:447-452 | core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:516-521 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala:447\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":447}}}],"partialFingerprints":{"codehealthFindingId/v1":"59d3e3763d631ad37c93f6e0395a99fd445465989fe053dd6ebed216e0cac30a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala:52-58 | core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala:55-61 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala:52\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/BinaryFileRDD.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"59960e717886b7869a6081625c84665e5cda2741bcb497009ba29744ae05a571"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:2792-2797 | core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:2872-2877 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2792}}}],"partialFingerprints":{"codehealthFindingId/v1":"73c9438846e2601e10ccfa6d65f54ded2188aa048304be35718211cfaa7e204d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:640-647 | core/src/main/scala/org/apache/spark/status/protobuf/TaskDataWrapperSerializer.scala:95-102 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala:637\u0060 calls \u0060Date\u0060 and \u0060core/src/main/scala/org/apache/spark/status/protobuf/TaskDataWrapperSerializer.scala:94\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":640}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e5d24a7636c886697d84556c6b15c7d0c874964b08d854b892011969f108044"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala:70-75 | graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala:112-117 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/ReplicatedVertexView.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"96bb13507c408c13e2cfbab029f7801bf77c3674afd652203dd934e4614e3908"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:262-270 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:264-272 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"5eda9e585ca26bdb8c8a07af382a78ff2e03d1846371ef56c3de51de6bb86a98"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:485-490 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:418-423 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"726b997a8839058195855d384994b84551ef8cfaddf97ee3b2b15a3d357d0292"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:203-209 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:526-532 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:203\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":203}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c4c1e3feccaafc22f9cb7a76d66328b38b47fc1b69b4690c473dd6f12421cc6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:301-313 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:552-564 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"8cd3afb3bc1463f52db8257c48de1db62fd1029a093eedb49cca7f02d436f15f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:958-970 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:301-313 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":958}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6ffff39638729cf15bec2acd01f575b72470259b54c4bb6b14b99e8bddbe52e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:163-168 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:148-153 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:163\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"a822adf1c5d553128fd446105c42fda4b9a0c62e7a1a17b9523f5c24b237211d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:122-127 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:165-172 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce364b230ae9552a573eccbae898ed07772306c6ce55c3b912eb25d786f48d72"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala:42-47 | mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:65-70 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala:72\u0060 calls \u0060setDefault\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala:48\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"e08e00b67f079dc9e08a588a9d1561485045b62b651158d52cd9baa177275b9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/linalg/JsonVectorConverter.scala:32-38 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:435-441 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/linalg/JsonVectorConverter.scala:32\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/linalg/JsonVectorConverter.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"76b90a1816bad61311396b01920b8b3d72df6dad4354de0e61792b2f3ece1df1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:227-232 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:265-270 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7e22394b0503a5c946d0edae0afdd0326218144fb259eae7db0c1864105e0ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:186-193 | mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:221-228 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"af75bd21d1b7515cc68f757bd4be49eec02f38a6fece17b90dd5d1493cc49030"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala:69-74 | mllib/src/main/scala/org/apache/spark/mllib/pmml/export/GeneralizedLinearPMMLModelExport.scala:55-60 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala:69\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"53f44f44446b255242e15d4bd9271332b27cfcfe740f0ba35619572e0b42fd77"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:575-580 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:607-612 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:575\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":575}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f4770e0195b258fee90ef65291b88c20b4b398b45abe857b10b0874b2753748"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/datasketchesAggregates.scala:175-180 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/thetasketchesAggregates.scala:235-240 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/datasketchesAggregates.scala:175\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/datasketchesAggregates.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1d85c21ddb464e2ced7148c89e6c43ce65ae254e9af06a33b3856fa0f82b258"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala:248-253 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala:255-260 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3dc5a343382a24715b6ea225a89956c45893ebbd3535b44d16ae28b317b77ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteWithExpression.scala:56-62 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala:317-323 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteWithExpression.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"640864e14601ddd5e0a7cbf108833889b78704805146b1fe5f38d6ea05e63c13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:2033-2041 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6298-6303 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:2041\u0060 calls \u0060entry\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6303\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2033}}}],"partialFingerprints":{"codehealthFindingId/v1":"2124deabfaa4cd890aa1e732b4cfc318f223e699125556cbd5356ea786a51a06"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6660-6665 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6756-6761 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala:6660\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6660}}}],"partialFingerprints":{"codehealthFindingId/v1":"53a73754e589cd94bf2f0b2d20000252b3383c494acd54dc63501bce68a44c4c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:829-834 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:838-843 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala:829\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":829}}}],"partialFingerprints":{"codehealthFindingId/v1":"32e8fa5dc65ef92852b48e16fdc94d0cb5646a6c71b8abff9477dc05c7b4b773"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala:86-92 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala:192-197 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala:86\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"9198c533e551de34fa2a63dd0bdc1b7c06eadc027d2a90313e29d71015a2bb3f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:153-161 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:241-249 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"097f3f7587b3e5dfb475f3ec3c73b1d36a62a650eb90e1338f1236c348c24d96"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:411-416 | sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:499-504 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala"},"region":{"startLine":411}}}],"partialFingerprints":{"codehealthFindingId/v1":"09038952c9ffe0a180cafcf73599c6665b34896fa9bb43eb30abe66790a9bbad"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala:377-382 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowSerializer.scala:474-479 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala:377\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"81ed545933306c976f0b3e815de8902c56b4a181d1d53adb3c0eeb3464c77c25"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:305-310 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:168-173 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:305\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5f791e221b33f95d7563e6736e447c41d9874ae4f2ca1bb54e3cfdc5c31d554"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20136 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:141-144 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:170-173 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:238-243 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:293-298 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:141\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:169\u0060 calls \u0060create\u0060, \u0060getOrElse\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala:141\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinEvaluatorFactory.scala"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"74d4a5c965b59bd5b83d6d8b0892adf5dbf5c91f7f1ea2f286c54e4ce17d1eed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala:254-259 | sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala:602-607 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala:254\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala:600\u0060 calls \u0060fromAttributes\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala:253\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/objects.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c19c37c79f39dafd214224f9442db387bfc8daf7d33c125494c97384780ff28"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 5): sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:127-133 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/ColumnarArrowEvalPythonEvaluatorFactory.scala:219-225 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonEvaluatorFactory.scala:103-109 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonUDTFExec.scala:78-84 | sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonIncrementalAggregateExec.scala:356-360 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 5 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:127\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"1947a6d8963b207c96a1a292ef27b3b7839993eee1ee91871c77e2eaf8cca127"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala:250-255 | mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala:158-163 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:724-729 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala:250\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0662a1fdd18cbeb53c1033c9e7171049e6147ac953275f4d171fb0a87cc61e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala:126-131 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:357-362 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:146-151 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"95af5553db7b45130a6709ac513ae560a3a34c46f2354438608da2302be9d026"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:184-188 | mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala:219-223 | mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala:83-88 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaf731818ae9d220162e686b8758888633cbde24fc18ac2f838be1ba20fddec1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1158-1162 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala:1294-1298 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/maskExpressions.scala:254-258 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":1158}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf93bf0ba822d88ec4b53fdf04c44aabc9fb2d6997192c2a4c22fcca0a307b90"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:262-266 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:191-195 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:262\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6fdf95235db64233272f7da1f1b1507436bd6434aafef0afe90416654f4c328"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:338-345 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:348-355 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"833978c3f9d9f0a15c9a21bb930cf01fb92df6c4e5a5d21a2dbf14bdab9d0bc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala:102-107 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala:109-114 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala:102\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ab35685dcc370c10b85751ecba710bde1c7f7a554dade0920ffdba952684859"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:39-46 | core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala:65-72 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/ui/LogPage.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"a318b3ba82ec18a8a793ee3a0225044e12d82e2e88580c6b1d8a0dc910fab051"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20135 lines \u00D7 3): core/src/main/scala/org/apache/spark/ui/UIUtils.scala:220-223 | core/src/main/scala/org/apache/spark/ui/UIUtils.scala:237-241 | core/src/main/scala/org/apache/spark/ui/UIUtils.scala:258-263 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/scala/org/apache/spark/ui/UIUtils.scala:237\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c8fdfdface140e17689262f38048178e99072ff7108662425fe4f87ff091613"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:1065-1074 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:926-935 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":1065}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c41ad2b229ae550dc5ac781e9d7832dd1ac8a43558fcd8b662acb8c52990c0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala:72-76 | mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala:117-121 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dcdf8562d13c958fad1faee00bca84049f323f526f0255882b5dde2328f45c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:195-205 | mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:240-250 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:207\u0060 calls \u0060Since\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:252\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"af507fd4db3c9f3dc51b4b35455a22cbfc6fcfc789a42190e94eae7d521dfe4a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala:827-831 | mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala:930-934 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala:827\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc2387f49145bf55907f00d08ca84774483e7b3e7d5af8034c41fe33d27db269"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:45-49 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:45-50 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"7078d1c0e94beae6f0592154424db13204b1eb76665aa2b11772ea54b592cc4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveChangelogTable.scala:123-127 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveChangelogTable.scala:145-149 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveChangelogTable.scala:123\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveChangelogTable.scala"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d99d7117198bb36b373422e76fe3328b58a3475163a00afd2b0048530835e3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveInlineTables.scala:44-49 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveInlineTables.scala:57-62 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveInlineTables.scala:44\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveInlineTables.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec3405c16185b5ce0d5884de4646dd85ef64c90f83944990726c4395a1eb6654"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:910-922 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:942-954 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala:910\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":910}}}],"partialFingerprints":{"codehealthFindingId/v1":"df4c1fcbf5deb240b6eeefc0bd85d62ce6e139b99ec3d2bf202faa608ded3f3e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1187-1191 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1222-1226 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala:1187\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1187}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfdb1070533221783eb08d1af5ac124858ea37ad0691ea86293d93a3221b4b38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:479-486 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:808-815 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":479}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ea57fb147d21571d240ec1cbea941b9080af80dbc631de6f6c9dd3026e7a5a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:291-295 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:617-621 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala:291\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060child\u0060 to \u0060Expression) extends UnaryMathExpression(math.cbrt\u0060 in one and \u0060Expression) extends UnaryMathExpression(StrictMath.expm1\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3c3d6e926d67ae02a214a0dcae90e051d808a59df565312228976c038f1e2f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:723-727 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/SparkShreddingUtils.scala:809-813 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:723\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala"},"region":{"startLine":723}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ec156687d8bab6abd061f3f3bd78c7809a8426629a01cc3abe4a1c0ce88a7a5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:602-606 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:654-658 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala:602\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":602}}}],"partialFingerprints":{"codehealthFindingId/v1":"80574f102a23d5013944582c75e737d90aa126abb14a4d9829e88939465c0fdd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala:380-385 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala:390-395 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala:380\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalUtils.scala"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"f34600b020d23dd6b9a3a37fcb0a44943650cb008a38448da55bc57e6315fb72"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:450-454 | sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:560-564 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:450\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala"},"region":{"startLine":450}}}],"partialFingerprints":{"codehealthFindingId/v1":"3211423247dcdeaf818bf13555a33b627faf399d47987772be62c316cd5cf401"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/Serializer.scala:68-72 | sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/Serializer.scala:87-91 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/Serializer.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"99fd889e5fe8d27569fa4c143f82a530afd3abbba28138ac27ead32087add8bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:416-420 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:444-448 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala:416\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"d138a568092b9d06d38e0756e56a3330fe58691a357edc13df5323672bdba3b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeTablePartitionExec.scala:76-80 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablesExtendedExec.scala:167-171 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeTablePartitionExec.scala:76\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeTablePartitionExec.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"65de08680df37d66209863e7406f6af89e88b7509b744b681d783c320d22a728"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:542-546 | sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:559-563 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala:542\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastRangeJoinExec.scala"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b55d2dccd0b5b857e79b6c989a9dc410530ed4badb7a6d21fb23b279616f615"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala:701-708 | sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala:710-717 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala:701\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala"},"region":{"startLine":701}}}],"partialFingerprints":{"codehealthFindingId/v1":"f598dc9f0343919346cfa47c9d25bd91994f8da0ed8ff20ab5e9fbde175faed1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:477-482 | streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:502-507 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala:477\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c60a87837e0f445bbf2d809957c94f8c2acf731ad690c5818a3d7935ef69b06"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:457-461 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:508-512 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:457\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"35c0bd6ecfbf9a728cc54c0cf5f90be8a75939ebca743e6b0c827355be4a92f0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (43 lines \u00D7 2): connector/spark-ganglia-lgpl/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala:51-93 | core/src/main/scala/org/apache/spark/metrics/sink/GraphiteSink.scala:43-102 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060prop\u0060 to \u0060String): Option[String] = Option(property.getProperty(prop)) if (!propertyToOption(GANGLIA_KEY_HOST).isDefined\u0060 in one and \u0060String): Option[String] = Option(property.getProperty(prop)) if (propertyToOption(GRAPHITE_KEY_HOST).isEmpty\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/spark-ganglia-lgpl/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f72a33dfcdaba89d6d3c1c325a2db0be1b7dc7b34583957f450a53bf89d2c13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (41 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/classification/StreamingLogisticRegressionWithSGD.scala:61-101 | mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala:58-117 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/StreamingLogisticRegressionWithSGD.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"c190291d13bb77aa994f50769c26e74428cac7e497982cdc36b4222a9bad4f08"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLImplicits.scala:30-39 | sql/core/src/main/scala/org/apache/spark/sql/classic/SQLImplicits.scala:32-41 \u2014 before extracting anything, compare \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLImplicits.scala\u0060 and \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/SQLImplicits.scala\u0060 as WHOLE FILES: 90% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 1 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLImplicits.scala:30\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLImplicits.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8552cc5167403f18ce024ca4f80151eee48cb18b13be5fb04fc3a7be6e002bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroDataToCatalyst.scala:158-172 | connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala:135-152 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroDataToCatalyst.scala:156\u0060 calls \u0060take\u0060 and \u0060connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala:133\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroDataToCatalyst.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"42eb3ae8a70be635b37965b60d709a71f227518d4c55c690db53879350c268ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/scala/org/apache/spark/MapOutputTracker.scala:671-677 | core/src/main/scala/org/apache/spark/StreamingShuffleOutputTracker.scala:169-176 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"04cdd096047dfa27a1c5edaaa45176dadd309ddbd1872d97c8572d698ad19358"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): core/src/main/scala/org/apache/spark/SparkContext.scala:3544-3556 | sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/ProtoUtils.scala:43-57 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":3544}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0fac58c73616f7d87d576775cd03bb3f8c5414cee750e2c03fc378b23aa353d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala:1172-1180 | core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala:120-128 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1172}}}],"partialFingerprints":{"codehealthFindingId/v1":"630250433cac156ec247e883040d23598ee44534f7b2fb65d31ee2a0809060f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala:60-68 | core/src/main/scala/org/apache/spark/status/api/v1/PrometheusResource.scala:112-120 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f92cf1299b45b3bb1e65fd7c98f2754936e81f3e00388d14f5329299878b41c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeRDDImpl.scala:32-39 | graphx/src/main/scala/org/apache/spark/graphx/impl/VertexRDDImpl.scala:42-49 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeRDDImpl.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa862126f9d208d58669191ee146929498a2c432ce23e1ffb592172ef7b447d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/impl/Utils.scala:91-97 | mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala:555-561 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/impl/Utils.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"b688e56d17e1d5129ac59b291fe4f879dea1749d3f5104b73920593189c2a5dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:40-46 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:42-48 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"1009fab0caf7da7c839b8ebc9ccc88fb783a6576579f7d13bc1a7cf7fa9ed960"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:196-204 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:198-206 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"065afde429faf1076aed357912c7e9251665f56cac45cb9189c6e14fcda7f056"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala:209-217 | mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala:211-219 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala\u0060 as WHOLE FILES: this scan already matched 26 separate duplicated blocks between them, totalling at least 479 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":209}}}],"partialFingerprints":{"codehealthFindingId/v1":"19b7ee9c2fd0756b7f0eac6ec06ca4702955845219e7ca42ff1d5830833077bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:56-62 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:56-62 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1eacf73da114143a6f3a7efd015915650847e17538d2808ce30b7597b1d7080"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:105-109 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:105-109 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd098223886fb48f7b85a598fcfb05650a680eba2952554aea7c01ad0eb05205"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:123-127 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:123-127 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"d52851a7c24d1417a68fc655dec460d60efc2d02c66008ee818a1abd6c561e41"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:353-360 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:318-325 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:329\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:364\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":353}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0901e5df3f872a625e7e96ae3799345062afccd6f7b7a37ebc57df38888118c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:366-370 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:332-336 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:329\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:362\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e1d039a1d35960988ccbc2dbc51e162d735d5edbc5113970d95d243c332b0af"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:381-389 | mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:738-746 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:348-356 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:669-677 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:679\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:748\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"005e0f8995087d73f55c37d4567897a7eb48606370a327fcf548e2bf16b90ae0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:545-553 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:482-490 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec187535301b1a1e26e21ced99e1d1ffc74db612ca989f92b7677c95e1c691ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:590-600 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:527-537 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":590}}}],"partialFingerprints":{"codehealthFindingId/v1":"d671dc918bd245993050a2c3dff86ebed67ccd4687b94137162759b59a659e0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:697-704 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:626-633 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":697}}}],"partialFingerprints":{"codehealthFindingId/v1":"88808fca55239e0bb53c3e9274f139326785d70bfc437f134252ee6249505cd2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:721-729 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:651-659 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala\u0060 as WHOLE FILES: this scan already matched 24 separate duplicated blocks between them, totalling at least 388 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala:661\u0060 calls \u0060Since\u0060 and \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala:731\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala"},"region":{"startLine":721}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a5690f5796ab18ab11b866efa80bdf3b34f0536d1863f221edfd97178b7ffba"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:291-295 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:405-409 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5b39745b0d1781099098a5e7b5aa2d74e7c1627168948e8ecada93b85fc2ab1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:660-669 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:812-821 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"09bd4a55c7730c0df85eced33dd12909124cb72312092b77b9e3d742fbec05b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:677-684 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:830-837 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":677}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c0c282dc5237edf7af324a5434f6872a67e4460fcc00132a0269eadbceb3dcb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:858-862 | mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:1001-1005 \u2014 before extracting anything, compare \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala\u0060 as WHOLE FILES: this scan already matched 17 separate duplicated blocks between them, totalling at least 331 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala:864\u0060 calls \u0060getSparseSize\u0060 and \u0060mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala:1006\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":858}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee56c752f4d22525212e06530f615b1b7139d60060a89077d82e726725928d67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 5): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:258-264 | mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:302-308 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:302-308 | mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:269-275 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:233-239 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 30 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:229\u0060 calls \u0060Since\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala:299\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"d34a45c3ffad31427f8f150b5e49aa9cc9bd2de8813b6c789884ba8beeb45f81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala:287-296 | mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala:385-394 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 30 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b146002dc6bb1f6c7587dbe08795a5d7c18d47f6f176fd3b9f45a7e9fd204f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:242-249 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:454-461 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a08e4e918b649bb9e03fcb69550d060c8805f386720469ddd6f5cb46bfdf304"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:325-334 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:499-508 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e960f00b5f5f05112dcc6aabcb37b480f64dd6b44c0b7c0308d9deabd24fb93"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:362-369 | mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:484-491 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1400-1407 | mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala:376-383 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"5009b47c4e74366c8a4312f8608b7c278f456fee0c66ff9f8e565963596853ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:371-380 | mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:493-502 | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:1409-1418 | mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala:385-394 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 66 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"231b1333baa099a2f2b38c4fd1e08cde60d9e10dfbb020d94479e841d00e2a9e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:391-396 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:528-533 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"a52f0eaa5dca617e7b765a16b3411fe42c6e50475706239b9703eba7d2fd84e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:398-404 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:535-541 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"f25cd626db48d82d6bc6fd76cf168f00133cedc1766905bd8f93fb56a160fb80"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala:416-421 | mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala:553-558 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7f28604458547f6ce2673b5bdd9dac4026618165cd1e1c7e7e9752498daf2e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala:179-184 | mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala:361-367 | mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala:448-454 | mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala:660-666 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 4 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"b41e3260287c6b6fdcf35c9ed2017bf61d096e13a007ee38e5f0f92796a0c4e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala:130-137 | mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala:175-182 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae1e82e346ae15b24dcfa46b42550fcef86615dae131b87080a69245eda2f21d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 4): mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala:237-241 | mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala:223-227 | mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala:309-313 | mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala:401-405 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"a638a5bfaecf3345653a6c2bab2bbc3ddde174ef5c8e4da32de3a649c6814137"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala:190-195 | mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala:372-377 | mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala:210-215 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"b025bb95c19eadd278cdc4163ba80924df7175b386cc48aba7d91dc7c79ca9a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala:98-102 | mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala:116-120 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb541697c2376d668a073f90016acee7bb4811f2b7b0526050b449e5d0318239"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala:74-80 | mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala:75-81 | mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala:126-132 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala:72\u0060 calls \u0060setDefault\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala:123\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a67959234b945346ee2b232d44c4136eac57bff94050baf71e84e3124e2cf7b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala:375-380 | mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala:325-330 \u2014 before extracting anything, compare \u0060mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala\u0060 and \u0060mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 39 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"5752dd74acb7b4325d876244a5491df5fea0af2a8048835be3a08cbf860e937f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala:156-167 | mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala:151-162 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"44976016817e8b1114eedb37852b4365a6133be13a34068b5edc69c57e1349d9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:81-94 | resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/StatefulSetPodsAllocator.scala:68-84 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala:81\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/DeploymentPodsAllocator.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0053e922e866ade3ca1c313b3cd55a4f1b1cdca387eec0358b62d0edfc52247"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrors.scala:182-187 | sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala:4149-4156 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrors.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"bffafacc81be5dd52985c7cde4b64b92a676da4f5ea788e084eaa56133a2a8c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala:158-162 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala:196-200 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"03845b51a844ffcdf28538660aeeaa9fe2aa447fee52efcf25e85c78893a6ff1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ParameterizedQueryArgumentsValidator.scala:53-58 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/NameParameterizedQueryResolver.scala:168-173 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ParameterizedQueryArgumentsValidator.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fb2e92794961b7fda155cb69c43c9b9cf2abf98e4f57bef8e9671f895549252"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SessionWindow.scala:70-82 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TimeWindow.scala:100-112 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SessionWindow.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"3955a50f9b46d5f2baf9ab7ca2ae6eb3b2a1d1cd03caa5e4cfb88daf7d8b696d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleSketchAgg.scala:294-305 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleUnionAgg.scala:231-242 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleUnion.scala:328-339 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/tupleSketchAgg.scala"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bf0b427e68c149e2d82479c3852a32897959e4bf0a6036602ef25a3f23b8eda"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala:2191-2195 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xmlExpressions.scala:100-104 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":2191}}}],"partialFingerprints":{"codehealthFindingId/v1":"95dd2114244639909edb3d409d0a7618607d1e1e896b3a284650322b270297a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ordering.scala:91-95 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/PhysicalDataType.scala:426-430 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ordering.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"de9c985e0ea0019eb256ef53fec31d53c6cc7185a12a61ac34ab1b4d88c283e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala:1884-1894 | sql/core/src/main/scala/org/apache/spark/sql/execution/BinByExec.scala:70-80 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":1884}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d5f82a99418158e3c05800ce46c457e7af611ac32e18a27ceb7c2063cf550da"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameNaFunctions.scala:151-158 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameNaFunctions.scala:199-206 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameNaFunctions.scala"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"a59cee28dc0bcce6b1f92a320b90cf8ed66b7d7a77bfc6868e11a205868376fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:697-707 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:1095-1105 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala:697\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":697}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8cf10ebaaa3cc5a8ece7b47d81b1f6b54fe7707ea7040ac3caef071469ecc7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/CommandResultExec.scala:94-99 | sql/core/src/main/scala/org/apache/spark/sql/execution/LocalTableScanExec.scala:116-121 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/CommandResultExec.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"c240fc402284b2de38abd875e5ca4575576fb7154f3b153f2a062f56f6f5c8e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala:580-585 | sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala:265-270 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala"},"region":{"startLine":580}}}],"partialFingerprints":{"codehealthFindingId/v1":"bae820508e2a46723f127a3ecea92c49374adb18af8d582b8acc27c45ab1221b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala:60-67 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonScan.scala:59-66 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextScan.scala:58-65 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"def930720418d787b50c98d896ed377cf9873c37b13faa08a5f0fc3f1aa2350e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 7): sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingSinkCommitRunner.scala:47-51 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:269-273 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:325-329 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:510-514 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:639-643 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:688-692 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/UserDefinedPythonDataSource.scala:753-757 \u2014 there are 7 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 7 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingSinkCommitRunner.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"73e74e94543de7d5b48a5533bed38baa4af79cd3de6e91ae4dbeaa8e5c2e4d33"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala:118-123 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala:208-213 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:794-799 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:1192-1197 \u2014 there are 4 copies across 3 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala:208\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ffe6920289bbb4981a1179cc430e514b40910deb40105b681f92e9fcad95f78"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala:350-354 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:1047-1051 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala:1313-1317 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"3867a43909391f3f499cfedd8d6afa0d064b310fd3bd4df524324e17bb0a56a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala:60-64 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala:1554-1558 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateStoreColumnFamilySchemaUtils.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"38f9b02e7c58b764b3aa78c68fb23f6aed65a45f7e77ad33249d477db22dd7a6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala:138-145 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/ListStateImplWithTTL.scala:149-156 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"6125bd49ec1a842b4f3ad780f5183675d8d36803a83b0b5bc1156314c6872027"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/MapStateImpl.scala:117-124 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/MapStateImplWithTTL.scala:155-162 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/MapStateImpl.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca3873d0724fe688ad2a8111f1dafd3a18ea583dc1eb70c6d681b09d724245c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/ListStateImplWithTTL.scala:239-246 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/ValueStateImplWithTTL.scala:155-162 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/ttl/ListStateImplWithTTL.scala"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"0503eb595f702bb7aea0acfe6ff04b8c7778497a6fa15b07913a247126cb6a34"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/memory.scala:319-330 | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/TextSocketMicroBatchStream.scala:153-165 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/memory.scala"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee877ff8d9233294041eacc2d8d21d05a33cbdf96da8199561465da90668ccb7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:58-66 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala:286-294 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala:113-121 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala:114-122 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"815662acddc40f3707dba72e8c1af38009adb1a8c530234c6708b5cf6459d4a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala:90-94 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:377-381 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e39172d2826bc86085d9e9cc1acfd5c5f5e8ab5f16aeb34c35547e52dcd79fc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/jdbc/DerbyDialect.scala:77-85 | sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala:395-401 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DerbyDialect.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d9403176adf4cf5252c78a3abccb8a44306d6ce6d596c8e83c0bb5285b2c533"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:542-549 | sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala:603-610 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:542\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a5542fa19a66c2ef15688c503547f70171c06ad93d086f3fc0990f942fec1df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): core/src/main/scala/org/apache/spark/deploy/Utils.scala:48-52 | core/src/main/scala/org/apache/spark/deploy/history/LogPage.scala:33-37 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Utils.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"783e6136a5e47a2478275b8e64ad6ae4e47d9ec3d659ab6b3be0d7b1c1e07424"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:245-249 | mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala:420-424 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"3074c1a574162d284563354625cba9e172c3c474216d591b2df3d3dde1849be4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:215-219 | mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala:259-263 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bddf19b0f7061be90e03a2732f50dc581ca2058584e17a64c755b2dc813872c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:182-188 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:218-224 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:256-262 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:182\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"df6598e45ddf1b24895fdd2b41ce4acea4bac0d18c3a299dfb16492c5a98cdab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:196-201 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:233-238 | mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala:272-277 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"17c82739169e8ebaa877142174f2ff800682e8a081bce432bb41f623e08821b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala:135-139 | mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala:107-111 | mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala:653-657 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a446741500d9044286eb4144962c1342fa612e85bfd7bb27b2660fb8241e15e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:52-57 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:53-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"331db47d1deb3d85faef4d18dacdf492f2309662f982b0a5f91c5eaf5904d609"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:93-97 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala:89-93 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala:93\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AlreadyExistException.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"b40530031261435fbdd807c30428d0dc7dcdfde7203b95a63324f5a8475a50c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:528-532 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala:862-866 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala"},"region":{"startLine":528}}}],"partialFingerprints":{"codehealthFindingId/v1":"520a0c479912fcd8070b5144b47bee8e509509b94b9981be4e61607f698847ba"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1180-1184 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1449-1453 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala:1180\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":1180}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e0276f84b337188c30e0a9e80f3ae7bfb437beff09e387c4190f34925c57563"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:353-357 | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala:453-457 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala"},"region":{"startLine":353}}}],"partialFingerprints":{"codehealthFindingId/v1":"e15e2b34f046c63b454277babf372f1d5f9a34b7ccc6d1684184e5ab62a522c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Implicits.scala:76-81 | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowCreateTableExec.scala:118-123 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogV2Implicits.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"64070b04f67dec19da2c006184d9f686e53002db1dc786b978f7caf65807958a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameNaFunctions.scala:134-141 | sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameNaFunctions.scala:102-109 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameNaFunctions.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"90f3d62598aeb83ce9fc65698b4aac3966e0d6e80dcac1c8cf4f4063d1aa0afb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:520-524 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:345-349 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:525\u0060 calls \u0060renderMLCacheStatus\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:350\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"01a7970887c47d09304b491825d88b7094cb515f593bb5e37056f44e749fb30f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:725-731 | sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala:393-399 \u2014 before extracting anything, compare \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala\u0060 and \u0060sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 118 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala:725\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerPage.scala"},"region":{"startLine":725}}}],"partialFingerprints":{"codehealthFindingId/v1":"69bac5252598f58df7a092a5bd6aeebd0102386f8477132c35db90f55206f863"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:2205-2209 | sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:2216-2220 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala:2205\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":2205}}}],"partialFingerprints":{"codehealthFindingId/v1":"835db31d9b7cead961e3ad91ef2879e65d169534b8f8023c341f8d5a724b6699"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala:76-80 | sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala:603-607 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala:76\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"93e68211dd2f700ad8f56ead36b0d8ab10595211d0ff8948445f4220db82a2b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:955-968 | sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala:471-484 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala:955\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":955}}}],"partialFingerprints":{"codehealthFindingId/v1":"0195055293bd67c09832aca102eb0559c15e7c28f5a28e173f08b14548b71690"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:432-436 | streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:481-485 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala:432\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5f12b15966c02f145069a8ebe5b80dc739310d2aab2ebe6c2a9dc7961d74cac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (52\u201353 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1847-1899 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1944-1995 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1847\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1847}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3fb1f82a48ee368ccbd14a05de855dec9c765cff9bb097894baa83147d05d33"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (32 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:228-259 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:338-369 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:228\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8c24e10de18e9df95f863ee306b47c3c8a679edbc08ee0630c57b3d6c4bcbf1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:331-361 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:333-363 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:331\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note first that the copies are not typed on the same thing: \u0060WriteBatch\u0060 names \u0060org.iq80.leveldb.WriteBatch\u0060 in one and \u0060org.rocksdb.WriteBatch\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ced52871e4a102b27ce02e7f998de275231c54fd38f07ed5d84bbb058ddb16a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:365-395 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:367-397 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:365\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note first that the copies are not typed on the same thing: \u0060WriteBatch\u0060 names \u0060org.iq80.leveldb.WriteBatch\u0060 in one and \u0060org.rocksdb.WriteBatch\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"87425b125051d92a9db36dc506bc84eef9af4346d5df1c797c1c4ee3c7afa493"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:69-99 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:61-91 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:69\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"1659e04db6dd419135f4a5da59510c0e4b61162c24237471b3f227cb92ac8e85"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (58 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:458-515 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:460-517 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"9833aafe866e9a38c884fe3b70aacc5d91540fb7523d83313e405a0b768c051e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:182-210 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:184-212 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"a04150ab4486d15f9024f0437f45f3db430c47498680f2e252ff85d15e31ebe5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java:64-91 | common/network-common/src/main/java/org/apache/spark/network/protocol/SslMessageEncoder.java:67-94 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java:64\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/MessageEncoder.java"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"172cd90f846b25950b454970cc7a5dfcd38cd4b6ca0093f9f687d617811f5254"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1425-1452 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1505-1532 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1425\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1425}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3513ccb73e7a48bce54b334a985532fd9c90d685ab7d60a2a5fdbc168084e25"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:139-165 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java:156-182 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 51 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:139\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"836d05fc0ee58470d31c33a3b733d9b8e5d0979374bf60f9c12ee54eaaa6e345"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (43 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:58-100 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:63-105 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:58\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"360bc26badd3fac1ea972d56965a720c7f71e904c25a0d74050ff4ac2fb89ab7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java:114-134 | common/unsafe/src/main/java/org/apache/spark/unsafe/Platform.java:265-285 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/Platform.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 1 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"53d0a2ff0156f7dfcd460614da9ac67639b8eb0753487af50431c4fe68447550"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:138-157 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:124-143 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"46d1b8282c3028638e1e6230a06aeee34b8de848bdbd0e42a1cfa51052cb12a6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1454-1473 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1555-1573 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1454\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1454}}}],"partialFingerprints":{"codehealthFindingId/v1":"255c355a9fd0d4a2a84739a6301a51480cc25aaa97c4299f4e88657dd0edb9a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:125-143 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:195-213 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:125\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d03551ed1793a4a35c070af92601518194fa15f4110e20f970a3e17d80f0532"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1826-1843 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1923-1940 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1826}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0f0df2d51898d1e02774a975c8474601891a69aca78f8c9a46045f229514e62"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:116-133 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java:128-145 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 51 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:116\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"87d78050e3ab677d1a1d9fa79bd73d21c6303cc58ec4286fd1dc8bd5e1248ca9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:90-106 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:123-139 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:90\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"a316bcffdca5eef79b45cc068c0de8cad2873738f213be8302c81597f9e0bc78"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:265-281 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:297-313 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:265\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"75eb6d5f3c4bbe927c31ad9bc9c1ff5110948ea3cf2c3ccf0f97876037bf9a9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:104-119 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:206-221 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:104\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"02630c03c43536e06e861c0368caeb04a395f62065662abea06b381b5f19a5ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1360-1375 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1593-1608 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1360}}}],"partialFingerprints":{"codehealthFindingId/v1":"d35de6ab4fb19fbf4d99c7d7b579402c31d82e965160acf4101102b3983251c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:188-203 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:194-209 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:188\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:193\u0060 calls \u0060isNullAt\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:187\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fbcbd6169b9c247c86885c1c82394e197eff5af2a7f352f30b173a474d201c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201316 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:106-121 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:201-210 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:106\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5b0e973e9fcc99fd5c04202ae78749f597b719bcd07c49c3442057e5bdc01c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:751-765 | core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:794-808 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java:751\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":751}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc7b25d8cd5cdbaf48373d59e4f6fab6987cc39c84141ff966f45900b59d1212"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 3): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:87-99 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:126-139 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:165-177 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd59775755f4268f9aafc3eec67c47178e4fb5f112967eb26d09b5b97dc3a36f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 2): common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleServiceMetrics.java:70-83 | common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleServiceMetrics.java:103-115 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleServiceMetrics.java:103\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleServiceMetrics.java"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"2498e6e83df36047e8f91facd69ce91daecd9d19e46510647b6393d6b02e3353"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:529-542 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:676-689 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0abc1829bc962dae136011d5680f4b41a2bf2918b4c07faa364ef3037cc357b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1539-1552 | common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1572-1585 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java:1539\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1539}}}],"partialFingerprints":{"codehealthFindingId/v1":"29340901378b23b9562455e6069b57406cb2d4238c263a54ca7413318b686454"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:633-647 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:737-751 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:633\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":633}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d74af8b204d3bd3385f521dd67ed971d8112b69022e5f325e0238a43675f4f3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/TimSort.java:713-726 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:835-848 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:713\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:710\u0060 calls \u0060newKey\u0060 and \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:833\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":713}}}],"partialFingerprints":{"codehealthFindingId/v1":"703721b99f5ee4fba95f9e5c9b035adff3ffcecf6cc77736647d2a9f5a6ade90"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 4): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:122-134 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:108-120 | common/network-common/src/main/java/org/apache/spark/network/shuffledb/LevelDBIterator.java:40-52 | common/network-common/src/main/java/org/apache/spark/network/shuffledb/RocksDBIterator.java:46-58 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"53887fa1a480312fe94b0f4624b741963f20c208529ccee1ba9b2a9ad3556246"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 4): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:133-145 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:203-215 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:268-280 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:319-331 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:133\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9457ffbcd2e5d3438622da6d1cd542f6ece593e7ba124ecadc9754608bbed3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201313 lines \u00D7 3): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:242-252 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:352-362 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:481-493 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java:242\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"a532547ddca25f4192302ed870ad137600c17294dd0ec06bbbca699b404c2b37"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:307-319 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:339-351 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:307\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"92708052ef75b06cd4dd8d4eb2fb3b9d2364dfdca37c3353ec161f8034385db4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 7): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:512-526 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:576-587 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:598-609 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:643-654 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:664-675 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:907-918 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:930-942 \u2014 all 7 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:512\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb5f8d4a4e80b553500cf3edf770e15513b3cf0f5e65c7db1d8b82997582e32c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:86-97 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:166-177 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:239-250 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:86\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d0766fa6e7053e0c28e2c588de2058e40564776f60e37cd056ee48d7b591ecb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:535-546 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:555-566 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:618-629 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java:535\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImpl.java"},"region":{"startLine":535}}}],"partialFingerprints":{"codehealthFindingId/v1":"79eae3d226b06c03a3261739d084a9638289e07d62409edfd363d24be43bd218"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:373-385 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:405-417 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"033621eb0f736977a6e0fb6159e16089a9dc6a1a4574ddfb2353f4ed4fc85afe"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java:119-130 | common/network-common/src/main/java/org/apache/spark/network/util/RocksDBProvider.java:159-170 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060db\u0060 to \u0060DB\u0060 in one and \u0060RocksDB\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"dab20e3b04a72c5c73e55a224f5408e52e2f1c8ba21ad2c6e1736ee700a68604"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:53-64 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:346-357 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2390081b2a59156c6adbf02a1f84105875f49759010a1eaac039d12a507c0bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:421-432 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:459-470 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"796e24c745436359018fd9bc377e094c1d84a5c704509c1aa0ef8dfd74e97618"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/TimSort.java:771-782 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:893-904 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:771\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":771}}}],"partialFingerprints":{"codehealthFindingId/v1":"d830c253eda59325419f721a1f77bf5ef945f20c0e16094b6af62926d04f8429"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:356-368 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:446-458 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c002e1a59e7056997d01f48fd391de1063ecd336ae744ee38833124526032b7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:210-221 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:214-225 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:210\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"95d9ac0acf0307aa411b495b13465287bb1de745fd7aded7a82d5915f858c9b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:205-216 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:209-220 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:205\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"aef025038ddc54d2a845bb4ceeab2236151503db20d3c724210c952b30906890"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 3): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:215-225 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:253-263 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:292-302 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9ce8369e54b75fb5d29da07ed9a86e4dc2db72979797e78765edef59f789736"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:167-186 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:199-218 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:167\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a541a019f7537cbe6aa58b476afb8a9846c6bbd90b2fc3aeff017cb202f8dd5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:95-105 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:95-105 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dde0532119377f05a44f41906873007b43c43ab58bd0ffb28128fee1fa8ba2a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:112-122 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:112-122 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"66416766d361dfa29765745bf946b2a6300fe11cc67ba68ef7e1bbd96e2bbbe4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/UnsafeKVExternalSorter.java:94-104 | sql/core/src/main/java/org/apache/spark/sql/execution/UnsafeKVExternalSorter.java:163-173 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/UnsafeKVExternalSorter.java"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f0d05ae64daf264e4889d6fa50ef40191321d4206885595a1df1873c290909a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:204-213 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:242-251 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:280-289 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb47edeaa2e342996a233b49a0c1699e4a366a06246217431328793c3092851b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:413-422 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:445-454 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060idx\u0060 to \u0060LevelDBTypeInfo.Index\u0060 in one and \u0060RocksDBTypeInfo.Index\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"71f24e191dd61bfbb62d34321dd01d4ad80e2f00b6f66b5a99255df2ce970fa0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:131-152 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:133-154 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060db\u0060 to \u0060LevelDB\u0060 in one and \u0060RocksDB\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"de390fd519b189834fd2a6755a18785a39002b6b4f89c12116155ab36793a612"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java:129-138 | common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslServer.java:158-167 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java:129\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"910c2553fecfa1c9f5e1bdac536010874a6af32431837c3c0a000983384e8276"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1704-1713 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1733-1742 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1704\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1704}}}],"partialFingerprints":{"codehealthFindingId/v1":"01445edd4b372f3aa5bb7fba11ecf219ab2843605b0d58cdf956eb2950394b8d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:497-506 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:608-618 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbb7f96630fa33c30b431cafb26b768d782325fe281d74840c7e20cfd502a684"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/TimSort.java:578-587 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:650-659 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:578\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":578}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c24252a93bdc102556a7635ff9249b3fb427fbe11f9ad7408642f7e2cdd9171"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:459-468 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:480-489 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":459}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5c09cd6486f2ab83136a9b3e88effc85b9ec8304bdd55a0783b717e32ff88cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:89-98 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geometry.java:89-98 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:89\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5d2e1effe15c674fa0e4d157002cc8d3f45ddfd003f35a9c0bc2a5b831825cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 10): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:150-158 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:168-176 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:186-194 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:208-216 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:231-239 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:249-257 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:274-282 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:295-303 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:460-468 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:483-491 \u2014 all 10 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java:150\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae42d597d7933c975f33e234ba57b957bbb74a64fe8b3d9e1429934d27d7b51e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 5): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:53-61 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:137-145 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:207-215 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:272-280 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:323-331 \u2014 all 5 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:53\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab52871cb8bb08f2548e584708a73cd840a90f056fd48e2200258ad4395560c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:427-435 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ConstantColumnVector.java:287-294 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java:492-500 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:427\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java"},"region":{"startLine":427}}}],"partialFingerprints":{"codehealthFindingId/v1":"6eb7c45e248afd4fdfa3564934d4eed7de7d90caf83bcf42a3293ca5d9ce33aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:197-205 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:203-211 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:207-215 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:197\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:207\u0060 calls \u0060getBinaryView\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:212\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbf50b8202c67ec252dc44f083a437163296ffa5f811d9c7591ecce82e79995b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:304-312 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:306-314 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:304\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5937a8ada74cc58ccb7870ba7a66a0d7eb8d77a1a1015c221b1fe03bfebb174"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/server/TransportRequestHandler.java:169-177 | common/network-common/src/main/java/org/apache/spark/network/server/TransportRequestHandler.java:196-204 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060req\u0060 to \u0060RpcRequest\u0060 in one and \u0060UploadStream\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/server/TransportRequestHandler.java"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"549c8a67a4f2fd37adfd872aa361c0420ea9e5c072f2e7f2c9e4435c3daa7648"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 2): core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java:241-249 | core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java:365-371 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java:241\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad5427a69da0bf589165cdbc3d27643648e0ad0d7db786b552b82f377dce31aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionInfo.java:150-157 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionInfo.java:180-188 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionInfo.java"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"505a1a7ba77a801f068b5b9d585e3f2529360bc761f261a45ee8c159978455f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:267-275 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:230-238 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:267\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa82cc9b3f688b1a761399dbd360bae0e79175470f2e386215d524cb58468133"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:351-359 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:309-317 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:351\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"99793d3bdffc61bb44a434a4ad961f48883910f107969522d3b61c1e5fb10f4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (3\u20138 lines \u00D7 9): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:55-62 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:65-67 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:139-146 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:149-151 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:209-216 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:219-221 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:274-281 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:325-332 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:410-417 \u2014 all 9 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:55\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:282\u0060 calls \u0060isNullAt\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:68\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9c165ef5035fbc7baa23a07401aa12ee522053881b0d938aca10affdb2505c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:208-215 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:212-219 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:216-223 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:208\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:207\u0060 calls \u0060getBinaryView\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:211\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4d949e30583a8e0663468872d00690f3da04fee7182453ce8b61cff4717fd3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:483-490 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:497-504 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:542-549 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:483\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":483}}}],"partialFingerprints":{"codehealthFindingId/v1":"9009418881232fa9812d2d92cd9d48ece550891a7e33fbe8f54e3c2778384a10"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java:67-74 | common/network-common/src/main/java/org/apache/spark/network/util/RocksDBProvider.java:84-91 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java:67\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/LevelDBProvider.java"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"450e7a4699e2ac9cea44de259c2d928f22d0c9177fb5da84c9b8aed5ec6fcbc8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java:333-340 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java:371-378 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dd82c35ea4fed9e68a89ce5523236a4c1cff94d30ef9528b885885a67f3145f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1293-1300 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1495-1502 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1293}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8e66f2dc60943af6ca896316aa2cb4f5eb090030b7502dd2f8a5ddadeb1fc59"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java:394-401 | core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java:470-477 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java:394\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java"},"region":{"startLine":394}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d66d07597f81c6be665703aaef7ea5c65a22358e57ef5880eb2db6df9efaa39"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:84-91 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:244-251 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:84\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"f42c7478559e00f784383ba7bc27aa34c47eddb74326db81e9b498c6912d16c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:340-351 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:429-440 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5422ebfef43f79fa590bb012cd25c0145ac60ed71a3788cf0d1434a15ac7240"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:35-42 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java:60-67 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ml/MLExpressionUtils.java"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5cf22115734bdeb025a195d149644566e5eeb929c58cba0b272cf3a5d50285d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:220-227 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:224-231 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 31 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:220\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccdca3a7015babf472288466ecba246c57078cbe827addf5a19e91b56bb3bf85"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:224-231 | sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java:228-234 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 96 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:224\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b3745f514f056c5f36f2106dbd968f10413736444aa969d35b0cade046bc87d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:137-144 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:151-158 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"8262ac6b00cd231f20519620719f649f1f907a6432fe583e158a9b4b8300bd7a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:383-389 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java:120-126 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:679-685 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2afb143cc430f841a5e8e9943eade6408b9b90e5494ed307a9cb94537100424"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java:246-252 | common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java:255-261 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060item\u0060 to \u0060String\u0060 in one and \u0060byte[]\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketchImpl.java"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"a103ad47668dc053c17b761f11c602b303296614d712160996e2334286f96ae7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:69-78 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:69-78 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"5dcaa9d018390e1eaa798bf82907f8fceee948d8840e14414580675beefc9067"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:83-92 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:83-92 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"644da490099e6c8c62b74475c42843d3909718c4dbc29a7cee2e654498cf1069"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1186-1197 | common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1380-1386 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:1186\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1186}}}],"partialFingerprints":{"codehealthFindingId/v1":"4454650dfd1a0f99c8181c3c2e281cd605e9d4c42e13c1b9fba14d2adcc7819d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java:462-468 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java:504-510 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":462}}}],"partialFingerprints":{"codehealthFindingId/v1":"170de27ac12884c436d9586cf2e986116fcf9a2d35e828b85e1e4d5d9e83f382"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20137 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:80-83 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:166-172 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:343-349 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:166\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"b41d61416a4fce9262ef8e6e9f1ceba8d7a448ac18239b855138bad1acdc347a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java:47-53 | sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java:76-82 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java:47\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/RecordBinaryComparator.java"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"69dc02a0828db8908826b832d41d8e275649365486cbf8887cb9f450cfecdd0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:156-164 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:249-257 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:156\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:167\u0060 calls \u0060skipIntegers\u0060, \u0060skipFully\u0060 and \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:258\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"b55daa670c211b194583064d958cb2252a1194afdbbb5295d4886b041fcb3393"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:265-273 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:397-405 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:265\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:276\u0060 calls \u0060skipLongs\u0060, \u0060skipFully\u0060 and \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:406\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"be5d70693920e0a875f07f082dcee27ebba8635fd34e556d7a3a897273c554cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:392-398 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:472-478 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:392\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"abf6eddbb1dde40ce54a4a5764d18ae6504360a8798315e6d34b9d63077ea0dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (2\u20136 lines \u00D7 9): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:68-73 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:77-78 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:152-157 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:161-162 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:222-227 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:231-232 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:283-288 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:334-339 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:418-421 \u2014 all 9 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:68\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:68\u0060 calls \u0060isNullAt\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java:418\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VectorFunctionImplUtils.java"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"c60c7ba1b667ac181748a9724a22c785c07a9131cfc26f119a700587e0433b7f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:303-308 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:330-336 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:305-310 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:332-338 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:303\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note first that the copies are not typed on the same thing: \u0060WriteBatch\u0060 names \u0060org.iq80.leveldb.WriteBatch\u0060 in one and \u0060org.rocksdb.WriteBatch\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"58ed669e7c68daada027da08f471a2ea6bc14a5aa78ab7a8a8996e38b91c036f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:597-602 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:666-671 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:773-778 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:871-876 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:597\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":597}}}],"partialFingerprints":{"codehealthFindingId/v1":"215658d81fe2adbb9904ccb0d1aa2c8bd412e4d8d3861c70eb4b02cdee824868"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:572-578 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:629-635 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:733-739 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:572\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":572}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1f172d1f77c550e56211b7a2141196612b92246a626831130dea8db33824bf4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:227-232 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:259-264 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:227\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"7183bc17c3c4d42c35a5b7eaf1d7e72ae75ac1f9dead4ea06f4d1b10f864e442"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java:151-157 | common/network-common/src/main/java/org/apache/spark/network/server/TransportRequestHandler.java:326-331 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java:151\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/server/ChunkFetchRequestHandler.java"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d463617ba7f02f673da8139b956beb58b17f9af821e6dd064ebfc51244c5f73"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java:133-140 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlocks.java:133-140 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java:130\u0060 calls \u0060readInt\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlocks.java:130\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b456e46be7524e89e31704b23fb7d6ba2136d2dcd7bd54d1473bf51ccb3eef8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:538-543 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:858-863 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:864\u0060 calls \u0060equals\u0060, \u0060appendWithArrayAppendImpl\u0060 and \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:544\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":538}}}],"partialFingerprints":{"codehealthFindingId/v1":"42eed287f5cfe8f35d4f59257b28c19f4abe2668596d9304bbd313dfcde52220"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:552-557 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:877-882 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:552\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:884\u0060 calls \u0060appendWithArrayAppendImpl\u0060 and \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:558\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":552}}}],"partialFingerprints":{"codehealthFindingId/v1":"911c3d9e7b37094f5d4c067177052226e97cbb2463eb47e379fff5d766b3d7c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:120-126 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:223-228 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java:120\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb9817df10a3ff92d82e4a5e9d059da2f8fb597d3321da34dcbdbef27abd054a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20136 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java:510-513 | sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java:517-522 | sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java:525-530 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java:510\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/datasketches/memory/internal/ResourceImpl.java"},"region":{"startLine":510}}}],"partialFingerprints":{"codehealthFindingId/v1":"f15876cfce83aa6af304c4096a3b2626db696125df46ac30990d655e5a167308"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:109-114 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java:117-122 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 51 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java:109\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"82416e4a92b76acc4e6641dc01e5f4f5bc0069ee2d1e7d70fc2ea9d601be6f4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:220-225 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:452-463 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:220\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"acea5cdc0d5d1b677d498af1687afb3fe64bd47525ec146e4cc0d27954a2aa04"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:52-57 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:58-63 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java\u0060 and \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 31 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:52\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java:58\u0060 calls \u0060apply\u0060 and \u0060sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java:64\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e0f77287a9227b94c657991123b1a8f2fdc30f73f045b7a3a683d98b47c1252"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:545-552 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:580-585 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:545\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ad78eeb6e39475fa3b7dd77e9834e0425ee2faf9a703230ecbb3428b8118911"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 4): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:534-540 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:578-584 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:854-860 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:941-947 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:534\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:586\u0060 calls \u0060equals\u0060 and \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:542\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":534}}}],"partialFingerprints":{"codehealthFindingId/v1":"bafff76aebfef5a94f2c36f30e1b79efdae4ec1f8bc5d125642cdc485432ef08"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:551-556 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:876-881 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:961-966 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:551\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":551}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0be8127efc6707426f0fa96c9d44e36a58f6e0121bbd97ae724417fc368f39f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:582-586 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:640-644 | common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java:744-748 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java"},"region":{"startLine":582}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f1953e417f599a3a669c4c9c9793c602afcccb51bbce7b6da857b95e944c544"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java:34-38 | core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java:40-44 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"65fff87b1c2c011e328c1783f456a032986e6c127602e8a5a06faa6344eebff2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): core/src/main/java/org/apache/spark/util/collection/TimSort.java:749-753 | core/src/main/java/org/apache/spark/util/collection/TimSort.java:762-766 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060core/src/main/java/org/apache/spark/util/collection/TimSort.java:749\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/TimSort.java"},"region":{"startLine":749}}}],"partialFingerprints":{"codehealthFindingId/v1":"15627310dcdab75d40adb291f88954d05b0e27e65399372bf1665f6f719395f0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:239-246 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:480-487 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:239\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"8031811aa3cc61ec215c428bda361fd14a1fc9f5773288368f7cebb9e6fac5e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java:74-79 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Unique.java:81-86 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java:74\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b1cecd5b80ccf92c9469ab1023d265d0390ef22ac4931db2d05f1286fb273fa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:79-83 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:453-458 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java:79\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fd1c8377ef71898ba4812ecaf9da16bed37e1b054c73370ab4384b4032730bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:622-626 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:628-632 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"2144f95b5de71bef8024c53394c8581d13144af0c5a781598718f237574eef6a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/DefaultValue.java:38-53 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/GenerationExpression.java:44-60 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/DefaultValue.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"e108ea2d9a854afa8e3a2e79e987a70b48dcca0d122cdc68ae89cd4fa7e40293"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Avg.java:34-43 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Count.java:34-43 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Sum.java:34-43 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Count.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Sum.java\u0060 as WHOLE FILES: 86% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 1 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/aggregate/Avg.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e98d41cb171076d108fe71aab84ac111e272f62b9d41a1cf873dd302253f8aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/filter/And.java:31-36 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/filter/Or.java:31-36 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/filter/And.java"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3813b1a0faf96425d3a301ca9d04a8ef64c7a17699030bac0300ecb1de3064b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReaderFactory.java:54-100 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/LogicalWriteInfo.java:56-67 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReaderFactory.java:54\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReaderFactory.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c2003ac911d90a8bf268f7e00f8e6b035607841a007bd5b66c3f0493e37a757"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (42 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/Scan.java:1-180 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/Write.java:47-88 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/Scan.java:1\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/Scan.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfe9baf363dc6d0b05531f7be7df0e9e8d22938b1eeba0c5607700d2bc509669"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): common/kvstore/src/main/java/org/apache/spark/util/kvstore/InMemoryStore.java:485-491 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:160-166 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:146-152 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/InMemoryStore.java"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad286f308e7ab0f7e3669b33720214dbc2f902df207d14f50d2dff63f58abf33"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:114-120 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:147-153 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1a22536e7995326c6ad2ad26458ad5c2705ab64707b7fa0487bc0c0c516a8dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:122-128 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:155-161 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ba6fc9c1c2f1b248e144fa3f86dd6cbe7b9c8e92929bca0fdd1b9e1b98a4634"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:146-150 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:179-183 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"72f777621eed519999fed38c25499ceeb383b4586c7fcadf9b85faa4aab7d53b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:197-208 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:186-197 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4303a5d439f48eecd5ab88c22e00e798a4045aacc8b115d1efae0f013c7d45e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:273-285 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:261-273 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"f88e9808dbcf1c8db65209909083db8c46cc0d394607c9e9295c76b9420969c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:166-171 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:168-173 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4bd4afe1fa04de037de52cd703c571eb0ae84536da20ea512ce2ca09648691c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:224-230 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:226-232 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"635026f4224e62bb38a3a75358d0c26a135dac06b668d06311c37621a90a9867"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:263-269 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:265-271 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"26404c25ce68deac642e3d11e128def0c72229b2b9ab092655440c0febe5a99f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:281-285 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:283-287 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"240af1c7e58086b7d3a9be07a91e8218d0b6add1b02a0da7e5d4ac8905c4ed78"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:288-292 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:290-294 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"51dad3a0dae1bb0fce79c1f4e69c6eff5d3489d37d85172d43fcb8ba99a409b8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:295-299 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:297-301 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5abc49d018a1973462296f8a334da422b8ab8d8b21c613989d4fe40be61af65"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java:314-321 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java:316-323 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java\u0060 as WHOLE FILES: this scan already matched 14 separate duplicated blocks between them, totalling at least 230 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: \u0060WriteBatch\u0060 names \u0060org.iq80.leveldb.WriteBatch\u0060 in one and \u0060org.rocksdb.WriteBatch\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f4cf62c456dbb5956b3fed68d0da9851618ef736a39099cef6046a328ec21cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/crypto/CtrTransportCipher.java:295-303 | common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java:216-224 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/CtrTransportCipher.java"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"f606d1430db78b6afce35013d130d15241c5c7fbed84169ddef08366a8be6b43"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/shuffledb/LevelDBIterator.java:55-63 | common/network-common/src/main/java/org/apache/spark/network/shuffledb/RocksDBIterator.java:61-69 \u2014 before extracting anything, compare \u0060common/network-common/src/main/java/org/apache/spark/network/shuffledb/LevelDBIterator.java\u0060 and \u0060common/network-common/src/main/java/org/apache/spark/network/shuffledb/RocksDBIterator.java\u0060 as WHOLE FILES: 85% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/shuffledb/LevelDBIterator.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7116d3a3265b065bd6ca78ae648d65dc89aa1eab2ccf6c25b02aaa1481375c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java:82-87 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java:82-87 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"890ab06f9970c7293cfb60a36320b47c2e6b0a08c9cf3f75945073fabb13e7a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java:67-71 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java:67-71 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 4 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"592ea333eae4b955798f08c2ba6a6214e75b95de929f2380690cc0b0ad172c72"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java:74-78 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java:74-78 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 4 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c41849cdcfa812c752f5121a79e47377b0b2958cb56279089028ee56d4d09cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:59-64 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:59-64 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"12cb3a8e2c7b9b920fc74976c4194443a0042b16786a4e4155c7dc67d781f2d2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java:139-147 | common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java:139-147 \u2014 before extracting anything, compare \u0060common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java\u0060 and \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/hash/Murmur3_x86_32.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Murmur3_x86_32.java"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee460fd6ce8530a8af4d49ad3b0b85a963e67e62ec2e2035e6937d5da0c55a37"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): core/src/main/java/org/apache/spark/shuffle/sort/ShuffleSortDataFormat.java:62-70 | core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeSortDataFormat.java:76-83 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleSortDataFormat.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ad56e2c69d1de050a0f842bcc99b4b22f804f490f81bdbfce9e0d8312c36540"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:208-214 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:438-444 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"11feaf2977443de010069b8a595c521dec149bb26625d67b135bd1478c25a7ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:228-234 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:467-473 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2121fdf5841a0f757a2e9c20140678e9a6adffa1ba20d1acaf1d47d5b70f426"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:102-109 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH64.java:120-127 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2ca9540be640be6203c0e64efd192eb575b4dbfef9d00373648cd001d9cd92a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java:185-195 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geometry.java:188-198 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/Geography.java"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"2de23e21d7bb3b6d8871620bd5aa3bb675a8dd55324b969b3fb388a0b6121577"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java:82-86 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Unique.java:89-93 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"247269620c83e69922b080e5f89419758c1bf3198596c42302d5fe84eb105d6f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:139-143 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java:122-126 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"45fcc09aa735d8497f84d32719bc48c246c0fbf721588bd3983273d38b2ce320"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:146-150 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java:129-133 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"19c8d4618d27a5f63a998a86d4c4de5b2954cbbbf87df122945798e11bc37c7c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 9): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCatalogsOperation.java:68-75 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetColumnsOperation.java:243-250 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCrossReferenceOperation.java:179-186 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetFunctionsOperation.java:140-147 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetPrimaryKeysOperation.java:124-131 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetSchemasOperation.java:89-96 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTableTypesOperation.java:85-92 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTablesOperation.java:136-143 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTypeInfoOperation.java:135-142 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 9 call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCatalogsOperation.java"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"752c6f255b390f8ca263cbe8ec933a4c954fd5ef3a9c64016b66945220a5abb9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftBinaryCLIService.java:119-125 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java:705-711 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftBinaryCLIService.java"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e5428b43be32dbf5370a2597230a59c35acbe261e4fbb1b38fcf87541de6891"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java:339-344 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java:371-376 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDB.java\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 121 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDB.java"},"region":{"startLine":339}}}],"partialFingerprints":{"codehealthFindingId/v1":"76d0ef1c17e5429c58f52326ba711e45ac9a1637de70ddc2199643e5afa5fb14"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java:287-291 | common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java:275-279 \u2014 before extracting anything, compare \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java\u0060 and \u0060common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 101 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"451c16a5b2a4601d58c4654e5dda1b6c2f17d5c091debdd201f581ea92e6c9f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java:59-64 | common/network-common/src/main/java/org/apache/spark/network/protocol/RpcResponse.java:59-64 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9820c47ca91d684f5c0c1fed57301a9b16bee97c1e7afee9629ff3815aa3010"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java:72-77 | common/network-common/src/main/java/org/apache/spark/network/protocol/RpcResponse.java:72-77 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"c25b2b1e6191d8ca24fe52c8c94e5eccb76f15f7a76bf3f2a5bbd0026e2aa352"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java:96-102 | common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslServer.java:117-123 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/sasl/SparkSaslClient.java"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"493a20c25612de1b984f64f69f18d549becee193f21cba42a85fd2a66770df24"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/network-common/src/main/java/org/apache/spark/network/util/MapConfigProvider.java:37-43 | common/network-yarn/src/main/java/org/apache/spark/network/yarn/util/HadoopConfigProvider.java:36-42 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/MapConfigProvider.java"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"2534acab365ae26a58d0e1c9a636e9b2d62f5c7e3e8bcaca6c11c288a5480c3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java:563-568 | common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleService.java:414-419 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060appExecId\u0060 to \u0060AppExecId\u0060 in one and \u0060AppId\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java"},"region":{"startLine":563}}}],"partialFingerprints":{"codehealthFindingId/v1":"873eb412cda390fdba21125f2c677ba9a1e9827cde107e06d87c67626a36ff75"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java:336-344 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockPusher.java:140-148 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java"},"region":{"startLine":336}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbe75a1ddb197f47a00fcca9158bec667f0612557f90972a0b900d5310cac9ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java:89-95 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java:89-95 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"e24402925e73c1b88376081c603807776f10b3375cd90bf1d30c56b1d7d31c03"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java:57-64 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java:57-64 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 4 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c7b670d7823ef36e72b08f278fcb261c64a02c6d289c2c0bef54a1dcb52e002"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java:80-85 | common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java:80-85 \u2014 before extracting anything, compare \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java\u0060 and \u0060common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 4 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39d9a14d8212a391349d8bfb00414122b9af966fb875946eb69f4e51a3e2589"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:369-376 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java:636-643 \u2014 before extracting anything, compare \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java\u0060 and \u0060sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 49 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":369}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a9314bb1a3a49db871ed001ffe04849930b193703a1f35fd3362ed79969ed7c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java:392-399 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java:129-136 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"1eb710bb6019c0c0eea26074be0c8f9694a2a8547fcf7d9304132757a0d15f93"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java:75-79 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/SupportsOverwrite.java:64-68 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java:75\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"7030bbf3c2e91722d42b930ec8439354de6177ea4ae0a3798fec07a9b5b55a87"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadMaxBytes.java:47-52 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadMaxFiles.java:46-51 | sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadMaxRows.java:46-51 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/streaming/ReadMaxBytes.java"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"74a33699eb968f93c1a407510ca00c49f932bdd168b93c3a7069a4c23c5f557b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java:60-66 | sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OnHeapColumnVector.java:51-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/OffHeapColumnVector.java"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"40c1a35ce7a35ecb144c15cbf582eca53889de00b637bb36c450c55cfbfa715e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetFunctionsOperation.java:70-76 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetPrimaryKeysOperation.java:69-75 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetFunctionsOperation.java:70\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetFunctionsOperation.java"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f8b538542df29febe196c8ce75aed3e6ec85bf8b41c3c4bddd42bd3d111d30d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/SparkDefaultUDAFEvaluatorResolver.java:45-53 | sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/SparkDefaultUDFMethodResolver.java:44-52 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060wrapped\u0060 to \u0060DefaultUDAFEvaluatorResolver\u0060 in one and \u0060DefaultUDFMethodResolver\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/exec/SparkDefaultUDAFEvaluatorResolver.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"473dcc01c678794ccade733c71305f234de7f17245812308064333d89058b3dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): common/unsafe/src/main/java/org/apache/spark/unsafe/UTF8StringBuilder.java:108-113 | common/unsafe/src/main/java/org/apache/spark/unsafe/UTF8StringBuilder.java:114-119 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060common/unsafe/src/main/java/org/apache/spark/unsafe/UTF8StringBuilder.java:108\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/UTF8StringBuilder.java"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"62cbfe93c2bf2affdc386f5265557ac268bd41aa6d7cf381468d61f7adac3205"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:326-334 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:414-422 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":326}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4382b99f4b4d0b5201b91ffca283eeed9d228d6a7665cb28a2629b57f690b29"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:396-400 | sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java:516-520 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":396}}}],"partialFingerprints":{"codehealthFindingId/v1":"098b242f7f0dd818648583e458566b398a0a5fa0fea4733569afd485efe4661e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java:179-184 | sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java:232-237 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"13c1d7defc21cc7db9ec9c15676ad83c20bfbb69c26ada01634307156a8ecbb1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/HiveSQLException.java:204-208 | sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/HiveSQLException.java:218-222 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/HiveSQLException.java"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"22052f557a25c8dcacddde88a9c2566dff00e70a08dd62dbd2fe110247b4d89e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (128\u2013268 lines \u00D7 2): python/pyspark/pandas/frame.py:8823-8950 | python/pyspark/pandas/namespace.py:3126-3393 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:8823\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note first that the copies are not typed on the same thing: \u0060Index\u0060 names \u0060pyspark.pandas.indexes\u0060 in one and \u0060pyspark.pandas.indexes.base\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8823}}}],"partialFingerprints":{"codehealthFindingId/v1":"2defa360a34f7947ce034639653bbc184d4bbb73c04699aa6249d96e3ce2c1e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u2013164 lines \u00D7 3): python/pyspark/sql/functions/builtin.py:27807-27810 | python/pyspark/sql/functions/builtin.py:27824-27987 | python/pyspark/sql/functions/builtin.py:28000-28158 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":27807}}}],"partialFingerprints":{"codehealthFindingId/v1":"823c338adf1cfed324fea5bbd17ea3606ba9a0e45a6e6e1b60b6c0aae0150782"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (163 lines \u00D7 2): python/pyspark/sql/functions/builtin.py:28417-28579 | python/pyspark/sql/functions/builtin.py:28661-28835 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/functions/builtin.py:28417\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":28417}}}],"partialFingerprints":{"codehealthFindingId/v1":"b66d482a7d008c9d17bce4677176bd7c0591a8f7eacbb75b5c0e878f51112e23"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (122\u2013131 lines \u00D7 2): python/pyspark/pandas/strings.py:1942-2072 | python/pyspark/pandas/strings.py:2111-2232 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/strings.py:1942\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/strings.py"},"region":{"startLine":1942}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f06406ec9c4384f71235bef3a1224312eca04f1aff79caadc1472802aef8c38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (118 lines \u00D7 2): python/pyspark/sql/functions/builtin.py:29139-29263 | python/pyspark/sql/functions/builtin.py:29309-29426 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/functions/builtin.py:29139\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":29139}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e747d895d8c237e15ae059cb368784c88fc1dcf17180ac112f113eb928e8b16"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (103\u2013114 lines \u00D7 2): python/pyspark/sql/protobuf/functions.py:40-153 | python/pyspark/sql/protobuf/functions.py:174-276 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/protobuf/functions.py:40\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/protobuf/functions.py"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"292fc7ee7ff4dc19334e4715ba6ffd53797dd3b522037684928cfe6b024c2644"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (103 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1560-1662 | python/pyspark/sql/connect/dataframe.py:1526-1628 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1560}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d7debb6971fa69a8a54e160c08270c3b40be933be09b30bf979bb3bd1f79eed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (62\u2013101 lines \u00D7 3): python/pyspark/sql/functions/builtin.py:24334-24395 | python/pyspark/sql/functions/builtin.py:24632-24732 | python/pyspark/sql/functions/builtin.py:24797-24892 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/functions/builtin.py:24334\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":24334}}}],"partialFingerprints":{"codehealthFindingId/v1":"f281e74dacc0469945407ddd080d15ab273deccf375abce3c2f56a488aa45b1e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (99\u2013100 lines \u00D7 2): python/pyspark/pandas/frame.py:6315-6414 | python/pyspark/pandas/series.py:2130-2228 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:6315\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6315}}}],"partialFingerprints":{"codehealthFindingId/v1":"af0fa37ba38bd31710c13d6f13fbbdf53e0a3a2a2c4c3b3ff0a8363080418a37"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (83\u201392 lines \u00D7 3): python/pyspark/pandas/generic.py:1867-1954 | python/pyspark/pandas/generic.py:1971-2053 | python/pyspark/pandas/generic.py:2198-2289 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060numeric_only\u0060 to \u0060bool = False\u0060 in one and \u0060bool = None\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1867}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ca4cc2b1653c8d2eec85147a839d0e2179710553944a18997ba7acfe7b8b31d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (86\u201388 lines \u00D7 2): python/pyspark/pandas/generic.py:1307-1394 | python/pyspark/pandas/generic.py:1416-1501 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/generic.py:1307\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1307}}}],"partialFingerprints":{"codehealthFindingId/v1":"d020575b8af6fc0b7736fd39df51b73b2e6fb73857c6bb55db0a07fdd3912960"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (66\u201384 lines \u00D7 2): python/pyspark/pandas/indexes/base.py:1425-1490 | python/pyspark/pandas/indexes/multi.py:745-828 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1425}}}],"partialFingerprints":{"codehealthFindingId/v1":"184cec9329fe42d2a79f00738fec956fffe8e712e416cf4e90fbcc0e55d119c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (76\u201381 lines \u00D7 2): python/pyspark/pandas/frame.py:11444-11524 | python/pyspark/pandas/frame.py:11575-11650 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11444}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7f34effcf38cf598447f1709a3ef085056164db5146838dd1ae0e89f80ca542"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (75\u201376 lines \u00D7 2): python/pyspark/pandas/frame.py:5498-5573 | python/pyspark/pandas/frame.py:5668-5742 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5498}}}],"partialFingerprints":{"codehealthFindingId/v1":"edcdd040dbb51cced24df8b4fe4a4e49652def93e08cefaf71936a9cca3416c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (54\u201374 lines \u00D7 2): python/pyspark/sql/avro/functions.py:37-110 | python/pyspark/sql/avro/functions.py:131-184 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060jsonFormatSchema\u0060 to \u0060str\u0060 in one and \u0060str = \u0022\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/avro/functions.py"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa1ec190c84f2f6ef6118698c867b0cdb732e61e5573d7d350ca7d7b5f38d084"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (68 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:720-787 | python/pyspark/mllib/linalg/__init__.py:827-894 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":720}}}],"partialFingerprints":{"codehealthFindingId/v1":"116239cf87df116180a6601f89375ad8424c4323df8725f05632dbc46911a5d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (61\u201363 lines \u00D7 2): python/pyspark/sql/functions/builtin.py:23473-23533 | python/pyspark/sql/functions/builtin.py:23961-24023 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":23473}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b3fcac79501e96d04a65138c741f30597cec8e37a7ac6431e2445463d87b1c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (61 lines \u00D7 6): python/pyspark/sql/readwriter.py:358-477 | python/pyspark/sql/readwriter.py:814-878 | python/pyspark/sql/readwriter.py:972-1048 | python/pyspark/sql/streaming/readwriter.py:391-459 | python/pyspark/sql/streaming/readwriter.py:710-772 | python/pyspark/sql/streaming/readwriter.py:826-886 \u2014 there are 6 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 6 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/readwriter.py:358\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"50ac38a455b48e7b78a7751bd981cd3fba35bfebccac757bede73dd6af52c485"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (50\u201360 lines \u00D7 2): python/pyspark/sql/readwriter.py:1204-1263 | python/pyspark/sql/readwriter.py:2398-2447 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/readwriter.py:2398\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":1204}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6be620e1ba25675082be2595699fcb554dae9678c1e6c0744579e64299dc4b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (49\u201358 lines \u00D7 2): python/pyspark/sql/readwriter.py:121-169 | python/pyspark/sql/streaming/readwriter.py:126-183 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on. Note first that the copies are not typed on the same thing: \u0060SparkSession\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.session\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"116eaee528fc346d4c446bf60e6cdbcd65b832bebfafac9431b0c19296e96ee5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (56\u201364 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:563-626 | python/pyspark/mllib/linalg/__init__.py:630-685 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":563}}}],"partialFingerprints":{"codehealthFindingId/v1":"edad6b577b0fb5a932c70f6c2983a29d854de1fa4a62482ff1d992f22af383a9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (56 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:662-717 | python/pyspark/mllib/linalg/__init__.py:769-824 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060other\u0060 to \u0060Iterable[float]\u0060 in one and \u0060\u0022VectorLike\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":662}}}],"partialFingerprints":{"codehealthFindingId/v1":"8130437660d3bd7c1dfbf22da5f128cfc3d5ad5ecd224a957028893de9885e52"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (56 lines \u00D7 2): python/pyspark/pandas/groupby.py:2422-2477 | python/pyspark/pandas/groupby.py:2519-2574 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2422}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cc63d236e613a63837486c444c3a136c239fd38c7bf9bc50cf27fee62c9742e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (51\u201354 lines \u00D7 2): python/pyspark/sql/worker/create_data_source.py:40-90 | python/pyspark/sql/worker/write_into_data_source.py:53-106 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/sql/worker/create_data_source.py:94\u0060 calls \u0060read_bool\u0060 and \u0060python/pyspark/sql/worker/write_into_data_source.py:109\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/create_data_source.py"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ab384ddb496ffa48cd5111d75d8ca5b6d746f7e866083f62153b72733ee6ee9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (45\u201353 lines \u00D7 2): python/pyspark/pandas/groupby.py:844-888 | python/pyspark/pandas/groupby.py:1059-1111 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":844}}}],"partialFingerprints":{"codehealthFindingId/v1":"87548634cce2d66469f91857b7fd459a807a7d0c97c3163d51439fa74b2d0ff1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (47 lines \u00D7 3): python/pyspark/pandas/generic.py:1229-1282 | python/pyspark/pandas/generic.py:1522-1568 | python/pyspark/pandas/generic.py:1590-1637 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1229}}}],"partialFingerprints":{"codehealthFindingId/v1":"e270b40dcbb4ad0c4f5b269425349e582842ff44931fff6dded35ad3a200b348"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (46\u201347 lines \u00D7 2): python/pyspark/pandas/series.py:6602-6648 | python/pyspark/pandas/series.py:6678-6723 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":6602}}}],"partialFingerprints":{"codehealthFindingId/v1":"138e8254ba273c13e66fc79c5a65c81facccec9af7c244ed43e5f2f3d856e0e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44\u201346 lines \u00D7 2): python/pyspark/core/rdd.py:1234-1277 | python/pyspark/core/rdd.py:1312-1357 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":1234}}}],"partialFingerprints":{"codehealthFindingId/v1":"5157fa99de5a9518cd17945874b6a664ec75a372a55efda11080677e82f23941"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44\u201345 lines \u00D7 4): python/pyspark/sql/connect/functions/builtin.py:4370-4413 | python/pyspark/sql/connect/functions/builtin.py:4463-4507 | python/pyspark/sql/functions/builtin.py:28570-28613 | python/pyspark/sql/functions/builtin.py:28826-28869 \u2014 there are 4 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4370}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb8da320b0647ba433d28acc5f34b89dadb0d45886665b91e136d0824647ee12"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:363-406 | python/pyspark/mllib/linalg/__init__.py:418-461 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060other\u0060 to \u0060Iterable[float]\u0060 in one and \u0060\u0022VectorLike\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"51f9a705f07367bde1fa8f613b105547b7e64c93a9dafb5b7f41901be2281839"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (44 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1201-1244 | python/pyspark/mllib/linalg/__init__.py:1396-1439 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1201}}}],"partialFingerprints":{"codehealthFindingId/v1":"59f698ba3d59faf5f6fab6a2f3f11f0898a95501ff98895000ee9a61995c6d3e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (40\u201343 lines \u00D7 2): python/pyspark/pandas/groupby.py:4675-4714 | python/pyspark/pandas/groupby.py:4757-4799 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:4675\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4675}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb9416282c59d40c442d37fd4be6fd149df2774c2f14d6b097e43c1a7a780034"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (39\u201341 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:443-483 | python/pyspark/sql/connect/dataframe.py:1135-1173 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":443}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f18d453ace8cc8a6708a4718773a2f76c090b1e2678092cd0acae4555804955"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (38 lines \u00D7 2): python/pyspark/pandas/groupby.py:4716-4753 | python/pyspark/pandas/groupby.py:4801-4838 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:4716\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4716}}}],"partialFingerprints":{"codehealthFindingId/v1":"09a260f57d6b0f6c1b6171c2b4e879d35dec51bb97ae466dc91302cd5861a7d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (38 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1235-1272 | python/pyspark/sql/connect/dataframe.py:1016-1053 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1235}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2f23cae423f5b2bd19caaf6531a5f724a62a7a7b938bfc4e508ca3af85ca671"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (37 lines \u00D7 2): python/pyspark/pandas/groupby.py:2480-2516 | python/pyspark/pandas/groupby.py:2577-2613 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2480}}}],"partialFingerprints":{"codehealthFindingId/v1":"31b781652ad14ada7a072271acbb8366d3154758ea94af900a39bd5de941eb6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201336 lines \u00D7 2): python/pyspark/pandas/frame.py:1663-1698 | python/pyspark/pandas/groupby.py:4233-4255 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:1663\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1663}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e0386b0e2d094936551e6c0def74da38b65d1c539b47fb9d6ad726e0d2be19d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:106-140 | python/pyspark/mllib/linalg/__init__.py:117-151 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"e66586d3380cef0cb66003f9e3bff39a0dd850cd8c3241abc1ec5c1fc57732c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): python/pyspark/pipelines/api.py:175-209 | python/pyspark/pipelines/api.py:279-313 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pipelines/api.py:175\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"77158c7c98805eb1699de46d9d71447c4b3ef905474fb894cd64790681d0f415"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): python/pyspark/sql/connect/udf.py:81-115 | python/pyspark/sql/udf.py:118-152 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/udf.py\u0060 and \u0060python/pyspark/sql/udf.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 142 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/udf.py:81\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfb84c83a9cae4e9aa5bb892be53b59a05b4340da3371d13f5412857e392bcea"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (34 lines \u00D7 2): python/pyspark/pandas/frame.py:12739-12772 | python/pyspark/pandas/frame.py:12874-12907 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:12739\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12739}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3beb8667c33c192099ce238df861343d3a497f13c52fd8268c0548adfc98062"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (33\u201334 lines \u00D7 2): python/pyspark/sql/connect/udf.py:158-190 | python/pyspark/sql/udf.py:177-210 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/udf.py\u0060 and \u0060python/pyspark/sql/udf.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 142 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4eeb84106c0e4b1ea9f8611733c3425934a8057dc2d694b7995fb8e166588b8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (34 lines \u00D7 2): python/pyspark/sql/connect/udf.py:255-288 | python/pyspark/sql/udf.py:714-747 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/udf.py\u0060 and \u0060python/pyspark/sql/udf.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 142 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: \u0060Column\u0060 names \u0060pyspark.sql.column\u0060 in one and \u0060pyspark.sql.connect.column\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"23a3549a12940a394ec8af5b973e0ecb50e376a4c421f182433b99d0c864c7dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (32 lines \u00D7 2): python/pyspark/pandas/strings.py:2074-2105 | python/pyspark/pandas/strings.py:2234-2265 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/strings.py"},"region":{"startLine":2074}}}],"partialFingerprints":{"codehealthFindingId/v1":"43f7d2891f734cf9d39bf0f62b63f7887b975756e5b04e89e7706ce8daf67993"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): python/pyspark/sql/connect/udf.py:316-346 | python/pyspark/sql/udf.py:889-919 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/udf.py\u0060 and \u0060python/pyspark/sql/udf.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 142 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd442194dda7c4249b54098dd7451a7ec5d409979bc2399d47922b8d16cabf09"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): python/pyspark/testing/pandasutils.py:212-242 | python/pyspark/testing/pandasutils.py:267-297 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"23df5efeed41bfa1067763f58244f8a6a46b7d52889745860ec37b25bb4ecc15"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 4): python/pyspark/sql/connect/readwriter.py:666-695 | python/pyspark/sql/connect/readwriter.py:712-741 | python/pyspark/sql/readwriter.py:1627-1656 | python/pyspark/sql/readwriter.py:1711-1740 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/readwriter.py\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 113 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":666}}}],"partialFingerprints":{"codehealthFindingId/v1":"256b8f113b31036733f107d519cb9acc42d2a4cb319a8778e8da87ad7df87436"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:752-780 | python/pyspark/eval_handlers/_stateful.py:1037-1065 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":752}}}],"partialFingerprints":{"codehealthFindingId/v1":"f337f83ae911e7a35c7bc500c1ec2e383f8fc8b7b0eeff5f00255d39f77202c2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26\u201328 lines \u00D7 3): python/pyspark/ml/connect/tuning.py:487-514 | python/pyspark/ml/tuning.py:926-952 | python/pyspark/ml/tuning.py:1506-1531 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/tuning.py\u0060 and \u0060python/pyspark/ml/tuning.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ef1521f168d9b2a67d80a544d2bff18f1034014ef9714b262ac78d2c6609d67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27\u201328 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1694-1721 | python/pyspark/sql/connect/dataframe.py:1751-1777 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1694}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d732ce13083413fe42ceca6b329edad606ac0880ef4d8c3d9b115070daee023"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201327 lines \u00D7 3): python/pyspark/pandas/frame.py:1675-1701 | python/pyspark/pandas/groupby.py:4246-4258 | python/pyspark/pandas/groupby.py:4455-4468 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:1675\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/pandas/groupby.py:4259\u0060 calls \u0060col\u0060 and \u0060python/pyspark/pandas/frame.py:1702\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1675}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8f1156fdb308ddca61f748f4dca481658a10aab7a3ae2ef0b2c5a41e7707238"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27 lines \u00D7 2): python/pyspark/pandas/plot/matplotlib.py:431-457 | python/pyspark/pandas/plot/matplotlib.py:552-578 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"f52d4a9a222a713620c091bf955e912cf7983c8899384b006a5e8639613d54b7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25\u201327 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:166-190 | python/pyspark/sql/functions/builtin.py:26594-26620 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"671c25785d94d9be80d288fe16bd2931d73fd2081654f2426542516b8de427f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:2838-2864 | python/pyspark/sql/functions/builtin.py:16712-16738 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on. Note first that the copies are not typed on the same thing: \u0060Column\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.column\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2838}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7762a0b1960cdf5c63021820ca9bd4fa0cee4f75100e7ae20e46bbd2c3ca78c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27 lines \u00D7 2): python/pyspark/sql/connect/protobuf/functions.py:39-65 | python/pyspark/sql/connect/protobuf/functions.py:78-104 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/protobuf/functions.py"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"da79a7a0ed3b7dc5c19db68efa937048c95473f0719484e67a3c552d7d1c82b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:538-563 | python/pyspark/eval_handlers/_stateful.py:859-884 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":538}}}],"partialFingerprints":{"codehealthFindingId/v1":"f78e6496ce88dfc3610d0c7e5026e480b28cbeb4196e50464ee275f6eb1fe2eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): python/pyspark/pandas/groupby.py:4287-4312 | python/pyspark/pandas/groupby.py:4497-4522 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:4287\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4287}}}],"partialFingerprints":{"codehealthFindingId/v1":"4abaf1223be32a4661b889048744781d00d6c7285ee51e78d15313fa518f188f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): python/pyspark/pandas/plot/core.py:352-380 | python/pyspark/sql/plot/core.py:761-789 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"158a2058f10d5b6f026218525607f8cb61295306ec9ee8593f0b54ca56a5d966"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): python/pyspark/pandas/plot/core.py:432-457 | python/pyspark/sql/plot/core.py:543-568 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"03978e63b88f14e7c980e79d8120f396a34f4cab32a03345de2f05f45f05739d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): python/pyspark/pandas/internal.py:767-791 | python/pyspark/pandas/internal.py:795-819 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":767}}}],"partialFingerprints":{"codehealthFindingId/v1":"741f7acb7ddf2a35d34a786a50ad98e08daec1ad4bda86479e600f527bc54310"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1751-1775 | python/pyspark/sql/connect/dataframe.py:1714-1738 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1751}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f71c9b633d588b38b8d0af8875b5a93b532c0a343c06ba1cf9c61a2a688dfa9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): python/pyspark/sql/connect/dataframe.py:1406-1430 | python/pyspark/sql/connect/dataframe.py:1485-1509 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1406}}}],"partialFingerprints":{"codehealthFindingId/v1":"eee1082573692a64ad2c72db7bb3c2505f58fc9496ed1b855b815c5103f42766"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:226-250 | python/pyspark/sql/connect/readwriter.py:441-465 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/readwriter.py:226\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"c69b035f275a0851ecf77b5874d4f5eb0465f640edbb733d494fc71c843ff2c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24\u201325 lines \u00D7 2): python/pyspark/sql/pandas/types.py:1229-1253 | python/pyspark/sql/pandas/types.py:1584-1607 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/pandas/types.py:1229\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":1229}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f4812d9da7772d72e6aa0a4c65326d9cea2a26b7b1eea51d4bed498db9bfc13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 4): python/pyspark/sql/connect/functions/builtin.py:4586-4609 | python/pyspark/sql/connect/functions/builtin.py:4644-4667 | python/pyspark/sql/functions/builtin.py:29253-29276 | python/pyspark/sql/functions/builtin.py:29416-29439 \u2014 there are 4 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4586}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0af5c48f950594be1d77cc5e5501af16b7b842ee812c788b923fd412c5b9212"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 3): python/pyspark/sql/worker/data_source_pushdown_filters.py:119-167 | python/pyspark/sql/worker/plan_data_source_read.py:279-319 | python/pyspark/sql/worker/python_streaming_sink_runner.py:43-66 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/worker/data_source_pushdown_filters.py:119\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/data_source_pushdown_filters.py"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"4262f0538c41175f277706342e3a71154d1845fdd254207c1ae548ec00234530"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201324 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:515-535 | python/pyspark/eval_handlers/_stateful.py:722-745 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_stateful.py:722\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e235e377e40506d80a8327bd3b5ffea6c88fe706ddbf0131d2ce21265bbff84"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201324 lines \u00D7 2): python/pyspark/pandas/frame.py:9054-9074 | python/pyspark/pandas/namespace.py:3524-3547 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/namespace.py:3524\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9054}}}],"partialFingerprints":{"codehealthFindingId/v1":"beb3c56822eff45616110fcb1bac2de3a1e72e6cfd454ee6ea1631f2e5378862"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 3): python/pyspark/sql/connect/streaming/readwriter.py:201-223 | python/pyspark/sql/connect/streaming/readwriter.py:372-394 | python/pyspark/sql/connect/streaming/readwriter.py:430-452 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/streaming/readwriter.py:201\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"2920213778e81ce20afe280fd4b6e32bf45f26e6d6dfcba8ed186fff2c1a3e83"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1247-1269 | python/pyspark/mllib/linalg/__init__.py:1442-1464 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1247}}}],"partialFingerprints":{"codehealthFindingId/v1":"c91faeb5d2049752d39c222ae4134f31b1bff563ee4b686141865ea5fd6b28d0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): python/pyspark/pandas/indexes/multi.py:527-549 | python/pyspark/pandas/indexes/multi.py:574-596 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/indexes/multi.py:527\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":527}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa9635655536e3b87e05ce997e64ed56637a14c97906e123f8678d5d1320fd13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): python/pyspark/pandas/series.py:4625-4647 | python/pyspark/pandas/series.py:4744-4766 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":4625}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c1405f64da2b5fa3b75b6e9878f3a11c4b813c19e5bb7b41110dfda03c8aef7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): python/pyspark/pandas/series.py:6653-6675 | python/pyspark/pandas/series.py:6728-6750 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":6653}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7026acd57d320343e07515aa2da58bf93acdf31d716ebeb94c8ca06d88656e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:240-262 | python/pyspark/sql/connect/dataframe.py:2179-2201 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"057802bf19be12b9956f7a2376413ba37ec87aa0b19a5995d19ed7f6eaecb6ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 4): python/pyspark/sql/pandas/typehints.py:63-84 | python/pyspark/sql/pandas/typehints.py:222-243 | python/pyspark/sql/pandas/typehints.py:415-436 | python/pyspark/sql/pandas/typehints.py:508-529 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/sql/pandas/typehints.py:246\u0060 calls \u0060all\u0060 and \u0060python/pyspark/sql/pandas/typehints.py:439\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/typehints.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8196fd928257ad261878440e1534b43f389295d4aef4b5bcd89e9045e5b5456"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201322 lines \u00D7 4): python/pyspark/sql/streaming/python_streaming_source_runner.py:227-248 | python/pyspark/sql/worker/data_source_pushdown_filters.py:153-173 | python/pyspark/sql/worker/plan_data_source_read.py:305-325 | python/pyspark/sql/worker/python_streaming_sink_runner.py:52-72 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 4 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/python_streaming_source_runner.py"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea3fe285c38738c77e3917bcbe93b675de6bc08d1ea8a742291b936340a53b74"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 3): python/pyspark/sql/profiler.py:508-529 | python/pyspark/sql/profiler.py:532-553 | python/pyspark/sql/profiler.py:556-577 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/profiler.py"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"c620fe96b25077e7105c589ffc53c375b7d787f8a7c84ccbc19c2b46ab33123d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/eval_handlers/_arrow.py:157-178 | python/pyspark/eval_handlers/_arrow.py:225-246 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/eval_handlers/_arrow.py:249\u0060 calls \u0060from_batches\u0060 and \u0060python/pyspark/eval_handlers/_arrow.py:181\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"1150e12e960c2cb3457fc9532387ef14adc073f61514bb7fb01a0f2e65205b90"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:990-1011 | python/pyspark/mllib/linalg/__init__.py:1166-1187 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":990}}}],"partialFingerprints":{"codehealthFindingId/v1":"30b0b539a6063d5eed5a422184cabde7fbcc2809497a0b7e71a6cddf08bdbab0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/pandas/data_type_ops/num_ops.py:566-587 | python/pyspark/pandas/data_type_ops/num_ops.py:704-725 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":566}}}],"partialFingerprints":{"codehealthFindingId/v1":"e17b5003856b6650143f2bde0f0bf9792fb077c8dacdaeb0499ee26619edcc99"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/pandas/frame.py:7720-7741 | python/pyspark/pandas/indexes/base.py:1391-1412 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:7720\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7720}}}],"partialFingerprints":{"codehealthFindingId/v1":"08bdb9434502783b0d66611b697eef1b8717f6353e40a0c006219d043fcee3e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/pandas/plot/plotly.py:220-241 | python/pyspark/sql/plot/plotly.py:143-164 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/plotly.py\u0060 and \u0060python/pyspark/sql/plot/plotly.py\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 54 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb64726b13ec058e1f87223b1979f7856dcee0c9f20e392842816781c5a87285"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 2): python/pyspark/sql/profiler.py:377-398 | python/pyspark/sql/profiler.py:470-494 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/profiler.py"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"1eb71dfed90a32769af29469972447f585c37a078350d154ce0b6ec3269e03ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): python/pyspark/ml/connect/pipeline.py:187-207 | python/pyspark/ml/pipeline.py:121-141 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/pipeline.py\u0060 and \u0060python/pyspark/ml/pipeline.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060dataset\u0060 to \u0060Union[DataFrame, pd.DataFrame]\u0060 in one and \u0060DataFrame\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b9e2ef3f0607c3dbd922976e5e338b1d07a72c047adc9d40691adc7ce98b1a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): python/pyspark/sql/connect/group.py:275-295 | python/pyspark/sql/pandas/group_ops.py:96-116 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":275}}}],"partialFingerprints":{"codehealthFindingId/v1":"d60431551679cec4412344d9d39b16c851ae6498253cec373619d6f2e75fc041"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): python/pyspark/sql/connect/group.py:316-336 | python/pyspark/sql/connect/group.py:503-523 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"e60631ca1eb85c68f9eb10a05c6318f5fc4cd72e7696ae04452464c233c41c90"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 4): python/pyspark/sql/avro/functions.py:204-223 | python/pyspark/sql/connect/avro/functions.py:91-110 | python/pyspark/sql/connect/protobuf/functions.py:116-135 | python/pyspark/sql/protobuf/functions.py:297-316 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 4 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/avro/functions.py"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"861a9adc73ed07fa246ee8d4a617c9fc96d6422db58efdd2d283230fea465d07"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): python/pyspark/eval_handlers/_pandas.py:350-369 | python/pyspark/eval_handlers/_pandas.py:513-532 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9c3935cf800b09fbc47b0e32badc7cd844af1370328dc78d574878acd91f759"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1179-1198 | python/pyspark/mllib/linalg/__init__.py:1374-1393 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1179}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f5e631b4855c8d33a0a2e82f7cd42785e3852201335828cca62f5fb09939684"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1289-1308 | python/pyspark/mllib/linalg/__init__.py:1486-1505 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1289}}}],"partialFingerprints":{"codehealthFindingId/v1":"97e507a78e4dee86dc6939c22dc0b0334f7c1c9f24deffcf1bb40a26b9f23524"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 2): python/pyspark/pandas/frame.py:9007-9026 | python/pyspark/pandas/namespace.py:3467-3485 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:9007\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9007}}}],"partialFingerprints":{"codehealthFindingId/v1":"48127e5c9720471bc14e1e408ddbe3430881e6d593ae9369c002a71c1bb82ec5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:838-856 | python/pyspark/eval_handlers/_stateful.py:1016-1034 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":838}}}],"partialFingerprints":{"codehealthFindingId/v1":"47377fbfcf626bb0600ffeabc3ab82626d7fe440336312a30fc9a83cbdc79837"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 2): python/pyspark/pandas/frame.py:8979-8997 | python/pyspark/pandas/namespace.py:3418-3434 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/pandas/namespace.py:3416\u0060 calls \u0060isinstance\u0060, \u0060ValueError\u0060 and \u0060python/pyspark/pandas/frame.py:8978\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8979}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5f97e6e88cb4ed6d88c71d4fa865b3436aa0e9597d552f3d6a292d5fcaa9873"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 2): python/pyspark/pandas/frame.py:10951-10967 | python/pyspark/pandas/frame.py:10983-11001 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10951}}}],"partialFingerprints":{"codehealthFindingId/v1":"191d0b443373c95f9d182afca4ebf42484035a242dcedac685ef46dc44e14f3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): python/pyspark/pipelines/api.py:87-105 | python/pyspark/pipelines/api.py:445-463 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"42f89d116a4e80d53238ab9d5ff0fbf997935207c68bd5e2b44687a8dee29fa6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 2): python/pyspark/shuffle.py:356-374 | python/pyspark/shuffle.py:803-819 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"20ab50efe3acccbb282e7d55ee258cf0067fdcb036941437fec267ae29301ba6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): python/pyspark/sql/pandas/conversion.py:1018-1036 | python/pyspark/sql/pandas/conversion.py:1098-1116 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note first that the copies are not typed on the same thing: \u0060DataFrame\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.dataframe\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/conversion.py"},"region":{"startLine":1018}}}],"partialFingerprints":{"codehealthFindingId/v1":"94002e2bc6fc524bb7c3f78d96f5e825276b9b3b896e81588177e740c6a2e408"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201318 lines \u00D7 4): python/pyspark/pandas/accessors.py:412-427 | python/pyspark/pandas/accessors.py:743-760 | python/pyspark/pandas/frame.py:3320-3335 | python/pyspark/pandas/groupby.py:2162-2177 \u2014 there are 4 copies across 3 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/accessors.py:412\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":412}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1ecab72c1904e663ed6b30617bdeb7a2622dc8340a3a0cf4daf8edae0921706"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:827-844 | python/pyspark/mllib/linalg/__init__.py:947-964 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d47941ab74ae308138b8a9e8c98f1c3ad919a18253e7052f94adf08aff6cd05"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201318 lines \u00D7 2): python/pyspark/ml/tuning.py:1164-1181 | python/pyspark/ml/tuning.py:1724-1740 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/ml/tuning.py:1164\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1164}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a349a94568ecd7fb68d129b1f272a35636e39bda5e71135efb6bc11f711ba77"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): python/pyspark/pandas/groupby.py:4197-4214 | python/pyspark/pandas/groupby.py:4395-4412 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:4197\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4197}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad55c4571853f346eb6db9c4007e7371e6cc8417a292367284f8c097a56545e8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): python/pyspark/sql/avro/functions.py:98-115 | python/pyspark/sql/connect/avro/functions.py:36-53 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: \u0060ColumnOrName\u0060 names \u0060pyspark.sql._typing\u0060 in one and \u0060pyspark.sql.connect._typing\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/avro/functions.py"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"40338383ca59f40e1ed59aa27e9b3e88ba42bd66d1ef3aea11d1e2f34965c49e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201318 lines \u00D7 2): python/pyspark/sql/catalog.py:364-379 | python/pyspark/sql/catalog.py:695-712 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/catalog.py"},"region":{"startLine":364}}}],"partialFingerprints":{"codehealthFindingId/v1":"674fc0106c25c2fa56fbf42403ff5111fda48255e830ce938ffee69a822bba45"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): python/pyspark/sql/connect/types.py:414-431 | python/pyspark/sql/connect/types.py:441-458 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f0368f0c9f709c087c91b091466a3c65f470d20fd8e52a15cf7894b7496c804"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 3): python/pyspark/sql/readwriter.py:497-513 | python/pyspark/sql/readwriter.py:906-922 | python/pyspark/sql/readwriter.py:1062-1078 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/readwriter.py"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4ee94b1982a7c9fb9cbe8239cc89f32346df233c6c3cc34d68db5496a282a57"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:246-263 | python/pyspark/mllib/linalg/__init__.py:257-274 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"42bc053db8894479f8c906e404a2183d96830c6f88945aa954503de32b32207a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201317 lines \u00D7 2): python/pyspark/pandas/frame.py:9141-9157 | python/pyspark/pandas/namespace.py:3587-3601 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9141}}}],"partialFingerprints":{"codehealthFindingId/v1":"c63f290d0dc7c7e8d00d066179e85ca67ad65978e83269449b714c3651b15a60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): python/pyspark/pandas/frame.py:12720-12736 | python/pyspark/pandas/frame.py:12855-12871 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:12720\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12720}}}],"partialFingerprints":{"codehealthFindingId/v1":"5149cbb41bb8629917754ebb06acd1dbff8d8d247eefb17e658477126fc0384f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201317 lines \u00D7 2): python/pyspark/shuffle.py:376-392 | python/pyspark/shuffle.py:830-845 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":376}}}],"partialFingerprints":{"codehealthFindingId/v1":"f865417c5caf8abf6cde4be358164e7357e7e785fba93c8ba1c5808c54bd5ea9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): python/pyspark/sql/streaming/list_state_client.py:82-98 | python/pyspark/sql/streaming/map_state_client.py:225-241 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/list_state_client.py:82\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"1605ca1c6c71ccfa238bf235aeadcb1dd0071591fb64457b43331134b9d64cbe"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 12): python/pyspark/sql/connect/readwriter.py:221-236 | python/pyspark/sql/connect/readwriter.py:370-385 | python/pyspark/sql/connect/readwriter.py:436-451 | python/pyspark/sql/connect/streaming/readwriter.py:198-213 | python/pyspark/sql/connect/streaming/readwriter.py:369-384 | python/pyspark/sql/connect/streaming/readwriter.py:427-442 | python/pyspark/sql/readwriter.py:476-491 | python/pyspark/sql/readwriter.py:885-900 | python/pyspark/sql/readwriter.py:1041-1056 | python/pyspark/sql/streaming/readwriter.py:455-470 | python/pyspark/sql/streaming/readwriter.py:776-791 | python/pyspark/sql/streaming/readwriter.py:879-894 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/connect/streaming/readwriter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 71 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/readwriter.py:221\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/sql/connect/readwriter.py:238\u0060 calls \u0060isinstance\u0060, \u0060load\u0060 and \u0060python/pyspark/sql/connect/readwriter.py:388\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"618a233390929d876fd685200da4188766406af97389b37ebae7596ff346aabb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 3): python/pyspark/pandas/namespace.py:1150-1165 | python/pyspark/pandas/plot/matplotlib.py:766-781 | python/pyspark/pandas/plot/matplotlib.py:930-945 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/namespace.py:1150\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1150}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a5c498d4057243e6e1f25480012be342d451bf4f70761c45c73ef3836613d63"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201316 lines \u00D7 2): dev/merge_spark_pr.py:3450-3465 | dev/merge_spark_pr.py:3539-3552 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060dev/merge_spark_pr.py:3450\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060dev/merge_spark_pr.py:3467\u0060 calls \u0060get_input\u0060 and \u0060dev/merge_spark_pr.py:3553\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3450}}}],"partialFingerprints":{"codehealthFindingId/v1":"11dca1f17294ed2316a00cd04bf66d5277707adeb312e1ad9dc8b702d6277fa6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201316 lines \u00D7 2): python/pyspark/ml/tuning.py:1122-1137 | python/pyspark/ml/tuning.py:1684-1698 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/ml/tuning.py:1122\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":1122}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9cd554a42ea520402fb2bf3d2f45bb8d9afa18ab93dc2a8d3b8d285767d374d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201316 lines \u00D7 2): python/pyspark/mllib/classification.py:392-407 | python/pyspark/mllib/regression.py:360-373 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/mllib/classification.py:392\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"63c005eaff4b7cc0aaf192ca665cf14b99320e614a0be719d39c895f727a035b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): python/pyspark/pandas/testing.py:148-163 | python/pyspark/pandas/testing.py:244-259 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/testing.py"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"377925bbe14a110786802fb9b32d02a12bc5152d9cc439d34ead376023df05fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1339-1354 | python/pyspark/sql/connect/dataframe.py:1234-1249 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. Note first that the copies are not typed on the same thing: \u0060Observation\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.connect.observation\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1339}}}],"partialFingerprints":{"codehealthFindingId/v1":"e908c96cd5d6fcfd5493125ff76f7fba17094f56207ee8b34eb7328c6d90953d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): python/pyspark/sql/connect/observation.py:36-51 | python/pyspark/sql/observation.py:90-105 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/observation.py"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"50fdcd81940c64140811e24a09d76e0770e4a144a2efc9f248cd8d510a602810"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): python/pyspark/sql/streaming/stateful_processor_util.py:76-91 | python/pyspark/sql/streaming/stateful_processor_util.py:124-139 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/sql/streaming/stateful_processor_util.py:92\u0060 calls \u0060set_handle_state\u0060 and \u0060python/pyspark/sql/streaming/stateful_processor_util.py:140\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_util.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"b96ed7c9f43c3817e0217a77f01341efb059ebd03a3ccb1d6e3bfa44c4a8ea47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 17): python/pyspark/pandas/testing.py:151-165 | python/pyspark/pandas/testing.py:247-261 | python/pyspark/sql/connect/readwriter.py:221-235 | python/pyspark/sql/connect/readwriter.py:370-384 | python/pyspark/sql/connect/readwriter.py:436-450 | python/pyspark/sql/connect/readwriter.py:890-904 | python/pyspark/sql/connect/streaming/readwriter.py:198-212 | python/pyspark/sql/connect/streaming/readwriter.py:369-383 | python/pyspark/sql/connect/streaming/readwriter.py:427-441 | python/pyspark/sql/readwriter.py:476-490 | python/pyspark/sql/readwriter.py:885-899 | python/pyspark/sql/readwriter.py:1041-1055 | python/pyspark/sql/readwriter.py:2232-2246 | python/pyspark/sql/streaming/listener.py:460-474 | python/pyspark/sql/streaming/readwriter.py:455-469 | python/pyspark/sql/streaming/readwriter.py:776-790 | python/pyspark/sql/streaming/readwriter.py:879-893 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/connect/streaming/readwriter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 71 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/testing.py:151\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/testing.py"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"a37cb869955633ec9fa97686970d21801834422b16b0b6b51c5e3b3c7b9c7513"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 14): python/pyspark/sql/connect/readwriter.py:210-224 | python/pyspark/sql/connect/readwriter.py:351-365 | python/pyspark/sql/connect/readwriter.py:430-444 | python/pyspark/sql/connect/readwriter.py:887-901 | python/pyspark/sql/connect/streaming/readwriter.py:189-203 | python/pyspark/sql/connect/streaming/readwriter.py:352-366 | python/pyspark/sql/connect/streaming/readwriter.py:421-435 | python/pyspark/sql/readwriter.py:464-478 | python/pyspark/sql/readwriter.py:865-879 | python/pyspark/sql/readwriter.py:1035-1049 | python/pyspark/sql/readwriter.py:2229-2243 | python/pyspark/sql/streaming/readwriter.py:446-460 | python/pyspark/sql/streaming/readwriter.py:759-773 | python/pyspark/sql/streaming/readwriter.py:873-887 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/connect/streaming/readwriter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 71 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/readwriter.py:210\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/sql/readwriter.py:2228\u0060 calls \u0060mode\u0060 and \u0060python/pyspark/sql/readwriter.py:863\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5cee45f9d735e1d5d43eb5db1a096174f2099be259b7c6502cb0c4682c9df91"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 8): python/pyspark/sql/connect/functions/builtin.py:4388-4402 | python/pyspark/sql/connect/functions/builtin.py:4482-4496 | python/pyspark/sql/connect/functions/builtin.py:4592-4606 | python/pyspark/sql/connect/functions/builtin.py:4650-4664 | python/pyspark/sql/functions/builtin.py:28588-28602 | python/pyspark/sql/functions/builtin.py:28844-28858 | python/pyspark/sql/functions/builtin.py:29259-29273 | python/pyspark/sql/functions/builtin.py:29422-29436 \u2014 there are 8 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 8 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4388}}}],"partialFingerprints":{"codehealthFindingId/v1":"8aa4b686fc73b41ece49101932a48bfc57ae88e98aba73192791009b67881215"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201315 lines \u00D7 4): python/pyspark/sql/streaming/list_state_client.py:48-60 | python/pyspark/sql/streaming/map_state_client.py:58-70 | python/pyspark/sql/streaming/map_state_client.py:106-120 | python/pyspark/sql/streaming/value_state_client.py:44-56 \u2014 there are 4 copies across 3 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb14c531a70c965d9ecf318baeb89c5e5d3b61897e5e41ce6a06fd2f603b750d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 3): python/pyspark/eval_handlers/_pandas.py:352-366 | python/pyspark/eval_handlers/_pandas.py:428-441 | python/pyspark/eval_handlers/_pandas.py:515-529 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_pandas.py:352\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"c049aa79421bafbb0d6c502035a466190ac23e6b78026d9002db7b24eb4b2389"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 3): python/pyspark/sql/connect/functions/builtin.py:2429-2443 | python/pyspark/sql/connect/functions/builtin.py:2450-2464 | python/pyspark/sql/connect/functions/builtin.py:2471-2485 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2429}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e2268e1e75f7161dd818b3e62156eae7d91bf7709f88dfc94b645e19cf154a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:468-482 | python/pyspark/eval_handlers/_stateful.py:639-653 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":468}}}],"partialFingerprints":{"codehealthFindingId/v1":"37ad15044f5dcb0d702625b549cc16de127d82eae6407ac9f6ce2477fd26f37e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/ml/common.py:87-101 | python/pyspark/mllib/common.py:77-91 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060sc\u0060 to \u0060\u0022SparkContext\u0022\u0060 in one and \u0060SparkContext\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"68e906d439cb3a4851d2e1d1f351775b45012d8064a2c9870c9e285b58715f0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:88-102 | python/pyspark/mllib/linalg/__init__.py:99-113 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"bee6ed87b00c8f5681a7b62560ad1ae28f75d42e160696033a707b76f1bd584e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/pandas/frame.py:8444-8458 | python/pyspark/pandas/indexes/multi.py:455-469 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:8444\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8444}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4135992008e282f8dfc31700fee06e51ca8ce31c3edac5f6883a6c01fdbd6cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/pandas/plot/matplotlib.py:755-769 | python/pyspark/pandas/plot/matplotlib.py:914-928 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/matplotlib.py:755\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":755}}}],"partialFingerprints":{"codehealthFindingId/v1":"b34107f7be0add30ca8d093e516afb9b14dccd06b8e0d8c441ded2c77748a9f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:2211-2225 | python/pyspark/sql/connect/dataframe.py:2609-2623 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":2211}}}],"partialFingerprints":{"codehealthFindingId/v1":"481d64f1ca670b955751142c6e9644962fc3d12243de2019e4d5fc2cba008e52"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:2012-2026 | python/pyspark/sql/connect/functions/builtin.py:2040-2054 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2012}}}],"partialFingerprints":{"codehealthFindingId/v1":"c72ca4975e4b01197bcdc09c592d2c8f9335f2c8b6a3d2e3f92981bfb17b6e18"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/sql/connect/group.py:555-569 | python/pyspark/sql/connect/group.py:586-600 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/group.py:555\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":555}}}],"partialFingerprints":{"codehealthFindingId/v1":"196d5052a046960e1b6b924720b444dc2dec1a4c78ba19bededadec218cb761d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:926-940 | python/pyspark/sql/readwriter.py:2311-2325 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/readwriter.py\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 113 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":926}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0e76b234312a38b822b536ccdc7592b484be9383584b3e90c82b4df0cceb140"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): python/pyspark/sql/streaming/listener.py:462-476 | python/pyspark/sql/streaming/listener.py:740-754 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/listener.py:462\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/listener.py"},"region":{"startLine":462}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1286379ed9fab594ef78decd438676fbc3f6f772c735d1aa1ee9bddc87c9d60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3): python/pyspark/sql/pandas/types.py:338-351 | python/pyspark/sql/pandas/types.py:355-368 | python/pyspark/sql/pandas/types.py:372-385 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":338}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b610fd5c3deb0bd8899dd3af4cacbd7148b1ec9bee7983ce462e16396a606c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/ml/common.py:151-164 | python/pyspark/mllib/common.py:161-174 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"f59f9ec852650b0196857475206f6ff5fd0ddcf49fb1ebbb28f436ab06c100ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/ml/connect/functions.py:53-66 | python/pyspark/sql/connect/tvf.py:138-151 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/functions.py"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef2bc50f88df29523db82af41991c4f40e14eab83d5e2d020abb59836f544a6e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 2): python/pyspark/ml/feature.py:4828-4840 | python/pyspark/ml/feature.py:4871-4884 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/ml/feature.py:4828\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/feature.py"},"region":{"startLine":4828}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a6a1e14fba0d521baca24996da29188f97578f800790cbb835ce83f06ed49c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/pandas/frame.py:9085-9098 | python/pyspark/pandas/namespace.py:3551-3564 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9085}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a2c95234de94b2ec01378e1bcc11a361061f67f1eb9d506b5420d6f4f4424b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u201314 lines \u00D7 2): python/pyspark/pandas/frame.py:12704-12717 | python/pyspark/pandas/frame.py:12845-12852 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":12704}}}],"partialFingerprints":{"codehealthFindingId/v1":"727d66ec4b4e62c3ec6f646c94b3553ebb9c788374da0dba83430a8fc42f3b83"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/pandas/namespace.py:4074-4087 | python/pyspark/pandas/spark/accessors.py:1250-1263 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/namespace.py:4074\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":4074}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4e0c10af0073a4be14141274631ed8d699214d2c122593a330ce2928e7640a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201314 lines \u00D7 2): python/pyspark/pandas/plot/core.py:315-328 | python/pyspark/sql/plot/core.py:726-737 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/core.py:315\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":315}}}],"partialFingerprints":{"codehealthFindingId/v1":"2327644276ba35f685b90f39a453ff6c015f2a6a594cb1990ea497e643602994"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:270-283 | python/pyspark/sql/readwriter.py:689-702 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/readwriter.py\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 113 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: \u0060DataFrame\u0060 names \u0060pyspark.sql.connect.dataframe\u0060 in one and \u0060pyspark.sql.dataframe\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":270}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7e86f0f5804850e64873416028e954c5deb8b19a9de76230fd1bdf6bd4fe0f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:892-905 | python/pyspark/sql/connect/readwriter.py:928-941 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/readwriter.py:892\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":892}}}],"partialFingerprints":{"codehealthFindingId/v1":"3275a2bfc4e20f682899e33ce0396c53876af18c18bf1feb9b3deb3c00b202f3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 6): python/pyspark/pandas/generic.py:1274-1286 | python/pyspark/pandas/generic.py:1560-1572 | python/pyspark/pandas/generic.py:1629-1641 | python/pyspark/pandas/generic.py:1946-1958 | python/pyspark/pandas/generic.py:2045-2057 | python/pyspark/pandas/generic.py:2281-2293 \u2014 all 6 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/generic.py:1274\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1274}}}],"partialFingerprints":{"codehealthFindingId/v1":"662285dcb41a164126a000289a9db2319b0ccfef197dac509656f5676308091b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): python/pyspark/pandas/plot/plotly.py:204-216 | python/pyspark/pandas/plot/plotly.py:226-238 | python/pyspark/sql/plot/plotly.py:149-161 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/plotly.py\u0060 and \u0060python/pyspark/sql/plot/plotly.py\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 54 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/plotly.py:204\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a00a060e4fda7148296d823f524b70100510d7cc79eeea7004cbc249d43adfb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): python/pyspark/sql/connect/client/core.py:2136-2148 | python/pyspark/sql/connect/client/core.py:2152-2164 | python/pyspark/sql/connect/client/core.py:2168-2180 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2136}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1c4af18449fb18403116ca5f2d75e5cd04448878572554a66825314814b405d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 3): python/pyspark/sql/pandas/types.py:1233-1245 | python/pyspark/sql/pandas/types.py:1555-1566 | python/pyspark/sql/pandas/types.py:1588-1599 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/pandas/types.py:1233\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":1233}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1da917a8c12d8c8eb6b253e5eedb82a213119d904bd4976f600bbb6d8f53dd8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/eval_handlers/_pandas.py:555-567 | python/pyspark/eval_handlers/_pandas.py:659-671 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":555}}}],"partialFingerprints":{"codehealthFindingId/v1":"f644bd3a933f047445541775281b5efdf58e7801b9427893e6c94d570c4e1db6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/eval_handlers/_stateful.py:438-450 | python/pyspark/eval_handlers/_stateful.py:589-601 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":438}}}],"partialFingerprints":{"codehealthFindingId/v1":"90c2f3c322705445ff0168260d5e9e19396fe9376efca54f4c518f9a994fe63b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/mllib/evaluation.py:70-82 | python/pyspark/mllib/evaluation.py:146-158 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/evaluation.py"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"5508133208dcfb5962d9ee14c83e256aaf755c9b96b2975286b4b1f4dd641e60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): python/pyspark/pandas/frame.py:7696-7708 | python/pyspark/pandas/indexes/base.py:1368-1379 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:7696\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. Note first that the copies are not typed on the same thing: \u0060Index\u0060 names \u0060pyspark.pandas.indexes\u0060 in one and \u0060pyspark.pandas.indexes.base\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7696}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1a6fd94594ed8a9f32ddf16d6609f6caf7d255fe512e6f698161257c79c1022"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/pandas/frame.py:8743-8755 | python/pyspark/pandas/frame.py:8767-8779 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8743}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cc786031d329617d9594b86d03986bcb2f769cf862fc3d088179436cd2e38b0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/pandas/internal.py:739-751 | python/pyspark/pandas/internal.py:753-765 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":739}}}],"partialFingerprints":{"codehealthFindingId/v1":"a014e37ccc7e561b53d87c436930d0edfc2702f9c4c01f89c1ef553a425dbb4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/sql/connect/group.py:420-432 | python/pyspark/sql/connect/group.py:472-484 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/group.py:420\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"87bce18206e823ce57abd409beb1b9bb356d12d4a6be3a6f6a422831e4740270"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): python/pyspark/sql/streaming/stateful_processor_api_client.py:426-438 | python/pyspark/sql/streaming/stateful_processor_api_client.py:445-456 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/stateful_processor_api_client.py:426\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"bad7e5fc8fca01caad02efb93da4b1671c7b33f95e2c5519c5a9ac99239ebab2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): python/pyspark/sql/worker/commit_data_source_write.py:45-57 | python/pyspark/sql/worker/python_streaming_sink_runner.py:80-93 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/commit_data_source_write.py"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"81e89e508f9c4a373ffd5175f25fbb37a345fa95cf0e79bcdeb60185c4eb5b89"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 8): python/pyspark/pandas/generic.py:1279-1289 | python/pyspark/pandas/generic.py:1386-1397 | python/pyspark/pandas/generic.py:1494-1504 | python/pyspark/pandas/generic.py:1565-1575 | python/pyspark/pandas/generic.py:1634-1644 | python/pyspark/pandas/generic.py:1951-1961 | python/pyspark/pandas/generic.py:2050-2060 | python/pyspark/pandas/generic.py:2286-2296 \u2014 all 8 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":1279}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e07bcc20ee73116c762198d625a484b52ba712eeeccf96c5b0440d1ffbd5bdf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/join.py:59-70 | python/pyspark/join.py:74-85 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/join.py"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ce8db7b9b029362418f024a7add83c674a0d02d74bd4e600a9ca7f3dc86a38c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:494-505 | python/pyspark/mllib/linalg/__init__.py:561-572 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":494}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec5a6e8b23992748cd2e59b1355c4f4b682b80dcc239644665b3ed8097844a81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1131-1142 | python/pyspark/mllib/linalg/__init__.py:1313-1324 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/ml/linalg/__init__.py:1131\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1131}}}],"partialFingerprints":{"codehealthFindingId/v1":"65c155cea3d1815f49fce6db6aba031df130da78f600f783011a2dec1320a345"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1311-1322 | python/pyspark/mllib/linalg/__init__.py:1508-1519 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1311}}}],"partialFingerprints":{"codehealthFindingId/v1":"eecc305fb4c2db9f30001d149a5640ae861567b9537ec2123601954af77b9ecb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/ml/util.py:171-182 | python/pyspark/ml/util.py:460-471 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/ml/util.py:171\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9f31602f29ac1676e59f5041913fabcb30ce0e1a6876cdad061037c05e93ea2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201312 lines \u00D7 2): python/pyspark/mllib/feature.py:1053-1062 | python/pyspark/mllib/random.py:682-693 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/feature.py"},"region":{"startLine":1053}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcb78902627d56180fad5563b4209b06ce939dcf065b35078f48d24f57e214bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/accessors.py:658-669 | python/pyspark/pandas/accessors.py:726-737 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/accessors.py:658\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":658}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f66ab79559d86e611b0ae8e11972440931d08bd6c429e5d39fe86a8b0cd27c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/data_type_ops/num_ops.py:666-677 | python/pyspark/pandas/data_type_ops/num_ops.py:695-706 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":666}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cb311c28df2fb1813d43c1e5ef277ed501b31578c6830692b7009fabc71b39a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/frame.py:3924-3935 | python/pyspark/pandas/frame.py:4003-4014 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3924}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a9a58543f4b1a529600667527eef84d4db7edc17651784cd900ba8b7acfe125"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/frame.py:4151-4162 | python/pyspark/pandas/frame.py:4175-4186 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:4151\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4151}}}],"partialFingerprints":{"codehealthFindingId/v1":"99743d4c05be1cc3872eb7070d8f26b34cfc761ba603f39452bff9cbc7dee58f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): python/pyspark/pandas/frame.py:7170-7181 | python/pyspark/pandas/frame.py:7184-7194 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:7170\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/pandas/frame.py:7182\u0060 calls \u0060tuple\u0060, \u0060list\u0060, \u0060cast\u0060 and \u0060python/pyspark/pandas/frame.py:7195\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7170}}}],"partialFingerprints":{"codehealthFindingId/v1":"32452a710e2e94724d0871d796e80db84c1305519e8338a2000472991b7ee59f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/generic.py:808-822 | python/pyspark/pandas/generic.py:965-976 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/generic.py:808\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":808}}}],"partialFingerprints":{"codehealthFindingId/v1":"0eed0cd8557537e18c5db6a2720b52b5f3ba6d1a4a4301a475605dfad0abc66e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/indexes/multi.py:514-525 | python/pyspark/pandas/indexes/multi.py:561-572 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/indexes/multi.py:514\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f303d1cb823b94020fdcaf464f9d24c9852db080b945517a111dbea4d5829a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/pandas/indexing.py:621-632 | python/pyspark/pandas/indexing.py:714-725 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":621}}}],"partialFingerprints":{"codehealthFindingId/v1":"53ebf36fd249dec2660e3cc1a2e558166dc938b8e6fad793e830f0689f5886a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): python/pyspark/pandas/plot/core.py:219-235 | python/pyspark/sql/plot/core.py:618-634 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/core.py:219\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2b1963cd521c6d19f6df0c6fd8cafa21ab32f1151bab64727767761e6e9e2bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): python/pyspark/pandas/plot/plotly.py:135-146 | python/pyspark/sql/plot/plotly.py:243-253 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/plotly.py\u0060 and \u0060python/pyspark/sql/plot/plotly.py\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 54 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/plotly.py:135\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060data\u0060 to \u0060Union[\u0022ps.DataFrame\u0022, \u0022ps.Series\u0022]\u0060 in one and \u0060\u0022DataFrame\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"26334c1ed84c37915dda61e9e6cc8604c2f9be65219498bd6cc5f3857688197b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201311 lines \u00D7 4): python/pyspark/sql/streaming/list_state_client.py:117-126 | python/pyspark/sql/streaming/list_state_client.py:139-149 | python/pyspark/sql/streaming/list_state_client.py:162-171 | python/pyspark/sql/streaming/list_state_client.py:178-186 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/list_state_client.py:117\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"44d8b79d16a9cb6e2768e002f0fea8ce2f523e0af6e6c78c120f6022ac252c4a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 3): python/pyspark/eval_handlers/_pandas.py:278-288 | python/pyspark/eval_handlers/_pandas.py:357-368 | python/pyspark/eval_handlers/_pandas.py:520-531 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_pandas.py:278\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b0eb816f65deee581f37eda1daa80c4cd9beef961e4acdf9afcbbd209aa4342"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/eval_handlers/_pandas.py:160-170 | python/pyspark/eval_handlers/_pandas.py:233-243 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_pandas.py"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"12ec4d07d1b7c7d5a94cd737689c5975725a57a1e2c3b0b70407e669b6e3a5bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/ml/connect/readwrite.py:68-78 | python/pyspark/ml/connect/readwrite.py:227-237 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/readwrite.py"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"29b7a7e6d26dab1f53ca576f33b7ec7e16376fdbf19618ffbeb22e7cf2d9c8c5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:814-824 | python/pyspark/mllib/linalg/__init__.py:934-944 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":814}}}],"partialFingerprints":{"codehealthFindingId/v1":"781830c7c3166db00ba48414bb8fe904f0f80b2f6979ab37ce4a3a6ebea6347d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:850-860 | python/pyspark/mllib/linalg/__init__.py:970-980 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":850}}}],"partialFingerprints":{"codehealthFindingId/v1":"523a2968dca68b37c41aa8e2a3c8842cf060bbddfde8b88fb0761be32fc93107"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/pandas/frame.py:2044-2054 | python/pyspark/pandas/frame.py:2131-2141 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":2044}}}],"partialFingerprints":{"codehealthFindingId/v1":"84beff287e1ef296ef647006bdae2bec5f70ede9bebe44ab2371c0b8cc0d561a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u201311 lines \u00D7 2): python/pyspark/pandas/frame.py:13135-13145 | python/pyspark/pandas/frame.py:13661-13668 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13135}}}],"partialFingerprints":{"codehealthFindingId/v1":"c76387a9830b5bd1fa6df5a828374dafb319e30827d9c1335498d2eceb09e3a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): python/pyspark/pandas/groupby.py:1372-1382 | python/pyspark/pandas/groupby.py:3710-3719 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:1372\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1372}}}],"partialFingerprints":{"codehealthFindingId/v1":"c323de2252a2a0955ef93a17ccbc0a9815bcab39d8a350532b10c9ec014ce2e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/pandas/indexes/base.py:2517-2527 | python/pyspark/pandas/indexes/multi.py:1108-1118 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2517}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d70090055f2544b762bd51e2f3c15f620a7a1999d3d5ca661ae0e1a7ef36b9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/pandas/indexing.py:1174-1184 | python/pyspark/pandas/indexing.py:1188-1198 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/indexing.py:1174\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":1174}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dfa5ca3833b51db96431763036d5b697da1a2dd4f349033d2396f525f8105fd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/pandas/plot/core.py:395-405 | python/pyspark/sql/plot/core.py:503-513 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":395}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dd21f15b36529c213281f167e8b030f74edd5295759f5905093b56b625d2b30"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/sql/connect/catalog.py:122-132 | python/pyspark/sql/connect/catalog.py:363-373 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/catalog.py"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"72d0875be487e3904c91036b844f02610aac19fa33bf089cda75c7286895fe9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/sql/connect/group.py:393-403 | python/pyspark/sql/connect/group.py:445-455 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/group.py:393\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":393}}}],"partialFingerprints":{"codehealthFindingId/v1":"54e3822d8d161afbc653b6caf1a01a904ac0de46f054089ecdb091f51b660fcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:1091-1101 | python/pyspark/sql/connect/streaming/readwriter.py:778-788 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/connect/streaming/readwriter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 71 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/readwriter.py:1091\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":1091}}}],"partialFingerprints":{"codehealthFindingId/v1":"25bfe3e6e8a0eb0346e6a50f9676c241ae2784f01404b693e766e101ec9c0e99"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/sql/udf.py:671-681 | python/pyspark/sql/udf.py:695-705 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/udf.py:695\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"afc22925d7d064e1f0420c88bdb1845da77535987eb2e5de9b54a398cf6c491e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/worker_message.py:76-86 | python/pyspark/worker_message.py:89-99 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/worker_message.py:76\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/worker_message.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2748c90e870af2e47d39531f19a37436d82b979fe9fc69b031945449c19e9b9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 3): python/pyspark/sql/streaming/map_state_client.py:139-148 | python/pyspark/sql/streaming/map_state_client.py:263-271 | python/pyspark/sql/streaming/map_state_client.py:278-286 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/map_state_client.py:139\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"31c97894b0fb1dfb0d82b477c07a909c1d38621df7843f015529ae1e2421ef7d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:201-210 | python/pyspark/mllib/linalg/__init__.py:212-221 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"0affc4b3d1c1a367ce5ec9cdde7a50a40a564df5b20af876796689fd7a69de94"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1145-1154 | python/pyspark/mllib/linalg/__init__.py:1340-1349 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1145}}}],"partialFingerprints":{"codehealthFindingId/v1":"788eef2528c732ec8c653b10681a92415dd6d1189bb533931f201ae26fef38bf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/data_type_ops/complex_ops.py:93-102 | python/pyspark/pandas/data_type_ops/null_ops.py:73-82 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/complex_ops.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc476be6ee3f1feb0cc4f68e61fa80f7744c481cc4ab9380007893b50b879538"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/data_type_ops/datetime_ops.py:143-152 | python/pyspark/pandas/data_type_ops/timedelta_ops.py:54-63 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/datetime_ops.py"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9fb9b1c04de4f293d5d99ce98f0d59b88b00b4eaab1bcaaf2e0ca26ba06faf6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/frame.py:6485-6494 | python/pyspark/pandas/series.py:2340-2349 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6485}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1bb045672bcfcfaf63006ef74adf1aaff764d71901b07390033ab2582ed9e18"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/groupby.py:4214-4223 | python/pyspark/pandas/groupby.py:4416-4425 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:4214\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4214}}}],"partialFingerprints":{"codehealthFindingId/v1":"c498d7cb0bbd0460dba86155a0e90e6304e108ae8e3fe942183a10a9c2f30d5a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): python/pyspark/pandas/indexing.py:660-669 | python/pyspark/pandas/indexing.py:752-760 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/indexing.py:660\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"331cbaed93537a181d6e4deea74535a6b4b6cb9893ae46a455afef7d9a780f27"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/plot/core.py:96-105 | python/pyspark/sql/plot/core.py:66-76 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/plot/core.py:96\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"25f5b3a493687db4072fd5839110a43120f2a63e7af206816a65d845c6c5214b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/pandas/series.py:567-577 | python/pyspark/pandas/series.py:588-598 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":567}}}],"partialFingerprints":{"codehealthFindingId/v1":"963740d7cf3ec3b625d5d1ee3f03594f7aa54e48a13369392165b98277ccad69"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/pandas/series.py:7270-7279 | python/pyspark/pandas/series.py:7283-7292 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":7270}}}],"partialFingerprints":{"codehealthFindingId/v1":"3db06de1881ec2359cf95f687406913ab4716fe572897f8a23e9358a1ab577c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/sql/connect/client/core.py:1581-1590 | python/pyspark/sql/connect/client/core.py:2041-2050 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1581}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cf0dd5df2aac8d798c444c6ff1a46b63508d6d627740fad17dc22fc34badd12"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/sql/connect/dataframe.py:2473-2482 | python/pyspark/sql/connect/dataframe.py:2493-2502 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/dataframe.py:2473\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":2473}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d3ab7fd61e872a1186d52b1dc2f5f726634784147c36ef9e2ff941511a7e8d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/sql/connect/session.py:615-624 | python/pyspark/sql/pandas/conversion.py:953-962 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/connect/session.py:615\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":615}}}],"partialFingerprints":{"codehealthFindingId/v1":"a295440c5d0dd98321782d95179850f0698fe86f75fb2477208b7b3cd6bcd908"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/sql/streaming/stateful_processor_api_client.py:204-213 | python/pyspark/sql/streaming/stateful_processor_api_client.py:227-236 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"aac4f64ff5b894a70b85d66d38970ff8e79004133e82e17673755d07d8fbb760"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): python/pyspark/sql/streaming/value_state_client.py:85-94 | python/pyspark/sql/streaming/value_state_client.py:101-109 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/value_state_client.py:85\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"9536690c7e117aa447208dd5244841a5b033ab5dc882e0b89cb1d1ecde7ad591"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 3): python/pyspark/pandas/groupby.py:2502-2509 | python/pyspark/pandas/groupby.py:2599-2606 | python/pyspark/pandas/groupby.py:3779-3787 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:2502\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2502}}}],"partialFingerprints":{"codehealthFindingId/v1":"226df940fe75e5d2e39ef3db56df2c166f862ebafe0e2b61d6c57b3310d3cc46"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): dev/generate_srs_registry.py:179-187 | dev/generate_srs_registry.py:213-221 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/generate_srs_registry.py"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"aceb56bb6d2432f48322347c173eed3a392d1ba03c37a100d807262a028a60a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/eval_handlers/_arrow.py:350-358 | python/pyspark/eval_handlers/_arrow.py:606-614 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_arrow.py:350\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"42086859065d29897e200bb232f8b6f45c18b866503695e11cc2fc1c9a53367d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): python/pyspark/eval_handlers/_arrow.py:367-374 | python/pyspark/eval_handlers/_pandas.py:671-679 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_arrow.py:367\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":367}}}],"partialFingerprints":{"codehealthFindingId/v1":"69c77e2ddae1f7945f1953a15f5aa0ab7d6efd349a4f4cfcb57f08390b412b1c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/eval_handlers/_arrow.py:554-562 | python/pyspark/eval_handlers/_arrow.py:610-618 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"53de8559bf8777277790c0e35c8ffc7706e5e0165d3f649cb7fd8f171f0f09c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/eval_handlers/_elementwise.py:188-205 | python/pyspark/eval_handlers/_elementwise.py:393-401 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/eval_handlers/_elementwise.py:187\u0060 calls \u0060require_minimum_pyarrow_version\u0060 and \u0060python/pyspark/eval_handlers/_elementwise.py:392\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_elementwise.py"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfc106ea7a97b77ba79c74e7ad72fa0ee91591d4256d76209b18bb506dc77e55"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:188-196 | python/pyspark/mllib/linalg/__init__.py:199-207 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7c58c3b11b0d96353dc26167934eccf7a74bcf47f6a76e3a1109bcdc5783b5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/ml/tuning.py:614-622 | python/pyspark/ml/tuning.py:1275-1283 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/ml/tuning.py:623\u0060 calls \u0060getNumFolds\u0060, \u0060join\u0060 and \u0060python/pyspark/ml/tuning.py:1284\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":614}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7d042a6b7f45496cbda19b970bf8c576f24ae39866dd21be64af0f2dc3d9c1f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/pandas/data_type_ops/num_ops.py:391-399 | python/pyspark/pandas/data_type_ops/num_ops.py:507-515 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/pandas/data_type_ops/num_ops.py:503\u0060 calls \u0060TypeError\u0060, \u0060is_ansi_mode_enabled\u0060, \u0060_is_decimal_float_mixed\u0060 and \u0060python/pyspark/pandas/data_type_ops/num_ops.py:390\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4079596722c5b647bd51a370a10af7da4cb8d135c8127084c5c716580b9a5b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/pandas/data_type_ops/num_ops.py:501-509 | python/pyspark/pandas/data_type_ops/num_ops.py:518-526 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":501}}}],"partialFingerprints":{"codehealthFindingId/v1":"25b357f60af1a6bbf778e4135f788f6e08040bf824383f8409fd378487407383"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): python/pyspark/pandas/frame.py:8089-8097 | python/pyspark/pandas/frame.py:8220-8227 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8089}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e7f8138c0e284c06e97864473af543eaf77ee340624cb31a0ac9e6f30938f2b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/pandas/frame.py:9102-9110 | python/pyspark/pandas/namespace.py:3567-3575 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:9102\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9102}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4670c322ad3526f5a84345ef35038897773748e2d36cb017b10f70a216da752"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 2): python/pyspark/pandas/frame.py:11533-11541 | python/pyspark/pandas/frame.py:11658-11664 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:11533\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11533}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc7c113fec11bc0400701332267a50f1bcfa0104c392491c12332a7a02693eb4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/pandas/groupby.py:2055-2063 | python/pyspark/pandas/groupby.py:2128-2136 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2055}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e2de2b6c0ff1dd1d5781da64b8b7722c080211d46db2d14afd296c06bec52af"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): python/pyspark/pandas/plot/core.py:170-178 | python/pyspark/sql/plot/core.py:576-583 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"f06c9804c1b7bd513b044fc5bfcae8f7311814821f03d73768cd9fc6059e450c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/connect/client/reattach.py:220-228 | python/pyspark/sql/connect/client/reattach.py:243-251 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/reattach.py"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"634b0b354a1f791a7d2676ffa8ba174747715724d51e1c77f07aabc595359ae5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:2818-2826 | python/pyspark/sql/functions/builtin.py:16638-16646 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2818}}}],"partialFingerprints":{"codehealthFindingId/v1":"df03a4cc44097bf189d8222bc38110c04d46df53054cac0dc3524aab23a89412"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/conversion.py:1494-1502 | python/pyspark/sql/conversion.py:1511-1519 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1494}}}],"partialFingerprints":{"codehealthFindingId/v1":"13381de21770ad63c8b9359b7f125571e664d8053599f7f42379e6045609b041"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/conversion.py:1991-1999 | python/pyspark/sql/conversion.py:2087-2095 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1991}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e4af26417cf3b5099600c297dfcd35fc966d3f8b853b6260cca4327647f81c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/pandas/types.py:1327-1335 | python/pyspark/sql/pandas/types.py:1344-1352 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":1327}}}],"partialFingerprints":{"codehealthFindingId/v1":"eed2c1fa6f3084fc14061e25cdf544388285cfc0cb12dcf959a4941bae91f986"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/profiler.py:348-356 | python/pyspark/sql/profiler.py:396-404 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/profiler.py"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"8958dca9a4fde3a5ea3d6f8813c08fc810800014df27bb7c75a0c922abf88fec"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/streaming/map_state_client.py:81-89 | python/pyspark/sql/streaming/value_state_client.py:64-72 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"34f211ad17b42fa2d512615e3433b01c88f448e969fd7f279e2732a0f117029d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/streaming/readwriter.py:1464-1472 | python/pyspark/sql/streaming/readwriter.py:1474-1482 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/sql/streaming/readwriter.py:1464\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/readwriter.py"},"region":{"startLine":1464}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4476622d7371d9af190496a09f6d434337489fd62c67e4da6b9d6ed94221fbc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/sql/streaming/stateful_processor_api_client.py:252-260 | python/pyspark/sql/streaming/stateful_processor_api_client.py:267-275 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"35e2357b994812ad44db189404e4cb287bd823de1fb7df8b021db70bee849817"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 4): python/pyspark/eval_handlers/_arrow.py:280-287 | python/pyspark/eval_handlers/_arrow.py:353-360 | python/pyspark/eval_handlers/_arrow.py:553-560 | python/pyspark/eval_handlers/_arrow.py:609-616 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c465a4e5d05f38ab4813f8ef1af4d431052ae9a26cbae5725c8d5473504b19b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/connect/tuning.py:413-420 | python/pyspark/ml/tuning.py:836-843 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/tuning.py\u0060 and \u0060python/pyspark/ml/tuning.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"5844df661a347db5317d044ca60af1bedad1d472d378ba8ebdee5d1ab225a7e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/connect/tuning.py:465-472 | python/pyspark/ml/tuning.py:891-898 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/tuning.py\u0060 and \u0060python/pyspark/ml/tuning.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 44 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":465}}}],"partialFingerprints":{"codehealthFindingId/v1":"eedd0583915d73fcba16849f9ede6b7b2d9628028e5617eba2ee761bf9d5c573"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:330-337 | python/pyspark/mllib/linalg/__init__.py:361-368 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdc2b7ba505a2fcd99de3f52137194445d934fa9969085d4cc0a4b0ceafdce81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:441-448 | python/pyspark/mllib/linalg/__init__.py:495-502 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/ml/linalg/__init__.py:440\u0060 calls \u0060isinstance\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py:494\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"1093774d5b987d21ac65722dab50b36b41f835444d01bbbe315c1f6dbf66166a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/mllib/classification.py:973-980 | python/pyspark/mllib/stat/_statistics.py:395-402 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":973}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c405b1ce81769616650d60d5e92607e0fab15901577f8d635023b5051932e43"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/pandas/accessors.py:620-628 | python/pyspark/pandas/accessors.py:694-701 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/accessors.py:620\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":620}}}],"partialFingerprints":{"codehealthFindingId/v1":"92f9b5c9cfbf8d2da96c67585dd9737b955e28694e59459c39570435508a937a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/pandas/config.py:505-512 | python/pyspark/pandas/config.py:522-529 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/config.py"},"region":{"startLine":505}}}],"partialFingerprints":{"codehealthFindingId/v1":"17153e5cb91347262fd1fee610effac19975a02560ef95c8930fddadd185fb47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/pandas/groupby.py:1490-1497 | python/pyspark/pandas/groupby.py:4922-4929 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:1490\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1490}}}],"partialFingerprints":{"codehealthFindingId/v1":"5504e78ae345579cd89c6535c0feef0d4203d69f3479987f8c4948c381c364d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/pandas/indexes/datetimes.py:804-811 | python/pyspark/pandas/indexes/datetimes.py:849-856 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/datetimes.py"},"region":{"startLine":804}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f332af63d20726ccc249b9a4b9bed1c9099d20723a8d7f22cdb4beee4eb272e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:815-824 | python/pyspark/sql/classic/dataframe.py:959-968 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/sql/classic/dataframe.py:827\u0060 calls \u0060join\u0060 and \u0060python/pyspark/sql/classic/dataframe.py:970\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"86b1eda84d81c6185b82e55a824c93941a58fce4d99e8f6e533a1a9bebc97e3e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:279-286 | python/pyspark/sql/functions/builtin.py:283-290 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: \u0060Column\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.column\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"a369dfd8a75936c55633292d45e2379290b72f4682b526a205462176688a2dcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:3395-3402 | python/pyspark/sql/functions/builtin.py:20230-20236 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: \u0060Column\u0060 names \u0060pyspark.sql\u0060 in one and \u0060pyspark.sql.column\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":3395}}}],"partialFingerprints":{"codehealthFindingId/v1":"33a6c650b0e32bda96f1a259027e47c673b58385c6f28b20eae3ac7106a1e840"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): python/pyspark/pandas/datetimes.py:166-172 | python/pyspark/pandas/frame.py:3927-3933 | python/pyspark/pandas/frame.py:4006-4012 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/datetimes.py:166\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/datetimes.py"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9ecdd905e7f74ff35135c77703e506f83b88fae7688d400acc7b176e81d4a0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): python/pyspark/pandas/groupby.py:411-417 | python/pyspark/pandas/groupby.py:1491-1497 | python/pyspark/pandas/groupby.py:4923-4929 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":411}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c7a2c090c1cfeba4c97a5a39810918eef045b7aeac875d8ceb72a99d127b571"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:482-488 | python/pyspark/mllib/linalg/__init__.py:549-555 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ea90b2a5996874b9fc7360cfb7b68b6b9990a586b541c349756b8f63da9fe9a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/pandas/accessors.py:370-376 | python/pyspark/pandas/accessors.py:637-649 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":370}}}],"partialFingerprints":{"codehealthFindingId/v1":"60393b0f5e62952134eb1d94bbc1f5650ca6733cbc3118fa16b3f2778a86a7ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/pandas/frame.py:1729-1735 | python/pyspark/pandas/groupby.py:4281-4287 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:1729\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060python/pyspark/pandas/frame.py:1728\u0060 calls \u0060orderBy\u0060 and \u0060python/pyspark/pandas/groupby.py:4280\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1729}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7af77bce6924455fb3df25bf0396ab9f26c362b9d699b88d43cfd63b6aed910"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/pandas/groupby.py:1215-1221 | python/pyspark/pandas/groupby.py:3788-3794 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/groupby.py:1215\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1215}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9b0483b13a4a4d2ae1d283abcff19727e8463adb51eb952851867b8c7799876"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/pandas/groupby.py:4069-4075 | python/pyspark/pandas/groupby.py:4630-4636 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4069}}}],"partialFingerprints":{"codehealthFindingId/v1":"519f8d18354b3caeaf208a1a7e052bd04b0fcb54775543e339cd1a328aac4edc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/pandas/plot/plotly.py:114-120 | python/pyspark/sql/plot/plotly.py:224-230 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/plotly.py\u0060 and \u0060python/pyspark/sql/plot/plotly.py\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 54 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/plotly.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"52c23fe533c1a0fd0517054179fda96dff0c5825e0f07b5b84d0fb050b1b44a0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/shuffle.py:431-437 | python/pyspark/shuffle.py:469-475 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b54e2075024383863bc0ec5532145242d1608f3e368b631003a9e0712b0750f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): python/pyspark/mllib/evaluation.py:683-688 | python/pyspark/mllib/feature.py:1058-1063 | python/pyspark/mllib/random.py:689-694 | python/pyspark/mllib/regression.py:1045-1050 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/evaluation.py"},"region":{"startLine":683}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcbc8360bdbd127661f82f396118303d53eb27a755292e92f83f5bc208aa727d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/eval_handlers/_arrow.py:295-300 | python/pyspark/eval_handlers/_arrow.py:805-810 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/eval_handlers/_arrow.py:295\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_arrow.py"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"f147d292bfe2ea6bbabd016674a8a03873f95a359c2c6ffd682dc2076f9a1a95"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/connect/serialize.py:92-99 | python/pyspark/ml/connect/serialize.py:111-118 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/serialize.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"7055dbd22659aec87142992b8adeaaf0ea884c4a5d68429c9313e23a87506709"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/pandas/accessors.py:373-378 | python/pyspark/pandas/frame.py:3244-3249 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/accessors.py:373\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba491fae7ae5e3dbf67787838d6b2daab27afe264436d5ae4745c38f13019e4d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (3\u20136 lines \u00D7 3): python/pyspark/sql/connect/functions/builtin.py:4204-4206 | python/pyspark/sql/connect/functions/builtin.py:4228-4233 | python/pyspark/sql/connect/functions/builtin.py:4253-4258 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":4204}}}],"partialFingerprints":{"codehealthFindingId/v1":"74ebd29e6d08f6a2f20baf929ac434eb90937b689f48bb5927ddb6db71342726"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/sql/conversion.py:1389-1394 | python/pyspark/sql/conversion.py:1399-1404 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":1389}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4231c35a88b18e49698878226969980d5b52ccd4ee03c6037d203d7cb9032d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): python/pyspark/pandas/plot/core.py:168-173 | python/pyspark/pandas/plot/core.py:395-400 | python/pyspark/sql/plot/core.py:503-508 | python/pyspark/sql/plot/core.py:574-579 \u2014 before extracting anything, compare \u0060python/pyspark/pandas/plot/core.py\u0060 and \u0060python/pyspark/sql/plot/core.py\u0060 as WHOLE FILES: this scan already matched 8 separate duplicated blocks between them, totalling at least 123 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dc3e59142f12cf1c344b9b2b70a57564ecd3187b3e67c92d4b2322013c3a84b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1157-1164 | python/pyspark/mllib/linalg/__init__.py:1352-1359 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1157}}}],"partialFingerprints":{"codehealthFindingId/v1":"377deb12228f809f70fc65bb47cf00732527c4bdd098619db500730f334aef24"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): python/pyspark/sql/connect/functions/builtin.py:5570-5574 | python/pyspark/sql/connect/functions/builtin.py:5587-5591 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5570}}}],"partialFingerprints":{"codehealthFindingId/v1":"5251be104f89bb71d386ee4c4187a3145e6e9f9cdc4f61709221d35388735a27"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/sql/connect/plan.py:1169-1175 | python/pyspark/sql/connect/plan.py:1337-1343 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":1169}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c26b2f6fa33dfb64e1a0725f250a2db8bc55801de86218520d194335cb16e4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): dev/create_jira_and_branch.py:29-33 | dev/merge_spark_pr.py:980-984 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/create_jira_and_branch.py"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e69ccd76b4a1d6ed358efdcd70481df0c0bdfbf103855e4a4ddba8de3817553"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/core/rdd.py:1437-1458 | python/pyspark/streaming/dstream.py:289-297 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060self\u0060 to \u0060\u0022RDD[T]\u0022\u0060 in one and \u0060\u0022DStream[T]\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":1437}}}],"partialFingerprints":{"codehealthFindingId/v1":"31e49cf7808447e1526ae2e1eb809117e7eef2d111216c6dd576f8095a789e39"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/core/rdd.py:4053-4087 | python/pyspark/streaming/dstream.py:278-286 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060self\u0060 to \u0060\u0022RDD[Tuple[K, V]]\u0022\u0060 in one and \u0060\u0022DStream[Tuple[K, V]]\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":4053}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fcf89f9570c584c4fc4a4743e53acff5faf5f96cd670256457e5810ad81bd92"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/core/rdd.py:4090-4124 | python/pyspark/streaming/dstream.py:265-273 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060self\u0060 to \u0060\u0022RDD[Tuple[K, V]]\u0022\u0060 in one and \u0060\u0022DStream[Tuple[K, V]]\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":4090}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0ecfac74e3d11d85da5987d957c01cac341d8df3e22989997eae6ed33c415e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 43): python/pyspark/ml/classification.py:745-757 | python/pyspark/ml/classification.py:1835-1848 | python/pyspark/ml/classification.py:2152-2166 | python/pyspark/ml/classification.py:2641-2656 | python/pyspark/ml/classification.py:3042-3052 | python/pyspark/ml/classification.py:3296-3307 | python/pyspark/ml/classification.py:4197-4210 | python/pyspark/ml/clustering.py:422-432 | python/pyspark/ml/clustering.py:801-811 | python/pyspark/ml/clustering.py:1158-1168 | python/pyspark/ml/clustering.py:1722-1732 | python/pyspark/ml/clustering.py:2069-2078 | python/pyspark/ml/feature.py:598-607 | python/pyspark/ml/feature.py:1096-1103 | python/pyspark/ml/feature.py:1439-1447 | python/pyspark/ml/feature.py:1851-1857 | python/pyspark/ml/feature.py:2140-2147 | python/pyspark/ml/feature.py:2588-2594 | python/pyspark/ml/feature.py:2753-2759 | python/pyspark/ml/feature.py:3204-3211 | python/pyspark/ml/feature.py:3935-3942 | python/pyspark/ml/feature.py:4279-4285 | python/pyspark/ml/feature.py:4414-4420 | python/pyspark/ml/feature.py:4674-4681 | python/pyspark/ml/feature.py:4952-4958 | python/pyspark/ml/feature.py:5376-5383 | python/pyspark/ml/feature.py:5589-5595 | python/pyspark/ml/feature.py:5889-5895 | python/pyspark/ml/feature.py:6323-6331 | python/pyspark/ml/feature.py:6558-6564 | python/pyspark/ml/feature.py:6805-6813 | python/pyspark/ml/feature.py:7184-7192 | python/pyspark/ml/feature.py:7677-7686 | python/pyspark/ml/fpm.py:256-263 | python/pyspark/ml/recommendation.py:385-395 | python/pyspark/ml/regression.py:323-335 | python/pyspark/ml/regression.py:890-900 | python/pyspark/ml/regression.py:1161-1174 | python/pyspark/ml/regression.py:1475-1489 | python/pyspark/ml/regression.py:1839-1852 | python/pyspark/ml/regression.py:2256-2268 | python/pyspark/ml/regression.py:2666-2678 | python/pyspark/ml/regression.py:3236-3246 \u2014 before extracting anything, compare \u0060python/pyspark/ml/classification.py\u0060 and \u0060python/pyspark/ml/regression.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 43 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/ml/clustering.py:434\u0060 calls \u0060_create_model\u0060, \u0060GaussianMixtureModel\u0060 and \u0060python/pyspark/ml/classification.py:759\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":745}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5a40d13fd32bd0a304131c89ec2135b2992c9757ccb81c6edf7bd2afbb494cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): python/pyspark/ml/classification.py:2859-2867 | python/pyspark/ml/regression.py:1654-1662 | python/pyspark/ml/regression.py:2061-2069 \u2014 before extracting anything, compare \u0060python/pyspark/ml/classification.py\u0060 and \u0060python/pyspark/ml/regression.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 43 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":2859}}}],"partialFingerprints":{"codehealthFindingId/v1":"0edde46024bbf17e9d69734db2a3d441a4df7740c1eeccc26c686a41c781be0b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): python/pyspark/ml/connect/base.py:240-267 | python/pyspark/ml/evaluation.py:87-112 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/base.py"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdd66789f692ee839738b066ad3f379ceb0cefc2139f641ada14b93e8ec62c38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): python/pyspark/ml/connect/io_utils.py:62-68 | python/pyspark/ml/util.py:987-993 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/io_utils.py"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9f4fd7f070971a89edc8c9a6d72d9c894798c426f761fc716e2dd2e822c66c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): python/pyspark/ml/connect/pipeline.py:213-234 | python/pyspark/ml/pipeline.py:145-164 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/pipeline.py\u0060 and \u0060python/pyspark/ml/pipeline.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"5290dd217347633c3f8de9d4be88db0850b47aea8ff83cc6ede3ff4ca2bc4dbd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/ml/connect/pipeline.py:257-270 | python/pyspark/ml/pipeline.py:307-318 \u2014 before extracting anything, compare \u0060python/pyspark/ml/connect/pipeline.py\u0060 and \u0060python/pyspark/ml/pipeline.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 57 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"206a471eec9e22960ba31dd5d738264c419cbff090f32bd66254eefbe3c503f1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:514-519 | python/pyspark/mllib/linalg/__init__.py:581-586 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"bda97b4d607ee65a0e09ed314520926a1a29585ff3883ed75bfc1afd82bce145"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:790-795 | python/pyspark/mllib/linalg/__init__.py:897-902 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":790}}}],"partialFingerprints":{"codehealthFindingId/v1":"92e903a9d19c689d782cee349f19317652d3ffefa3a53f916620ee8859123d83"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:806-811 | python/pyspark/mllib/linalg/__init__.py:926-931 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"9eddabeab1e81784e834b4f5aebeedc351cc23e008e7465738acc986fed27653"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:940-953 | python/pyspark/mllib/linalg/__init__.py:1060-1073 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":940}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bc3c9b382f00e154e68ef7f55f0c01390d983b8881341f4782e0d4bdb67e79c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1034-1039 | python/pyspark/mllib/linalg/__init__.py:1217-1222 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1034}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3afe4cd9955b64315148e32b982b89c8b223414fa866e19ebec38d7c7e79134"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1068-1088 | python/pyspark/mllib/linalg/__init__.py:1251-1271 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1068}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ac5888a72f45f5da34e0e7ec5250e789e5923fd03104dd806f6a81670baf282"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1115-1128 | python/pyspark/mllib/linalg/__init__.py:1297-1310 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1115}}}],"partialFingerprints":{"codehealthFindingId/v1":"b546d795e1bdc99373242c82d741605d95eb9e5de01a56b5733f81fb42697636"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/ml/linalg/__init__.py:1279-1286 | python/pyspark/mllib/linalg/__init__.py:1476-1483 \u2014 before extracting anything, compare \u0060python/pyspark/ml/linalg/__init__.py\u0060 and \u0060python/pyspark/mllib/linalg/__init__.py\u0060 as WHOLE FILES: this scan already matched 33 separate duplicated blocks between them, totalling at least 646 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1279}}}],"partialFingerprints":{"codehealthFindingId/v1":"477d657ee1ed369a6cceb9c40d2747f1044940d61747e357104b01754b675ece"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): python/pyspark/pandas/data_type_ops/base.py:556-561 | python/pyspark/pandas/data_type_ops/num_ops.py:613-618 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":556}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8960050a9d928a6e619688d16fe4c8a08bd07cef6c93eae19ef420adbdfd5ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): python/pyspark/pandas/frame.py:186-190 | python/pyspark/pandas/series.py:164-168 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060self\u0060 to \u0060\u0022DataFrame\u0022\u0060 in one and \u0060\u0022Series\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e23a70a7853420b19b7f01f88636b4bc875ae5230ea7ddf875c5a6367c8944f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (37 lines \u00D7 2): python/pyspark/pandas/frame.py:8333-8388 | python/pyspark/pandas/series.py:3272-3308 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8333}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d85e8a99f675be7ae88339be49a35f3d3bd2a489f0a288a0b501385befe68f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:1981-1985 | python/pyspark/sql/connect/dataframe.py:2170-2174 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1981}}}],"partialFingerprints":{"codehealthFindingId/v1":"040a42fb2b7d8bfcd80a2ebb293a95ac99b4d2918be7831400b70cb5157388d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): python/pyspark/sql/classic/dataframe.py:2025-2035 | python/pyspark/sql/connect/dataframe.py:2313-2323 \u2014 \u0060python/pyspark/sql/classic/dataframe.py\u0060 and \u0060python/pyspark/sql/connect/dataframe.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 305 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":2025}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d9be05cc3fd6309c33c1b55379208f477e117c726862ea2bdb70f6149c8e9ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:70-77 | python/pyspark/sql/readwriter.py:51-58 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/readwriter.py\u0060 as WHOLE FILES: this scan already matched 7 separate duplicated blocks between them, totalling at least 113 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"c199f64149f65e97728eab2695dfbea3401aaf93ed7ce3eb2f517d9bf0e19a1f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): python/pyspark/sql/connect/readwriter.py:96-109 | python/pyspark/sql/connect/streaming/readwriter.py:77-90 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/readwriter.py\u0060 and \u0060python/pyspark/sql/connect/streaming/readwriter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 71 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"4153c73ea786bccce1665a365040009ba07eebfb1ad226f4eeb50e79ca2f9cf3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): python/pyspark/sql/connect/udtf.py:124-135 | python/pyspark/sql/udtf.py:278-289 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udtf.py"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"a677db677b0df625a01e03133611f3759c9b735c2f8fb73db096643a32284168"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 5): python/pyspark/ml/classification.py:916-932 | python/pyspark/ml/classification.py:3433-3449 | python/pyspark/ml/classification.py:4375-4391 | python/pyspark/ml/regression.py:504-521 | python/pyspark/ml/regression.py:2851-2868 \u2014 before extracting anything, compare \u0060python/pyspark/ml/classification.py\u0060 and \u0060python/pyspark/ml/regression.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 43 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":916}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6ec81e0265bb3068d48d7791974c389d969d7b2502d7aad22e16af056435f78"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): python/pyspark/ml/deepspeed/deepspeed_distributor.py:148-159 | python/pyspark/ml/torch/distributor.py:881-889 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/deepspeed/deepspeed_distributor.py"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"44aa6d06cebcf802ac1989eb208ab1c19edc0240b2836e08d04d604c98f419df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 4): python/pyspark/mllib/classification.py:610-618 | python/pyspark/mllib/regression.py:232-238 | python/pyspark/mllib/regression.py:443-449 | python/pyspark/mllib/regression.py:620-626 \u2014 there are 4 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/classification.py"},"region":{"startLine":610}}}],"partialFingerprints":{"codehealthFindingId/v1":"9aa09b759f226b0e490d068efaef61bdd091d4f19e5315fba432229692054d60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): python/pyspark/mllib/fpm.py:63-69 | python/pyspark/mllib/recommendation.py:219-223 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/fpm.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"01c4e9aabf855377d03a8c9a8b01438dd7a8dfcadb3d59579299f5606c18d98c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (40 lines \u00D7 5): python/pyspark/pandas/frame.py:2158-2230 | python/pyspark/pandas/frame.py:2472-2565 | python/pyspark/pandas/frame.py:2590-2685 | python/pyspark/pandas/frame.py:5992-6068 | python/pyspark/pandas/series.py:1679-1718 \u2014 there are 5 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 5 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060python/pyspark/pandas/frame.py:2472\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note first that the copies are not typed on the same thing: \u0060Index\u0060 names \u0060pyspark.pandas.indexes\u0060 in one and \u0060pyspark.pandas.indexes.base\u0060 in another \u2014 different types that share a simple name, which is why the text matched. A single extracted unit cannot be given a parameter type that fits both, so unifying those types (or introducing a shared abstraction over them) is the step that has to come BEFORE the extraction above; if they are deliberately separate, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":2158}}}],"partialFingerprints":{"codehealthFindingId/v1":"d20fc85f3a8f84da71324e05867ac1be4b5fa6dd4ad28a0d732b6c19a8e5a7f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (57 lines \u00D7 3): python/pyspark/pandas/frame.py:2259-2352 | python/pyspark/pandas/frame.py:2375-2469 | python/pyspark/pandas/series.py:1609-1665 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":2259}}}],"partialFingerprints":{"codehealthFindingId/v1":"de6d62f81b5263f14bbf398737a579be1314c655058176e2314ff5d83a720bd8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (57 lines \u00D7 2): python/pyspark/pandas/generic.py:2863-2923 | python/pyspark/pandas/groupby.py:3421-3477 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2863}}}],"partialFingerprints":{"codehealthFindingId/v1":"de3d9293eded0fc77d40468a354a7e4501fbdf7bcebc8dce25ef2bb115695d3c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): python/pyspark/pandas/groupby.py:114-118 | python/pyspark/pandas/strings.py:53-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060self\u0060 to \u0060\u0022GroupBy\u0022\u0060 in one and \u0060\u0022StringMethods\u0022\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5b2d7527457f1f58175fbcb705ca2b8cc2b3326b709e1d10cd5879902636bd3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 7): python/pyspark/pandas/groupby.py:4561-4567 | python/pyspark/pandas/window.py:223-229 | python/pyspark/pandas/window.py:1037-1043 | python/pyspark/pandas/window.py:1636-1642 | python/pyspark/pandas/window.py:2261-2267 | python/pyspark/pandas/window.py:2849-2855 | python/pyspark/pandas/window.py:2950-2956 \u2014 there are 7 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 7 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060python/pyspark/pandas/window.py:1645\u0060 calls \u0060__repr__\u0060, \u0060format\u0060 and \u0060python/pyspark/pandas/window.py:2269\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4561}}}],"partialFingerprints":{"codehealthFindingId/v1":"85478b03aa978126eae664a157e80c4902ca535d651da1f0783ffab72229f1bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): python/pyspark/pandas/indexes/datetimes.py:171-177 | python/pyspark/pandas/indexes/multi.py:982-988 | python/pyspark/pandas/indexes/timedelta.py:144-151 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/datetimes.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef93daae7f4cbe79650dbcb0b471844c00f4dc30e38103514667b981a81c75fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): python/pyspark/sql/connect/udf.py:211-218 | python/pyspark/sql/udf.py:519-526 \u2014 before extracting anything, compare \u0060python/pyspark/sql/connect/udf.py\u0060 and \u0060python/pyspark/sql/udf.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 142 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udf.py"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e3c56735dda5172840a7fc89595733a028662bc07e286261a4b6fc4a86c6e9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 43 shared lines): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:68-132 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:66-135 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:67-141 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:70-154 \u2014 These 4 members are variants of one another: a block of 43 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee528dea8fc2cd2d1af957766156dbc0b66d6e903cc14301d21d175b637f5472"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 23 shared lines): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:68-132 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:66-135 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:67-141 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:53-95 \u2014 These 4 members are variants of one another: a block of 23 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"343a5a8af6e632d4a561b73b18711fd87f9be07a11be61c874e0a616f0c95c69"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (71 shared lines): examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:137-240 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:143-248 \u2014 These two members are variants of one another: 71 of their lines are already reported as duplicated blocks below, spread through both bodies rather than gathered into one. Read them as a single construct written twice. The repair is at the members\u0027 grain \u2014 factor the shared pipeline into one implementation the two call with their differences as parameters or as an injected step, or, where the difference is systematic (sync against async, one transport against another), generate one from the other. Extracting the individual blocks below is not the same fix: it leaves the two bodies in place and the next edit still has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cd04710db6d17fa155d508291d43bcba039861c90be2e9f4548584512c3983e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:37-67 | examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:36-72 \u2014 These two members are one piece of code written twice and then edited apart: 17 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a0d2c87eaa192ffde57d0cb631f6352528b4fa74f24dfc987be606ef5d72dbb"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:33-103 | examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeRegressionExample.java:34-88 | examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:34-104 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java:34-104 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java:35-89 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java:34-100 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java:35-89 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"14b0f50c05f03b870e3ce2c30986943486f2ac6fd4810baa8fa7f6809e7012ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java:38-78 | examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java:38-78 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java:38-79 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java:38-79 | examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java:33-54 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java:37-79 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java:37-79 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae32c7f962b100bb94903fc2e58063d6df3ff2c6037df29bc21b761c68f470e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala:30-67 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala:30-66 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala:30-67 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala:30-66 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala:29-67 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala:29-67 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"25baecbea6167fe797d4657ae5eddbff5c02a167392347dea05459ce0483f164"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java:48-109 | examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java:40-71 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinHashLSHExample.java:48-110 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java:40-73 | examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java:39-73 | examples/src/main/java/org/apache/spark/examples/ml/JavaVarianceThresholdSelectorExample.java:43-78 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"19d06b5edbfe8bab5ad74d408d9a2dfc8dd922d08647fb3079681bd15df0c4d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:62-103 | examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala:40-63 | examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala:52-97 | examples/src/main/scala/org/apache/spark/examples/mllib/MultivariateSummarizer.scala:41-64 | examples/src/main/scala/org/apache/spark/examples/mllib/SampledRDDs.scala:38-59 \u2014 These 5 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 5 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 5 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"745d816e57cbcf8e30232fc329b8fbac739b2caf6d49cb73b52ba344843ffa01"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java:57-80 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java:55-97 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java:94-139 | examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java:47-72 | examples/src/main/java/org/apache/spark/examples/streaming/JavaRecoverableNetworkWordCount.java:113-158 \u2014 These 5 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 5 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 5 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"707f94b48f41fe3b207f60d8f025e56850ec5fe239cb4935629406bb8e35f753"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala:31-93 | examples/src/main/scala/org/apache/spark/examples/ml/FMClassifierExample.scala:30-94 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala:30-96 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala:30-95 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"c07f7b4026bdd90651e4e58f18765932ecfc91997902bf306276835d7a70514f"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala:31-83 | examples/src/main/scala/org/apache/spark/examples/ml/FMRegressorExample.scala:30-82 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala:30-83 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala:30-82 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"6bf573f78cfe037835b7f6740bf83c167466bb3d80393853c8b18cfa84710cae"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala:40-60 | examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala:36-55 | examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala:37-59 | examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala:41-81 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7dafa0efa8afd0efdd28c5fa62e26baf0070189628749b558d5854fd26033b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java:111-288 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCount.java:40-77 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCountWindowed.java:53-111 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredSessionization.java:39-85 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"53d0a00c1b8b5d3c569ecf4d4eb485223f89d40b0d35022a36c721314c572a4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (55 corresponding lines): examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java:34-101 | examples/src/main/java/org/apache/spark/examples/mllib/JavaMulticlassClassificationMetricsExample.java:35-89 \u2014 These two members are one piece of code written twice and then edited apart: 55 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"19db54a3d19ac21df3c322be5d75c4ba3f08cb9c582d00e28e0ffebca00bf3dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 49\u002B corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala:53-101 | examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala:58-109 | examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala:57-109 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 49 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb985aed5fe2d2b8dc8a42fb856822df522cdaf855b1c62fb500cfdd9e5230cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java:46-81 | examples/src/main/java/org/apache/spark/examples/ml/JavaChiSquareTestExample.java:44-74 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffa49efa3475388d4647d00b09d5820f6d3eb778bde902c688f89478c161ab97"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (43 corresponding lines): examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java:32-74 | examples/src/main/java/org/apache/spark/examples/mllib/JavaLatentDirichletAllocationExample.java:37-81 \u2014 These two members are one piece of code written twice and then edited apart: 43 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb8c8e72a233277f96a54c9471e0fcf050c7a0d777cef06a4a0d1073e9ce988c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/UnivariateFeatureSelectorExample.scala:35-71 | examples/src/main/scala/org/apache/spark/examples/ml/VarianceThresholdSelectorExample.scala:35-67 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/UnivariateFeatureSelectorExample.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"97e0d5677efd4b3c41bc55146c0b127a0a8f39cb1d302ce75e74d7b4b8388cc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala:40-81 | examples/src/main/scala/org/apache/spark/examples/streaming/DirectKerberizedKafkaWordCount.scala:79-121 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"3304464e0fecda2e0ea02c327bc129fe37b3153214c658c7ff75a960b213031b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (39 corresponding lines): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:53-91 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java:89-128 \u2014 These two members are one piece of code written twice and then edited apart: 39 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"3da69648758eb0e56fabda03bafe1fb2e6f82722f43dea63bedc6f02fadfc74f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): examples/src/main/java/org/apache/spark/examples/mllib/JavaPCAExample.java:40-70 | examples/src/main/java/org/apache/spark/examples/mllib/JavaSVDExample.java:41-73 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaPCAExample.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"0902cbe55b86439409e5e982b14463405fd76fb61d401ea4c956dddc23059947"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java:36-64 | examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSizeHintExample.java:38-77 \u2014 These two members are one piece of code written twice and then edited apart: 29 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1c7897fa3e8a7dd086be29e770d1b3141f2b62b437b92dc5ccff49b32207cb8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaCorrelationExample.java:44-71 | examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java:39-68 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaCorrelationExample.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"c31e9b59a6445ce5f1bf63eec7afa897a89066c64b176ca0e7a4015a7cc28673"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (36 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaFPGrowthExample.java:41-76 | examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java:35-71 \u2014 These two members are one piece of code written twice and then edited apart: 36 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaFPGrowthExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ddb1c269478db4e9687730b0af419ed2501fec305c8f0b48c3c58667cc9ec69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:51-90 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala:90-130 \u2014 These two members are one piece of code written twice and then edited apart: 40 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"6db46499feb1cb4a1f0d0dad625b2c25680229c3aea63aeac7d082989147f155"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (35 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:38-72 | examples/src/main/java/org/apache/spark/examples/ml/JavaPowerIterationClusteringExample.java:36-70 \u2014 These two members are one piece of code written twice and then edited apart: 35 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfa99487b5662c0c9db4ab2ac2d7a191f1bc93c2cd04ca57cba1f0e33339be88"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): examples/src/main/java/org/apache/spark/examples/mllib/JavaLogisticRegressionWithLBFGSExample.java:39-72 | examples/src/main/java/org/apache/spark/examples/mllib/JavaSVMWithSGDExample.java:38-74 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaLogisticRegressionWithLBFGSExample.java"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"e40f221c241bab1e35e6fe753ab5e7c83f57a482c912b2bca479e29e75feb1d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaImputerExample.java:41-70 | examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java:37-67 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaImputerExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"da479fef09e743f221c835b44d07cdf2c081892fd5164a321d77106a6280550c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 36\u002B corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java:34-75 | examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java:34-69 | examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java:40-82 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 36 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4c0d5e6babccc1e97c9bf0ff105df7ca6d767f94b5280c5194ab8d9844e98e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala:33-60 | examples/src/main/scala/org/apache/spark/examples/mllib/SVDExample.scala:38-66 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c49190b587d5e2db1c1f7b6b8ecf4177ab822815687793142e76d11c44ca27b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java:38-66 | examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java:38-65 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e0859fc25436d8a4c0aaba1e088e696ef455cfa20d4ba230a869ab20b800795"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (28 corresponding lines): examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala:60-94 | examples/src/main/scala/org/apache/spark/examples/SparkLR.scala:63-90 \u2014 These two members are one piece of code written twice and then edited apart: 28 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfcaf869fd5aadf0be41f8cf2433a60c0042f99d1a831cfd7a3af243497a8418"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java:40-72 | examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java:40-73 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad52e9ee43cf2c1a2f3c522f835ebc3cd2ff354047eb6a0f2128ce470e013ff3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 24\u002B corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/StreamingKMeansExample.scala:55-81 | examples/src/main/scala/org/apache/spark/examples/mllib/StreamingLinearRegressionExample.scala:50-75 | examples/src/main/scala/org/apache/spark/examples/mllib/StreamingLogisticRegression.scala:49-72 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 24 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/StreamingKMeansExample.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"79fe840582f7406a60be7c8e414eaa9ad1bae035d2c3086f4113e53bedce32ad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (34 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java:31-64 | examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java:29-68 \u2014 These two members are one piece of code written twice and then edited apart: 34 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f9e43fa2d52520d7744147a66a7be716ec84ce63b28036e0ca6b627055038b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/LogisticRegressionWithLBFGSExample.scala:31-67 | examples/src/main/scala/org/apache/spark/examples/mllib/SVMWithSGDExample.scala:30-68 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/LogisticRegressionWithLBFGSExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"b194faf88462a7cd4123203521b1e5217ce13436818f725d7348b8895c481bea"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala:37-73 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredSessionization.scala:40-87 \u2014 These two members are one piece of code written twice and then edited apart: 37 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e4b0566fb6e4c4391f09c986b55a633a9d8b58dee361aa5ec49397dd81d6665"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 26\u002B corresponding lines): examples/src/main/scala/org/apache/spark/examples/graphx/ConnectedComponentsExample.scala:41-66 | examples/src/main/scala/org/apache/spark/examples/graphx/PageRankExample.scala:34-59 | examples/src/main/scala/org/apache/spark/examples/graphx/TriangleCountingExample.scala:42-68 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 26 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/graphx/ConnectedComponentsExample.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdc226f33e5290190ec504b90efc4781988ac7315aa8e1eab36d0726bd8d9ce6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 27\u002B corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/MaxAbsScalerExample.scala:27-53 | examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala:28-55 | examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala:28-58 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 27 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/MaxAbsScalerExample.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"357f26b149b14d1909d2ec2e19e4af71d426a97c4229812e1c0db37b251bef88"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala:50-75 | examples/src/main/scala/org/apache/spark/examples/LocalLR.scala:57-77 \u2014 These two members are one piece of code written twice and then edited apart: 21 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaf8e6398350e099bc32529f986653800c319afd3d94ad7a68a8bbc790bb8ecc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (23 corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala:38-60 | examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnySVD.scala:38-60 \u2014 These two members are one piece of code written twice and then edited apart: 23 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"2004455a7430e0e966e929747d6d4b3826fa7cd08859e8ca7882337ff23868b7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala:29-54 | examples/src/main/scala/org/apache/spark/examples/mllib/PMMLModelExportExample.scala:29-57 \u2014 These two members are one piece of code written twice and then edited apart: 26 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b0e548c2638af75a26ed89131ee1bc70f13dd19f0d3becf8663af19d5b9777f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala:37-68 | examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala:37-66 \u2014 These two members are one piece of code written twice and then edited apart: 30 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"779c34ef090c74ebcfeca8f07aa41c7e91c090d02984c65ed47eb37c9e26781b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (38 corresponding lines): examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java:322-359 | examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java:509-557 \u2014 These two members are one piece of code written twice and then edited apart: 38 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"52db6cf7393331ceafcf90f8fe3c29be83dd1d97057178b9afcaf0fa444a49e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): examples/src/main/scala/org/apache/spark/examples/LocalALS.scala:77-94 | examples/src/main/scala/org/apache/spark/examples/SparkALS.scala:60-79 \u2014 These two members are one piece of code written twice and then edited apart: 18 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalALS.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"40a0b123c1dd34f51034c86d36d3389f03eb719e9067e208910c271a3b10d511"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): examples/src/main/java/org/apache/spark/examples/ml/JavaRobustScalerExample.java:30-56 | examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java:30-54 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaRobustScalerExample.java"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"8622c3084ef40e17ddfff8d867d8e679ede6339fb9b361bb18f5e767e4e76ae4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala:28-59 | examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala:37-76 \u2014 These two members are one piece of code written twice and then edited apart: 32 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"b16c7bd9df6bf656e0b35e954ef4ec09adef26197d36baab8b0999c13d00f1bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 26\u002B corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala:30-56 | examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala:30-55 | examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala:28-54 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 26 lines, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below: the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain. Factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Left alone, the next edit has to be made 3 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"74b8815b22f42f7bddd52dd8612fae4c356b1de34df1862dd41f6a5bbec79e15"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (33 corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala:28-60 | examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala:28-64 \u2014 These two members are one piece of code written twice and then edited apart: 33 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8a6e93624918e41dff9eee45f9b26214e9fe8aa247bdb8c17f7e410d15156f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): examples/src/main/python/sql/arrow.py:145-159 | examples/src/main/python/sql/arrow.py:172-187 \u2014 These two members are one piece of code written twice and then edited apart: 15 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/python/sql/arrow.py"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"290fe501dd0f3ed2f660344aee31e77ea498579d059ebe27302761b93a5f1831"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): examples/src/main/scala/org/apache/spark/examples/ml/RobustScalerExample.scala:27-53 | examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala:27-51 \u2014 These two members are one piece of code written twice and then edited apart: 25 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/RobustScalerExample.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"86f0c22b83382b63e3dc61ad23ce1bbba2f30ea725c110f58e760ca5e5771890"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): examples/src/main/scala/org/apache/spark/examples/sql/SQLDataSourceExample.scala:238-279 | examples/src/main/scala/org/apache/spark/examples/sql/SQLDataSourceExample.scala:430-477 \u2014 These two members are one piece of code written twice and then edited apart: 42 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/SQLDataSourceExample.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f69c919bdbbcc38bc56aa5bcad3400ebdb070fecfd9c296c546613c84fabfad"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): examples/src/main/python/sql/datasource.py:235-265 | examples/src/main/python/sql/datasource.py:441-474 \u2014 These two members are one piece of code written twice and then edited apart: 31 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/python/sql/datasource.py"},"region":{"startLine":235}}}],"partialFingerprints":{"codehealthFindingId/v1":"b343c7aa152c4b3155ec75bff8a81fd2443bb6c60643adbaf1e01e3dbe4e1d0d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): examples/src/main/scala/org/apache/spark/examples/LocalLR.scala:40-47 | examples/src/main/scala/org/apache/spark/examples/SparkLR.scala:46-53 \u2014 These two members are one piece of code written twice and then edited apart: 8 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalLR.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"428e9dec38f2640e3902b9bcf015f0e487991ac47236974ed84159aad2c1b112"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedTypedAggregation.java:98-104 | examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedUntypedAggregation.java:75-81 \u2014 These two members are one piece of code written twice and then edited apart: 7 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedTypedAggregation.java"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f355c95229bbc593c803ffaff2c2d7cc256c0149ae32148b65fbf4f61531b50"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:352-355 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:151-154 \u2014 These two members are one piece of code written twice and then edited apart: 4 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfa80606b18b407eccdf9399021bd99feaad9a2a8e1d2a9a1eb3f4508384207a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:215-240 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:223-248 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 165 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:215\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9a16ae49a997231d289c16668ff6b4be633d7345fd792811749d3fc768a6564"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201325 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala:32-54 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala:31-55 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala:31-55 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"475235c0ac103c3bd59ace27d8c39043f97447204240402ab0712a7413ae760f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201325 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala:67-89 | examples/src/main/scala/org/apache/spark/examples/ml/MinHashLSHExample.scala:64-88 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala:67\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/BucketedRandomProjectionLSHExample.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"d392ff54217cf96716213af45b29b42e00b6187c28784042ed403add598fb86b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala:41-65 | examples/src/main/scala/org/apache/spark/examples/streaming/DirectKerberizedKafkaWordCount.scala:80-104 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKerberizedKafkaWordCount.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala:41\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cb3d77536285a914ba0aa25f21fb8da924001e1b993ad119a442436610ab2cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:52-74 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala:91-113 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala\u0060 as WHOLE FILES: 85% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala:114\u0060 calls \u0060option\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:75\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"850257d07727cac7146f5ae573f518544d3b0b986dc2c3c44d38b1464ae7c569"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:213-234 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:150-171 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:156-177 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:213\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"14951743bc39b87a69e9eb42dbdb12de7ef82e3104a4db50bc01c4397637c8ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201322 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala:29-47 | examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala:29-50 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7883ab7c1bbfc97e037fe7676051ae75c0bdb21c6abdfba54718a0091123e87"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala:42-61 | examples/src/main/scala/org/apache/spark/examples/mllib/MultivariateSummarizer.scala:43-62 | examples/src/main/scala/org/apache/spark/examples/mllib/SampledRDDs.scala:39-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala:42\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"0efa93dc0d8b81b716e0acb704747a2824819e570ee49cbfc53684cc8e6b644d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredComplexSessionization.scala:96-115 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala:38-57 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredSessionization.scala:41-60 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredComplexSessionization.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c9c09d9525192e7be8397ff85d9566ea50b1294b913961f1da874ac69f64a57"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:97-113 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:98-116 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:104-122 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:112-128 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:97\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2de1362eb4005603013e6e7a38854e099eefec8f986d4e78a0a19f5cf6ba6d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala:32-50 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala:31-49 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala:31-49 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4f326200dda9f03d785bdd74a9f6bd8b92754c91e08677503094044251a1031"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 5): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:115-132 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:118-135 | examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala:84-101 | examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala:92-109 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:124-141 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:115\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbbf5695f76e1a8162d1e10a36588c5f0d716e46bb7ce5a97cd93ff80225dfe8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:84-101 | examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala:78-95 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:84\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f52d33d29cc6cfb92477bd950f2d3b3f722aa7343c0f04a4e4b941f6ea6e20c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/LocalALS.scala:59-75 | examples/src/main/scala/org/apache/spark/examples/SparkALS.scala:63-79 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/LocalALS.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/SparkALS.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 34 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/SparkALS.scala:63\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalALS.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c2d9b6692fc9e2eaa0069f846defda232ed18a79679ed0e2d30f725372a44c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala:38-54 | examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala:42-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"9734ac806aa3d71b45eee66a0084fcbca712ae0995c417f7f7d028bc06536427"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:75-90 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala:115-130 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala\u0060 as WHOLE FILES: 85% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:75\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKerberizedKafkaWordCount.scala:114\u0060 calls \u0060option\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala:74\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredKafkaWordCount.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"8545a4c1bdd2c716a25bff2efbca856059666fda94be0f3d687d520df9c686d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 5): examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:87-103 | examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala:48-63 | examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala:81-97 | examples/src/main/scala/org/apache/spark/examples/mllib/MultivariateSummarizer.scala:49-64 | examples/src/main/scala/org/apache/spark/examples/mllib/SampledRDDs.scala:45-59 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 5 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:87\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala:85\u0060 calls \u0060required\u0060, \u0060text\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala:47\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"e950718066732bb32f47bb3e3bb8736696ca4041685f8a041943d614638c85e7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala:72-86 | examples/src/main/scala/org/apache/spark/examples/ml/FMClassifierExample.scala:72-86 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala:75-89 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala:74-88 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"d132d16bfc342a339e89658455fce93fbbe779d12b2bf0d3b91c182d00d7f607"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala:62-76 | examples/src/main/scala/org/apache/spark/examples/ml/FMRegressorExample.scala:60-74 | examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala:62-76 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala:61-75 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/ml/FMRegressorExample.scala:53\u0060 calls \u0060setStepSize\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala:55\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"d29c51197f62b0686dab7d640ae3cc4f0f4f49bdf5f933970f79119866d3e58a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201315 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/IndexToStringExample.scala:29-42 | examples/src/main/scala/org/apache/spark/examples/ml/OneHotEncoderExample.scala:28-42 | examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala:28-36 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/IndexToStringExample.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"baf790485c7f03cdefd1d5f38f735489aa5eaa95e4b5633fbf957e3cccac3161"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala:81-94 | examples/src/main/scala/org/apache/spark/examples/SparkLR.scala:76-90 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala:81\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"efaf5b15c60d62f64864dcebcce87fc8b91114714f37b320f47b914c1c6eaae9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/graphx/Analytics.scala:76-90 | examples/src/main/scala/org/apache/spark/examples/graphx/Analytics.scala:110-123 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/graphx/Analytics.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a6d974169bd1596d71e463cc9819bb619473fb7729d9e435b5627c02d171548"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala:54-68 | examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala:59-73 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala:54\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"95e748e4c40a4c3e2a23b5e8a2d7e32a924158662f33d62a0da59285cc25ca79"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala:33-46 | examples/src/main/scala/org/apache/spark/examples/mllib/MulticlassMetricsExample.scala:32-46 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala:49\u0060 calls \u0060clearThreshold\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/MulticlassMetricsExample.scala:49\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"a039d7620981ade029c0e85ee1f437c653edefe6df3a204b8529e4c97ac53bce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala:67-81 | examples/src/main/scala/org/apache/spark/examples/streaming/DirectKerberizedKafkaWordCount.scala:107-121 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKerberizedKafkaWordCount.scala\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala:67\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2fa8e673b8c4f63ba2907eecc4eb68db8c672f16c38f46808cf44ca24d324cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:254-267 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:193-206 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:201-214 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:254\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:192\u0060 calls \u0060setMaxIter\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:253\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab078809cf0df51307dc61cdd70543bd44fab0734c85ded57c245d1f295c044e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala:34-47 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala:34-47 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 36 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbdd115d932d19b0289b44880a1baf28fa0f3721bae48e369d48a7b051b0a90c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala:39-52 | examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnySVD.scala:39-52 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"8015ddc58a9f62e65b61aaf79aa8cbe21bbf40dc0028c08ea281e63e69326767"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCountWindowed.scala:68-81 | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredSessionization.scala:49-62 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCountWindowed.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"9542a3586ade9758fcba941ae1a2f15519e9cf7855433501a43d92fca78570e4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:76-88 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:74-86 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:75-87 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:82-94 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae27453433fd44ed50d40b1d1bc771dd927a7ae7ea7b4cc08520b06aaf70dc5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala:32-44 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala:31-42 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala:31-42 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 32 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fa4eeae27ceb43c4cfc27419ad32485eec7562dfcfeacdb64ad997daf158bcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 7): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:108-119 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:111-122 | examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala:77-88 | examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala:85-96 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:117-128 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:123-134 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:71-82 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:108\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca1dc20c9be656fcf4dd4bdb7037ae6bd5cd6b21003717bbd2fd926343ad20e6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/LocalALS.scala:45-56 | examples/src/main/scala/org/apache/spark/examples/SparkALS.scala:47-58 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/LocalALS.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/SparkALS.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 34 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalALS.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b699cf8ade1f355ff1c504d53966488626c562948c43348188b8f71b7a0f760"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:331-342 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:133-144 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:331\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala"},"region":{"startLine":331}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e8f13cf7cc341891deab896f7fd328bb2b2e8e24e2834cc3fba460726afbad8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala:32-43 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala:32-43 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"16df9367b9cd3b9b4f738e9e278e2f95dd957f7fb803adf6b2f867048eae9ce3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala:31-42 | examples/src/main/scala/org/apache/spark/examples/mllib/PMMLModelExportExample.scala:30-41 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe6a2182ab2510731202f9fdee0d36720a8f3a3c11e2d49c32ec3608ff377972"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala:35-46 | examples/src/main/scala/org/apache/spark/examples/mllib/SVDExample.scala:40-51 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"912aa22790396814d4aaec9790198e7731512ef8a2a928ff1f5ccad7abaccd41"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u201311 lines \u00D7 5): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:99-107 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:100-110 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:106-116 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:114-122 | examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala:90-96 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:99\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"12755adca988ac7b925c19764fbd14d879866311ea81b764940e93c2a52dcef7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:69-79 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:67-77 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:68-78 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:54-64 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:69\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf36106e02309e6ecf3ff1ced32725b1003b00dc88e4fc2890ddd11e0c3099f1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala:60-70 | examples/src/main/scala/org/apache/spark/examples/ml/PipelineExample.scala:41-51 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala:60\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/scala/org/apache/spark/examples/ml/PipelineExample.scala:52\u0060 calls \u0060setNumFeatures\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala:71\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"333c6d66b8a9aa97b4a057dddac17f9bcb464d946c6c731ba321630524a64a09"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:313-323 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:117-127 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc06856c0b6aa69c390ab2a8da205716dfb5b04e14833b90adc7884e8517b06e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/DenseKMeans.scala:67-77 | examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala:58-68 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DenseKMeans.scala:67\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DenseKMeans.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b4f2382f4b31d844a12a18c6655d270279789e5bc1bdc9eda19da1f68b38686"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/LogisticRegressionWithLBFGSExample.scala:32-42 | examples/src/main/scala/org/apache/spark/examples/mllib/SVMWithSGDExample.scala:31-41 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/LogisticRegressionWithLBFGSExample.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"5743cf2111d99555ab3dd258051843d47c9de24a03b0cc0db0d838ee4337fcd9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala:53-62 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala:52-61 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala:53-62 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 32 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"99943a4ec0554fe857e23a3857daf60592e52ffb899d893e139fb5e2bee0477a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala:29-39 | examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala:29-39 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee1986201967c56ff7173b9f07bf76c3b4007fed748a1c955fc17e883efe5d40"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:179-188 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:191-200 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:179\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d0b47633ed28b24e94f461f1ff0351294e147f6a46b9a3416ea3c5b47761933"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:114-123 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:131-139 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala:114\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"52cc200561876319096fc1447e066fb2776d5a63b663a0b5cc590758e628565a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 6): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala:31-39 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala:31-39 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala:31-38 | examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala:31-38 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala:30-37 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala:30-37 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 32 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"120434c7e88bac3bd912db881f8abeab232031c968e922689bdb6f32077c29a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala:41-50 | examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala:37-45 | examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala:38-47 | examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala:42-51 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"33eac60f9fcc7b836280311e1316926d39c5f109bbe4225cbf486f4966777989"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:201-212 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:138-146 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:144-152 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed84ce5887c95847f56ed8722f1951fb2011d439cbd7a07f91d3ca3a9bba49d5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:173-181 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:184-192 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:173\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7d2bf00d9393df2938e8c14f9af254f4896f9d6446bec13877e92dadd686aac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala:51-60 | examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala:53-62 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"c79be95042c313fc92dd0cee93ab2c20ff323fdbd46eb250b0f87d8c07fdac3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 4): examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala:89-95 | examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala:90-96 | examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala:96-102 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:104-110 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/ml/GBTExample.scala\u0060 as WHOLE FILES: this scan already matched 10 separate duplicated blocks between them, totalling at least 139 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d6a6b8f383415d659c60262cc0df87395c610bbaf0cc315caf5be74ee1625a5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6\u20137 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/GaussianMixtureExample.scala:31-36 | examples/src/main/scala/org/apache/spark/examples/mllib/LatentDirichletAllocationExample.scala:31-37 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/GaussianMixtureExample.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ba1471123f4b09bd87d6fc42806833e22b100dc055fd4aaa1d189eace5986ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:296-300 | examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:322-326 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala:296\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala"},"region":{"startLine":296}}}],"partialFingerprints":{"codehealthFindingId/v1":"63990a88c116133dcf2ad04b9f215afcfbcd447db5d98eed0c86110696755dff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/LocalALS.scala:38-42 | examples/src/main/scala/org/apache/spark/examples/SparkALS.scala:40-44 \u2014 before extracting anything, compare \u0060examples/src/main/scala/org/apache/spark/examples/LocalALS.scala\u0060 and \u0060examples/src/main/scala/org/apache/spark/examples/SparkALS.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 34 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/LocalALS.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef3214535b89869da5a646099afaed5508686a7ea463e622317377016c8b0e0f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): examples/src/main/scala/org/apache/spark/examples/extensions/SessionExtensionsWithLoader.scala:25-30 | examples/src/main/scala/org/apache/spark/examples/extensions/SessionExtensionsWithoutLoader.scala:25-30 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/scala/org/apache/spark/examples/extensions/SessionExtensionsWithLoader.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbaeca0f1c6f46da7913ebc599e612c52fed5316bd8bebf212808a900f6deabb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24\u201327 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:35-61 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java:36-62 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java:36-59 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 79 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:35\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"c405b751172027967e0e16bfa1f50154a575bcc205c2b3bebd3d3e2f25a14235"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23\u201325 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java:87-109 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinHashLSHExample.java:86-110 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java:87\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"4185d81288d40440ad07374d942b8716e68e85b1fbfa80bff042ad48e9c6f198"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 4): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:71-94 | examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:71-94 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java:73-96 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java:69-92 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 79 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc1bb79dc917912c5cec6801fbec5834ab0512498954f9aa74209e4352bc009a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:54-74 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java:90-110 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java:111\u0060 calls \u0060option\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:75\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac5380f7a199fbce474c2d91b618e49a80e5b710444edd4ef1e0e430672c7f60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201320 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java:267-279 | examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQLExample.java:324-343 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java:267\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"55107f706c1472cf70619fce618c555af0e91c16a284427f05625559ec0379a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeRegressionExample.java:35-53 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java:36-54 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java:36-54 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 48 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeRegressionExample.java"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"0984d5e123259cce1f70a9d7577782291ce6e261094ae8cbb7aa1dca78bc7521"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18\u201319 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaFMRegressorExample.java:63-80 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java:65-82 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java:64-82 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 48 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaFMRegressorExample.java"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1cd89df1c5409bdaf414d66ad891484357b7eebb2b08c338569dbd84587d94c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java:112-130 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCount.java:41-59 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredSessionization.java:40-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1badd929c5f05c57497fa35a0297a64a789854f94b9d5b750b598071ccd965c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201318 lines \u00D7 4): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:34-51 | examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:35-52 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java:35-52 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java:35-49 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 79 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"de56d223cf0d34f7dc3472ecac399aabf66dfed7afe6be37c61cdef9b80a1c95"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201318 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java:117-129 | examples/src/main/java/org/apache/spark/examples/JavaPageRank.java:69-86 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1fd685db33595b94f6d6032e8a799d37115341ab1ff94819f449cf3cab4e7e3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201318 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java:56-72 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java:95-112 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"b75505ef8ba71d2a4106e2c11c0c98dc98abd49a35621ce765f831c070d5a491"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201317 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionSummaryExample.java:32-47 | examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionWithElasticNetExample.java:30-46 | examples/src/main/java/org/apache/spark/examples/ml/JavaMulticlassLogisticRegressionWithElasticNetExample.java:31-47 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaLogisticRegressionSummaryExample.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fa35efce37cc6c9ca4209c6b93cac5097e553e83a52c4cf03134f3e409ef270"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:75-91 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java:112-128 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java\u0060 as WHOLE FILES: 87% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:75\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKerberizedKafkaWordCount.java:111\u0060 calls \u0060option\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java:74\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredKafkaWordCount.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"f154683be15845ddf611312c3129c705b56d078275ad6daf7e104536feea856b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201317 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCountWindowed.java:71-85 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredSessionization.java:49-65 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCountWindowed.java:71\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCountWindowed.java"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"95f8cbf2595d66b4c43cd476b1dcead33c6fdf94b6449f62c0794110b4b91ee3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201316 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java:35-50 | examples/src/main/java/org/apache/spark/examples/mllib/JavaLogisticRegressionWithLBFGSExample.java:40-54 | examples/src/main/java/org/apache/spark/examples/mllib/JavaMulticlassClassificationMetricsExample.java:36-50 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java:53\u0060 calls \u0060clearThreshold\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaLogisticRegressionWithLBFGSExample.java:57\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"73f89359dadee58d94bc3bde7e4301cab20f0702f412491d9741c74de5b27c43"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java:49-64 | examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java:51-66 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java:49\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"08aca8fb79a9cdc0a201aef9243b7cf7742bbc1205c1d534918274703c851a9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201314 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java:44-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:42-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java:41-52 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java:44\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"83e7341b25646e7997de1ff20839062c9ead9bb9eaf3783febc9b7e21666f8bb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java:37-50 | examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSizeHintExample.java:39-52 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSizeHintExample.java\u0060 as WHOLE FILES: 84% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"38fffd2b0c3f3856bc979efbe678281f140bf73ee2ab357836c7e9f025d30150"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:38-49 | examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java:40-51 | examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java:45-57 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:38\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"44f26596f1eb17e1fb03a49f4e51f23d85135bc65709e90955b9d1043b478960"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java:120-132 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCountWindowed.java:70-82 | examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredSessionization.java:48-60 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredComplexSessionization.java"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"1868c37db14aa741e01a43ccb8b616b42f3743c70720e6fc52be0d2bea5ba963"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java:53-64 | examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSizeHintExample.java:65-77 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSizeHintExample.java\u0060 as WHOLE FILES: 84% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java:53\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"98e7756883b42c0738c214392aeb3cb5dac0cff1f9bb1fbccd18268171c7a91a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 4): examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java:41-51 | examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:39-50 | examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:37-48 | examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java:38-48 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java:41\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:50\u0060 calls \u0060create\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:48\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"da0744f929a6968b328c33e2e4053451d0653f59c1fdb277c8f4869e3cec7229"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java:45-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java:39-50 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java:45\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e252fe423aace64992d8f113509a32232eaccf279b00f9ad0051dbf45fef49c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaTrainValidationSplitExample.java:43-53 | examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java:36-46 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaTrainValidationSplitExample.java:43\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaTrainValidationSplitExample.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"127821be14a6fa5568c86175ab8852abc11bcfae77204ed11a45438db3badb96"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10\u201311 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java:57-67 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java:55-64 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java:56\u0060 calls \u0060getTreeStrategy\u0060, \u0060setNumClasses\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java:54\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"e89954c4098e102ccd87dcf0ea963f45c3b28d856fcbb2516ec47040955b2857"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 6): examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java:54-63 | examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeRegressionExample.java:46-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java:55-64 | examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeRegressorExample.java:47-56 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java:52-61 | examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestRegressorExample.java:47-56 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 79 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"2187f8db626050181d0b3cbd830aeedcd44ba7c6535ffc83ba6222c2d484e559"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java:48-57 | examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java:50-59 | examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java:53-62 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cc577a72ef41b6221579c417613b2745ec5f7e48d4d468266bcd8322cb4b2ee"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java:105-121 | examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java:71-87 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java:105\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaModelSelectionViaCrossValidationExample.java"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"40578ce745b0a2096c5129a3c8fb125d4745dbbf270eec1ad278e72bd8a2a71a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6\u20139 lines \u00D7 7): examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java:41-48 | examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java:41-48 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingClassificationExample.java:40-48 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java:40-47 | examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java:34-39 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java:39-45 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java:39-45 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 7 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"3aa04c8444efe3b7861473e4f592bcf973fe160dc81b708355c34377e0a20cda"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java:64-74 | examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostingRegressionExample.java:63-73 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java:63-73 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeRegressionExample.java"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"9db1ed7dcc6dfaff32e1ba0187116b56a57a87f5588f517bda87df23c3f22990"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java:89-96 | examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:50-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java:89\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"12e207ae6b43f85c273b8ee426f61098e5de7ea2fda169fa68f3ee396a5a44e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java:41-49 | examples/src/main/java/org/apache/spark/examples/ml/JavaEstimatorTransformerParamExample.java:44-52 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java:41\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"593e97abce7b3fc5dd0998e8f2fe3d30caeb20c660afa93b331bc40444ca0b49"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:54-62 | examples/src/main/java/org/apache/spark/examples/ml/JavaFMRegressorExample.java:46-54 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"25377cc416d2597df9d7b5e0ffbaf9813d73e8542b4790cfd4439100075dafda"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaTargetEncoderExample.java:65-73 | examples/src/main/java/org/apache/spark/examples/ml/JavaTargetEncoderExample.java:76-84 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaTargetEncoderExample.java"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"d189bdad3c146532364a143868a36aaab58a201686bca5a54b685fe96c1987eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java:53-61 | examples/src/main/java/org/apache/spark/examples/mllib/JavaLBFGSExample.java:80-88 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"86a0a4a8bb58343fe81be61110c2d1ee3bcf7e4de38134f280bb57fde1e3cbaa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java:41-48 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java:41-48 | examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java:40-47 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java:41\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"414181a15c192befa98fb92918cef834ef7917d336ba1f5d2e5685f61c47a416"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:34-41 | examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java:34-41 | examples/src/main/java/org/apache/spark/examples/mllib/JavaLatentDirichletAllocationExample.java:39-46 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:34\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a975d3eb6795ce6c8029c52a54b8556f8a8d673610e7d77fc88d939b393fc60"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:46-52 | examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:47-54 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:46\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:44\u0060 calls \u0060create\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:44\u0060 does not \u2014 after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ba72b0d3b51bce9506f4427d76abbb2f1f647d2cfdce6ee07775f37bcd6aea1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaPCAExample.java:41-55 | examples/src/main/java/org/apache/spark/examples/mllib/JavaSVDExample.java:42-56 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaPCAExample.java"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"52b315649282bb4119e52a25a93d194879ef42070d5a8e77c3e9183869cebb4e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java:82-90 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java:124-132 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java:120\u0060 calls \u0060put\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java:79\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"6040a99e15ece36c67e1a737f747998d79dd956c15e2a4ea1b996d6e271841d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (2\u20137 lines \u00D7 5): examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java:74-80 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java:90-97 | examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java:132-139 | examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java:66-72 | examples/src/main/java/org/apache/spark/examples/streaming/JavaRecoverableNetworkWordCount.java:131-132 \u2014 before extracting anything, compare \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKafkaWordCount.java\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaDirectKerberizedKafkaWordCount.java\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java:74\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccc629ba694171c9f8ee1ee8db0fde3ef8a04cfed980700700283c172031128f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:98-104 | examples/src/main/java/org/apache/spark/examples/ml/JavaFMRegressorExample.java:83-89 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java:98\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaFMClassifierExample.java"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b4a1cf52810262296397d25345cd8053215034e61fe123dbc6dca5ae0e6768f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:43-49 | examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java:43-49 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:43\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1d23e0c68d7f2ee8c184ba33620230ef848c01c043a6bd55c4d0a517dcaf56a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:45-50 | examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java:51-56 | examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:46-52 | examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java:52-58 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:45\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java:44\u0060 calls \u0060create\u0060 and \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java:44\u0060 does not \u2014 after which the two agree again for 3 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4dbc6008c1f37337fd5bf41131e7463b50fab93501d751fa00561ba1d9fe669"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java:89-94 | examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java:50-56 | examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java:47-52 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java:89\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f554aa5384e229ab1afecf3cbf11f5844292a5e6f78de2a4cf02cd0c4417409"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:43-48 | examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java:43-48 | examples/src/main/java/org/apache/spark/examples/mllib/JavaLatentDirichletAllocationExample.java:48-53 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java:43\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaGaussianMixtureExample.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e9713f686e7930d5ce21e20a38edcb3b7bc51bb18a823cb2859e7b1d8c95b11"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java:62-67 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java:62-67 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java:62\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTreeClassificationExample.java"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"172edc373ad02ae3f809a73f62129f094008a07dd23e3c64bff5785b872b9b32"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 6): examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java:67-72 | examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java:51-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinHashLSHExample.java:65-70 | examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java:51-55 | examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java:50-54 | examples/src/main/java/org/apache/spark/examples/ml/JavaVarianceThresholdSelectorExample.java:57-61 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 6 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java:67\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaBucketedRandomProjectionLSHExample.java"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9337bcf2426fc96b86d4b4279519c8e4f99644d7ffdfcaf04c10ffaf5807f22"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java:50-57 | examples/src/main/java/org/apache/spark/examples/ml/JavaUnivariateFeatureSelectorExample.java:57-64 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java:50\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"61d18d92ddd03549468be76860b3dbc64f0d6234a267b8310c3500ee5b81f153"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java:53-57 | examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java:59-64 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java:53\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1e2bdb427e0564694eb777335af8a5ade736744589bbde156b354a843dabf9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java:61-67 | examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestRegressionExample.java:60-64 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java:61\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestClassificationExample.java"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5b4b045e7936bbcb416395bea110af02b5f7aac6757af637443dde8c1551cf7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedTypedAggregation.java:107-113 | examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedUntypedAggregation.java:84-90 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"examples/src/main/java/org/apache/spark/examples/sql/JavaUserDefinedTypedAggregation.java"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"025d0422c0ff95b1c490b4d8977ffc71a9aff5d9d50c43721db4b74fce527475"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SparkSqlAstBuilder (LCOM4 28): SparkSqlAstBuilder\u0027s methods fall into 28 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 28 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a28600f3f4f29b85cffdf3a7c306523b016776dc56fdf350bdd5e5366204dc1"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: Shim_v2_0 (LCOM4 27): Shim_v2_0\u0027s methods fall into 27 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 27 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"f36a95cc1b89aea0845fe5ad39c10e4de88acd2ceb52adb68c0dda8e8941cc3a"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SQLShuffleReadMetricsReporter (LCOM4 17): SQLShuffleReadMetricsReporter\u0027s methods fall into 17 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 17 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLShuffleMetricsReporter.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"d145fd37f65ff1496f3b11778d61352c2d8adea89bc3c3e8453e8e510de68f5c"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SparkContext (LCOM4 12): SparkContext\u0027s methods fall into 12 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 12 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa6f6001a93e48a967d959a2fc5f1ffe56645ff2045405fc5358230fb03c4edf"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: QueryPlan (LCOM4 12): QueryPlan\u0027s methods fall into 12 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 12 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c980502007b45321152c38724e46426cac986510804d9eeb3c6838685743c23"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SparkHadoopUtil (LCOM4 11): SparkHadoopUtil\u0027s methods fall into 11 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 11 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"492d52f0b3225f958343719bc846fe298f32816bc48d78f47d8052ae8c79409e"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: InMemoryCatalog (LCOM4 11): InMemoryCatalog\u0027s methods fall into 11 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 11 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"71adaebab7c96ee4347af3b7092d4cae31050cd2403bca7e748d5d57d774b8a9"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: TreeNode (LCOM4 9): TreeNode\u0027s methods fall into 9 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 9 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b0c4ad86d536c8fa14f689c88c9054bdcc6548e5e8f44ee8d2b5f284368ca22"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SpecificInternalRow (LCOM4 8): SpecificInternalRow\u0027s methods fall into 8 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 8 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/SpecificInternalRow.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"df2685a20d6bdb2aedcfe2afc3661be93788f8280fda656dbae2c449cb474821"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: GraphOps (LCOM4 7): GraphOps\u0027s methods fall into 7 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 7 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe0ca72a907c2179586df8fff8fde50299c5621fdedfb1ce52d78b1aa201a66a"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: StreamingJobProgressListener (LCOM4 7): StreamingJobProgressListener\u0027s methods fall into 7 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 7 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"02eed9e53e15fff2793c8a078720fcff661da96fe46ad605aeabbc1f9397e8ee"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: StandaloneSchedulerBackend (LCOM4 6): StandaloneSchedulerBackend\u0027s methods fall into 6 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 6 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/cluster/StandaloneSchedulerBackend.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"e98794af973e09fb36e3dcb5904222cc5787ae557966a22bc71a91bd4bf9daa7"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: FMClassificationModel (LCOM4 6): FMClassificationModel\u0027s methods fall into 6 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 6 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cfeaabd93f974da108029bc4ce0fa857a699bca0e15efc8186a183de12b3950"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: YarnSchedulerBackend (LCOM4 6): YarnSchedulerBackend\u0027s methods fall into 6 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 6 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"5398b3a117ea9e6ebc420076e44307a696a0e51e7af2e4c7c857b5323648965d"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: TimeTypeConnectOps (LCOM4 6): TimeTypeConnectOps\u0027s methods fall into 6 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 6 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimeTypeConnectOps.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffb478cb121c2e5d4e20493a6b5c7a4ecb44eb1e68ea8ec21bf416f432ce95dc"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: TransformWithStateExecBase (LCOM4 6): TransformWithStateExecBase\u0027s methods fall into 6 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 6 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExecBase.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"7da7d99eb3b292a31860bc35d7a5f90ac644df6b7a085249058fcb9daf90d123"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SecurityManager (LCOM4 5): SecurityManager\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SecurityManager.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"30c74e49249d1525ff9762328594090021d02ef0e028d830fc66ed55b9253407"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: HadoopMapRedWriteConfigUtil (LCOM4 5): HadoopMapRedWriteConfigUtil\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/io/SparkHadoopWriter.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac62d06fb3b8cb1b6a0d21afd1382185cf6856db51173755115517b50e39dc0e"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: NewHadoopRDD (LCOM4 5): NewHadoopRDD\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8b852a5ecee8491a7ecb6a985f3e3e1d5409d2e6f4a4880cb90b31055d84410"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: LinearSVCModel (LCOM4 5): LinearSVCModel\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fddbc26a1cb6d98761afb6908dbfe5b36cc21ffc51076b812491ac1e24166dc"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: LDAModel (LCOM4 5): LDAModel\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"26b1b9df84c09cd918789c833f41b328970553f140db65e4d7b9b305782ab495"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: LDA (LCOM4 5): LDA\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"9db79132898617fb9f4e1fc4f8373808fab7772fca579d776a06fefd04a93be3"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: BinaryArithmetic (LCOM4 5): BinaryArithmetic\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"225e9f7d1d5e3a3e0396ee266c3542e6c7e99daa3546dd3a34b93e0061ce3818"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SparkSession (LCOM4 5): SparkSession\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad63c92a99defd02d96d529c00158d4258c92227c78affb3cf4f15efa07c8b05"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SparkPlan (LCOM4 5): SparkPlan\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cc981e2c56ccaad4ce568a91c6fcc5bfbabfa10e3d90f31f65674d85a00ea90"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: RocksDBDataEncoder (LCOM4 5): RocksDBDataEncoder\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"4096fbed1f0e6584426a641d36073d221e750a5bed9b8cdb83af52ec4ca0db37"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: Shim_v4_0 (LCOM4 5): Shim_v4_0\u0027s methods fall into 5 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 5 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":1305}}}],"partialFingerprints":{"codehealthFindingId/v1":"38985a8e9c6c32adc7846a03db20839cc5a9d3320f28530fa48e05cef12649ab"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: KafkaRDD (LCOM4 4): KafkaRDD\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaRDD.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cc47a86e421a759437c5642842ad1951c632af4c7c2ddb75561aa647850bcd2"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: MasterPage (LCOM4 4): MasterPage\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"56ab1c32a812159b4af1c9f23fe6d8d5a0a9b55b00b05406695dc44ef81e420b"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: RDD (LCOM4 4): RDD\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"2299e6b8836fbffee937afc059d3b2ef621b7c8e486d53ee6a83308f6a44558b"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: BlockPagedTable (LCOM4 4): BlockPagedTable\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"524fce774b749a18b2b87dcd545cd58d02552e4735844201995bccf69c0ebe18"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: BitSet (LCOM4 4): BitSet\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/BitSet.scala"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"49bbafa641e1b64d3e39a210520e21faed55343ea6512e11c1e696b3c93454f7"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: EdgePartition (LCOM4 4): EdgePartition\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2eebcce6ff72911f442151088355994aa0c879a7774919b2d548312161a5b1d"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: MultilayerPerceptronClassificationModel (LCOM4 4): MultilayerPerceptronClassificationModel\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6c4d3f9474fbb9685cd5a12cc5eb76f0703f92cdcc64929acaeb5876911ab6f"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: KubernetesClusterSchedulerBackend (LCOM4 4): KubernetesClusterSchedulerBackend\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"466aa39a8f3dee8146d0b7dd3b977a02689bd62f7a72954b8ae7b4b577693460"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: YarnSchedulerEndpoint (LCOM4 4): YarnSchedulerEndpoint\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d36bea287a326f5c27311df4b98be4b6a8ce279c4f1857262c20ccea1e56a19"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: DataFrameWriter (LCOM4 4): DataFrameWriter\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"f796e73424a88917cd5d947b270733b47211a968e601144b6201c6139e36f627"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: Analyzer (LCOM4 4): Analyzer\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"06fc07f7a84a58d0f38dee47688e99e5b9774bcd2fa931395f43fad0b1506b93"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: ExceptionHandlerTriggers (LCOM4 4): ExceptionHandlerTriggers\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SqlScriptingLogicalPlans.scala"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca0d669f603c0c65e9801c22288f18a58aa85944c82927f6e6af57329b5cd1da"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: TimestampNTZNanosTypeConnectOps (LCOM4 4): TimestampNTZNanosTypeConnectOps\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimestampNanosTypeConnectOps.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"323e81234c43214906b3e96ba0f93eb46def346f53a8f4f7aaa8b2035ff95258"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: TimestampLTZNanosTypeConnectOps (LCOM4 4): TimestampLTZNanosTypeConnectOps\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/types/ops/TimestampNanosTypeConnectOps.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"66ec6204b5bfbf4aa45aae1adbd96490ced20e655495bd3a370e9358d8d8165b"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: ParquetFilters (LCOM4 4): ParquetFilters\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"089090a7b416053d12538e20261061898783337a91e4629a38e155a99d50c99f"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: SymmetricHashJoinStateManagerV4 (LCOM4 4): SymmetricHashJoinStateManagerV4\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"654bd1bbb65d3e9904859e21031bbf846abcb0d09529743d7ccb221b1c1d0996"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: StateTypesEncoder (LCOM4 4): StateTypesEncoder\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateTypesEncoderUtils.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aeb87479e76019dec6c51e2714fd9acb83bfa9982811510a1a482bfc4678224"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: StatefulProcessorHandleImpl (LCOM4 4): StatefulProcessorHandleImpl\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statefulprocessor/StatefulProcessorHandleImpl.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6542c3f77b3f3dc7c58e49ec2c7365f036065425244f97867ef529cb5a07886"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: ForStatementExec (LCOM4 4): ForStatementExec\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":1068}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab68eddf81e105adcb4a0272e3f529eed832d90b3824ce81979b0c08e2f74cc8"}},{"ruleId":"D6","level":"warning","message":{"text":"Low cohesion: PartitionKeyedAccumulator (LCOM4 4): PartitionKeyedAccumulator\u0027s methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable \u2014 your repository\u0027s bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected \u2014 and which would otherwise dominate this list \u2014 are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/util/PartitionKeyedAccumulator.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ae7db623bf006efa5d643d92c49601b2f2732f6ad9dcc3795a5fde4b04c9f51"}},{"ruleId":"D8","level":"warning","message":{"text":"Coverage not measured \u2014 JavaScript/TypeScript suite: Coverage NOT MEASURED: the JavaScript/TypeScript half could not be measured \u2014 the dependency install for ui-test/ refused the committed lockfile (npm error code EUSAGE), so the suite never ran. Coverage is excluded from the score rather than counted as a near-zero. The named suite step is one the repository\u0027s maintainers can perform; once it passes, the real number is measured on the next scan."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"62e63e619c28f057e129f2997c965d32a457366a9ce18ca019ffb6bdfba85c99"}},{"ruleId":"D10","level":"warning","message":{"text":"No assertions: All inline scripts use CSP nonce: This method\u0027s body runs code, and no assertion call was recognised in it. Recognised by name: Assert*, *Should*/ShouldBe*, Verify, Expect, Throws, Record, Received/DidNotReceive, MustHaveHappened/MustNotHaveHappened, EnsureSuccessStatusCode and *AndEnsure*, in the test body and in the helpers it calls in the test and test-support code (a helper there that throws when its check fails counts as an assertion) \u2014 so verification routed through a callback object whose members hold the assertions, or through a harness in production code that fails by throwing, is not visible to this check and is not counted here. Read it as \u0027no assertion this check knows how to see\u0027, and if that is right, add one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"ui-test/tests/csp-compliance.test.js"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"64020dc85e239b22ac12885e47e5171947a510cc7983619d9022be3c29e3e60a"}},{"ruleId":"D11","level":"warning","message":{"text":"Test reliability not measured \u2014 JavaScript/TypeScript suite install refused the lockfile: Test reliability NOT MEASURED: the JavaScript/TypeScript suite\u0027s dependency install refused the committed lockfile, so no test ever ran and flakiness could not be exercised \u2014 the dependency install for ui-test/ refused the committed lockfile (npm error code EUSAGE), so the suite never ran. It is excluded from the score rather than counted as a defect; a lockfile in sync with package.json is what lets the suite be re-run."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"166e5a7f1e7f7840934bd0f1c14ddd658b4d7aa7c7571340b9874ca6caf351a2"}},{"ruleId":"D11","level":"error","message":{"text":"Test suite cannot be installed from its own lockfile: ui-test/: The jest suite in ui-test/ was never exercised because its dependency install refused the committed lockfile \u2014 the dependency install for ui-test/ refused the committed lockfile (npm error code EUSAGE), so the suite never ran. The suite is declared and committed but cannot be installed from what the repository ships, so neither this scan nor a new contributor can run it. The ask is the one the owner performs: run the install locally and commit the lockfile it writes."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"8ca27dcb14a1499e798d166ca012c32695318ff74f0eeaa238c489407f8ff945"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala changed 23 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 157 in CheckAnalysis.checkAnalysis0 at line 414. 2 of those changes were fix/bug commits, and the other 21 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b7fcef37f5aad970d13635225969ab904fdb23b06b6f35f4ebf7040c4c57d78"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala changed 15 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 129 in DataSourceV2Strategy.apply at line 158. 3 of those changes were fix/bug commits, and the other 12 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"2672d9b7915f08757215e261a51d3c97219b4e8a3a67907369c48ed21c7544ef"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala changed 27 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 62 in ResolveReferences.doApply at line 1653. 5 of those changes were fix/bug commits, and the other 22 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1653}}}],"partialFingerprints":{"codehealthFindingId/v1":"f40afb0fb214700463c1bb432b2473d0ae6f39ec843f465ca9a7df6b4a169f1e"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala changed 16 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 74 in BasicOperators.apply at line 1033. 1 of those changes was a fix/bug commit, and the other 15 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":1033}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ca6fcc61442d9ec816853f35c1b197f83da763ffdb09094d7b75e47a9459a4d"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala changed 14 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 79 in DAGScheduler.handleTaskCompletion at line 3904. 1 of those changes was a fix/bug commit, and the other 13 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3904}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d98816960aafb1f8ffb3b21f9feb3b440f7f4fe8dcb45aab06000885c28e50d"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala changed 27 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 38 in EnsureRequirements.checkKeyGroupCompatible at line 637. 10 of those changes were fix/bug commits, and the other 17 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"617df6cf441287a3eb36eaf8617fa7051e175588816c0bb10e9a0811ebc85893"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala: sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 104 in ResolveSessionCatalog.apply at line 48. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c196266f77198766e62cb652d4570a0577c044eb6f69738bf7eb82ec544115f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 135 in V2ExpressionBuilder.generateExpression at line 107. 1 of those changes was a fix/bug commit, and the other 5 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e93a9e681aefa040493275a66e1b828314a26fb953b9e3e20d93513714991ed"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala changed 24 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 31 in ColumnPruning.apply at line 1517. 4 of those changes were fix/bug commits, and the other 20 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":1517}}}],"partialFingerprints":{"codehealthFindingId/v1":"b31f3a511d984aa2e0bb2d06d89eb293080e048d398bda9898925e56d3c9323b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: dev/merge_spark_pr.py: dev/merge_spark_pr.py changed 19 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 35 in merge_spark_pr.main at line 3353. 6 of those changes were fix/bug commits, and the other 13 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- dev/merge_spark_pr.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3353}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2f254c5cd24fb038913ed5d80f4bd1d3ed3ae79f04867ab84c319442823f0e5"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/transpile.py: python/pyspark/sql/transpile.py changed 10 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 60 in CatalystTranspiler._convert_chunk at line 707. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/transpile.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"308d53c4c51e670d14cd26ce8e48f54c4bbffd961754c47a6d32291f47d777e5"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 55 in PlanMerger.tryMergePlans at line 404. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/planmerging/PlanMerger.scala"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"54ddda00d19248c67dc1617d420e428102cf533b71959df0d1c6060656211292"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala: sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 45 in ParseSqlResult.collectPlanReferences at line 593. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/parser/ParseSqlResult.scala"},"region":{"startLine":593}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c79fab3c75f2c308afae8622042c999278539653b51e6b272625db2b59fc363"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 68 in JacksonParser.makeConverter at line 260. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"183e3bd7aff780d1c98cef3e47b2b06d8759dc2fb664e1d6d53e941ee9e04b77"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 110 in UnsupportedOperationChecker.checkForStreaming at line 191. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a4a41318beb4b924b4540ea17e969ca684adea96e9a5bfe8933a36eeaff83d"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/conversion.py: python/pyspark/sql/conversion.py changed 12 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 23 in LocalDataToArrowConversion._create_converter at line 674. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/conversion.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":674}}}],"partialFingerprints":{"codehealthFindingId/v1":"efe7f651a4c98e64d0f79efbf9e5f8bb24f68164b036ceb12fb33f5d9baf784f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 44 in JdbcUtils.getCatalystType at line 211. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"29d45802d5c6e53dfedcaada9616188c1083cf0dfd2206b7e930788eaed9ed3a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/types.py: python/pyspark/sql/types.py changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 42 in types._parse_datatype_json_value at line 2674. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/types.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":2674}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dbf46b016fea2e86154b29b4411c1e44114a0fce156a5c4dafdf37be66fdf80"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala: sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 70 in AvroDeserializer.newWriter at line 172. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"de86cc1911b83557a9746eb582d89cc8fd606a650fad086449ca0e56edc95b74"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala changed 9 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 23 in HashAggregateExec.doProduceWithKeys at line 574. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":574}}}],"partialFingerprints":{"codehealthFindingId/v1":"4832fa55e21b235533f5df8c4b97b1f47c755e22b93f2c567f694b49f7e0cd84"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 29 in CodegenContext.collectInputs at line 1331. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala"},"region":{"startLine":1331}}}],"partialFingerprints":{"codehealthFindingId/v1":"75edab13430c6b3aab2b74037a14b05e0b3b16930e695848c5cfe8bb9fccba60"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 25 in NativePartitionReader.checkArrays at line 999. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ffi/NativeDataSource.scala"},"region":{"startLine":999}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f0cc87edd6018a01a7e4a9b99876535e4ef07aaa4092e3e646d32edd815a75b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 27 in MicroBatchExecution.runBatch at line 1198. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":1198}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb9457818ea9c26b7f80082291a2e770b200ee85ecda4ac8d8a64ac36f926a60"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 27 in FunctionResolution.validateFunction at line 660. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":660}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e5ea1aa09ee330111a37d3f6293a8ecae62efc31fded9d4f36dd24a81c45916"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala changed 9 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in ImplicitTypeCoercion.apply at line 736. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionHelper.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb374e948a0ed90128a14bccc2c052a658d09f7acd17a7bdc1bb072b7cc22400"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 74 in ParquetVectorUpdaterFactory.getUpdater at line 75. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetVectorUpdaterFactory.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"f23c411e654cb10994a3510470b5d7dcbad374972a76edccf6d296878724aef9"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/connect/types.py: python/pyspark/sql/connect/types.py changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 48 in types.proto_schema_to_pyspark_data_type at line 226. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/connect/types.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/types.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"34a53d2d067d78be8f7d2bc0d750e3a88dda747cb196dacaf53ba5a645a3f83b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 23 in ResolveCatalogs.apply at line 42. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"b561a027e071664d1e3fa547b20c1e4b59733d262a4c438c65a7650c51d6b1c5"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala: sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 45 in SchemaConverters.toSqlTypeHelper at line 149. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6a3b74e5aab84d069e96e2b58842ddc521bdb42d073fac52416a70d4b67b536"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in TableOutputResolver.resolveColumnsByPosition at line 520. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TableOutputResolver.scala"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d255a64551f4122ceeb55e28267e0dcfc4cd2820a17cccd39bc83ca9b81252b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: core/src/main/scala/org/apache/spark/deploy/master/Master.scala: core/src/main/scala/org/apache/spark/deploy/master/Master.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 44 in Master.receive at line 234. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- core/src/main/scala/org/apache/spark/deploy/master/Master.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"b59c2c645930c7fd699f0aa5e1e3f99fa94a8a55999c1553f6769b56bc171724"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in JoinSelectionHelper.getNonEquiJoinBuildSide at line 372. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"186a3c94af637f5d6694144bf0cf71f02a58e054dcebcf1ef59a48d1539cb06a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 30 in HiveInspectors.toInspector at line 1085. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1085}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b2189ef600d57eb93e0eb86fc58922ff5e6a71b7898423638f7b7c4d865bed6"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala: sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in OracleDialect.getCatalystType at line 181. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd98c11d8dff68f51eeec88dbebcd96d196dfd25fab690eef7e08a2aa5588d4b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 28 in ShuffleExchangeExec.prepareShuffleDependency at line 359. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7e6e8c283410b9cb21de99e0178ed6a0273658a189939dddae6801a62b76116"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 22 in RelationResolution.tryResolvePersistent at line 241. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"55c70d8bb17a0d3a448e810b9b621163140ddebe3958ad2c9095991c5dbf4520"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 27 in CreateSQLFunctionCommand.run at line 73. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"4236827912531439aeb15e22426d5b382f5d6c74cddff0c7a7353d7588eb86ce"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 18 in OrcUtils.orcTypeDescription at line 456. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":456}}}],"partialFingerprints":{"codehealthFindingId/v1":"1491d22e368853a5b1f7e7c8ad3bebfe7073e34aef2c7d03f0473953e72d16ff"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 18 in VectorizedColumnReader.readBatch at line 257. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"55287b5cf79460d60df679bbc9bdee0117886a1c36e05743f98bc79cd850da46"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 34 in TypeCoercion.implicitCast at line 202. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb3d7a9b8d0ce1600dccb2e8783b7b8677d593c84901f4629803434033736e14"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in InjectRuntimeFilter.tryInjectRuntimeFilter at line 485. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"59359e3225766ef07453ba805704b366c6a2f2dfef4d8f6b636c4bee007bb278"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: core/src/main/scala/org/apache/spark/TaskContextImpl.scala: core/src/main/scala/org/apache/spark/TaskContextImpl.scala changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in TaskContextImpl.markTaskCompleted at line 258. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- core/src/main/scala/org/apache/spark/TaskContextImpl.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskContextImpl.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0dca1368a98cfbc285e43f0a67b94e75de40531b2d36f7d33d2ea766b000d6f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 32 in Literal.sql at line 654. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala"},"region":{"startLine":654}}}],"partialFingerprints":{"codehealthFindingId/v1":"783596fe22f098bd0003ac91b4bae69bd713727fbd33160c1333f18921a52073"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 24 in ParquetFilters.valueMatchesParquetType at line 958. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":958}}}],"partialFingerprints":{"codehealthFindingId/v1":"70960b19f90abb2c6aa64740797c92378e938f94d109a0f40deacc8303392b1c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 24 in InsertIntoHadoopFsRelationCommand.run at line 83. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ac5d9638bf809f9396681e0985c5396407ccef6f73936165838ac2457aa3a5b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala: core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in FsHistoryProvider.doMergeApplicationListingInternal at line 1056. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":1056}}}],"partialFingerprints":{"codehealthFindingId/v1":"db6ed4fcb57ea5ea65d576ae11e0b37939ac95a75b5e1710aba13a2b377fea9b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/udf.py: python/pyspark/sql/udf.py changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in UserDefinedFunction.__init__ at line 168. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/udf.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udf.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"c05bb19e5e53b5b2e1d026f710a67cc698be52766bcb7660a4a6e24e3f816e45"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/connect/local_server_pool.py: python/pyspark/sql/connect/local_server_pool.py changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 21 in ServerPool._reap_retired at line 715. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/connect/local_server_pool.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/local_server_pool.py"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"2120451a0f1369f6302fcfbc84c6a437bd0b7578d9ac5b7e708a9dbcf00e3020"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in RewriteDistinctAggregates.rewrite at line 272. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e54c5be410f3793de8b1d8fe57cc8b4a8f658df5e904794ddafb85d3def1e8b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in TungstenAggregationIterator.processInputs at line 210. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregationIterator.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ba622993d476fdd6c119638190266bf05fbf9ba24b6599f30401320ae1bdde6"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in LateMaterializationParquetRecordReader.evaluateStorageFilter at line 708. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java"},"region":{"startLine":708}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f20d6a90072933059b4885c97f80a345a87aefec6d542d62490de1cafaa8c94"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala: connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 35 in ProtobufDeserializer.newWriter at line 249. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"a75aaf50b966c5a2525b040647d58aeb16d45dab22e52bc83fb9db52b81cd6be"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in JDBCRDD.compute at line 284. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCRDD.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"36a8907c976f08857cb0cb9d1c7bd72ecf8b06e1199e7f983036b284b8d1d58b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java: sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 34 in ArrowColumnVector.initAccessor at line 193. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ArrowColumnVector.java"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"626642a58dd7bf9e503d7c67c9bb89eaa9331204e9c78298cb6662eaa29bcc5c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in PreprocessTableCreation.apply at line 148. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6d73d53b71f0b6a712722c939be849bf79ee3b3215cf25439ac5691abf24011"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: python/pyspark/sql/pandas/types.py: python/pyspark/sql/pandas/types.py changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 21 in types._check_arrow_array_timestamps_localize at line 554. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- python/pyspark/sql/pandas/types.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":554}}}],"partialFingerprints":{"codehealthFindingId/v1":"738c5cd4615d1bdee334d35b3ecc8f8c0ad3bc465a6491821fad2589c0c203af"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala: sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 30 in DataType.nameToType at line 271. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"9edb4f9d39c33d80e6eff4d2a022acb5e5c9173e9937831140aab0ad773da64c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in DeduplicateRelations.apply at line 39. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"faca2d40bb1312973168ad89ab0de39ec4e479c3a993fdb18dceae95e6ba8d8d"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in UserDefinedPythonFunction.builder at line 66. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f22eadcbeb8791238ff18bece916ece996a4847145bfe9eec0ea036d26cbafb"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala: core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in AllJobsPage.render at line 278. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"80e154b74b327800a83477f6616b5491e1f223f17a97434d7b86cc408f5b913a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala: resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 18 in BasicExecutorFeatureStep.configurePod at line 112. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/BasicExecutorFeatureStep.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"6810628ee37b2a13f8a696c9ea7ec0b8d061e38c8111d244e292d1964eea4f64"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in ExternalLookupJoinEligibility.apply at line 93. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FormExternalLookupJoin.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"84ac4388b4d05bd06c6d5753a6efb82cd4d71685507a4ea67e7097b638e00cbe"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in PrepareExternalLookupJoin.prepare at line 91. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PrepareExternalLookupJoin.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"79c88f3ce30a08bcb2864cf825bc38d2eb4da9dc1203850738a5387dce6e4a47"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in util.usePrettyExpression at line 91. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"bae9859a4d138afa39614070e712219c863d85a6a4420c442a5d1c84fa048fc8"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 23 in UnwrapCastInBinaryComparison.unwrapCast at line 112. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"df04ae01a17c584623258d3ad78f221ce16bbcd543794c6c2ed68c2c0ee4512a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in SQLExecution.withNewExecutionId0 at line 205. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, with the area under test before it moves. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecution.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cae745a1f9d6e1edb6e496449be7edeceef7ac1f26294918f6f2de89cc87f4d"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/OffsetSeq.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/OffsetSeq.scala changed 6 times in last 90 days and 4 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 8 (its worst body is OffsetSeqMetadata.setSessionConf at line 365), AT OR UNDER the 15 threshold, so this is deliberately not filed as a churn \u00D7 complexity hotspot \u2014 the difficulty here is in the behaviour the file has to get right, not in its control flow, and refactoring it for complexity would be the wrong move. The repairs counted were: \u201C[SPARK-60905][SS] Fix streaming query restarts from checkpoints before Spark 4.4 when a filter uses a Python UDF\u201D; \u201C[SPARK-60885][SS] Fix wrong results by changing \u0060avoidDoubleFilterEval\u0060 across streaming query restarts\u201D; \u201C[SPARK-60632][SQL] Fix the LIKE/RLIKE expensive heuristic to look at the pattern\u201D; \u201C[SPARK-59919][SS] Fix OffsetSeqMetadataV2 missing shuffle partitions on rebinding\u201D. Each one is a case this code did not handle. Before the next change lands here, check that every one of them is pinned by a test that fails without its fix; where the same area keeps coming back, the durable fix is usually at the interface that keeps being misused rather than at the line that was last corrected. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/OffsetSeq.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/OffsetSeq.scala"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef4e5a86d521a8de6d78267da2a6a68a012b522f6ad3aca5cf0460810c56de28"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala changed 6 times in last 90 days and 4 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 12 (its worst body is PartitioningUtils.parsePartitions at line 117), AT OR UNDER the 15 threshold, so this is deliberately not filed as a churn \u00D7 complexity hotspot \u2014 the difficulty here is in the behaviour the file has to get right, not in its control flow, and refactoring it for complexity would be the wrong move. The repairs counted were: \u201C[SPARK-60825][SQL] Fix missing validation of datetime partition values when ANSI mode is off\u201D; \u201C[SPARK-60818][SQL] Fix wrong TINYINT and SMALLINT partition values when they are out of range\u201D; \u201C[SPARK-60797][SQL] Fix wrong decimal partition values when the scale differs from the schema\u201D; \u201C[SPARK-51830][SQL] Fix partition type mismatch when validatePartitionColumns is disabled\u201D. Each one is a case this code did not handle. Before the next change lands here, check that every one of them is pinned by a test that fails without its fix; where the same area keeps coming back, the durable fix is usually at the interface that keeps being misused rather than at the line that was last corrected. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7878b9ebc1dba45fffd1db10ae7e7fa77f6af4332a7d2612cb837ad42bfe90"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TransformExpression.scala: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TransformExpression.scala changed 4 times in last 90 days and 4 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 15 (its worst body is TransformExpression.storedAlike at line 485), AT OR UNDER the 15 threshold, so this is deliberately not filed as a churn \u00D7 complexity hotspot \u2014 the difficulty here is in the behaviour the file has to get right, not in its control flow, and refactoring it for complexity would be the wrong move. The repairs counted were: \u201C[SPARK-60522][SPARK-60027][SPARK-60539][SQL] Fix storage-partitioned join failures and wrong results when Spark cannot evaluate a partition transform as is\u201D; \u201C[SPARK-59887][SPARK-59901][SQL] Fix wrong results when a storage-partitioned join pairs a transform of a join-key expression with one of a column\u201D; \u201C[SPARK-59121][SQL] Fix wrong results when a storage-partitioned join reduces the partition keys of both sides\u201D; \u201C[SPARK-59045][SQL] Fix SPJ ClassCastException when reducer changes partition key data type\u201D. Each one is a case this code did not handle. Before the next change lands here, check that every one of them is pinned by a test that fails without its fix; where the same area keeps coming back, the durable fix is usually at the interface that keeps being misused rather than at the line that was last corrected. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TransformExpression.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TransformExpression.scala"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"83277ee57a2654d428a9b9af89a2f216fb62ab5fb3106011bb72123ea9ec070d"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/InvokeProcedures.scala: sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/InvokeProcedures.scala changed 4 times in last 90 days and 3 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 6 (its worst body is InvokeProcedures.invokeProcedures at line 41), AT OR UNDER the 15 threshold, so this is deliberately not filed as a churn \u00D7 complexity hotspot \u2014 the difficulty here is in the behaviour the file has to get right, not in its control flow, and refactoring it for complexity would be the wrong move. The repairs counted were: \u201C[SPARK-61669][SQL] Fix CALL failing with INTERNAL_ERROR when an argument has a Python UDF or a nested IN subquery\u201D; \u201C[SPARK-61656][SQL] Fix CALL failing with INTERNAL_ERROR when an argument has an IN subquery\u201D; \u201C[SPARK-61557][SQL] Fix CALL failing with IllegalArgumentException when an argument is not foldable\u201D. Each one is a case this code did not handle. Before the next change lands here, check that every one of them is pinned by a test that fails without its fix; where the same area keeps coming back, the durable fix is usually at the interface that keeps being misused rather than at the line that was last corrected. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/InvokeProcedures.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/InvokeProcedures.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9d1e5ebadc974d088e5ad459c10bc9ce15951dc02bced3c86b04b6f9a10a567"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala: sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala changed 3 times in last 90 days and 3 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 6 (its worst body is LogicalRDD.fromDataset at line 186), AT OR UNDER the 15 threshold, so this is deliberately not filed as a churn \u00D7 complexity hotspot \u2014 the difficulty here is in the behaviour the file has to get right, not in its control flow, and refactoring it for complexity would be the wrong move. The repairs counted were: \u201C[SPARK-61256][SQL] Fix wrong results by stale partitioning and ordering when a checkpointed Dataset is joined with its source\u201D; \u201C[SPARK-61254][SQL] Fix wrong results by stale LogicalRDD constraints in checkpoints and recursive CTEs\u201D; \u201C[SPARK-61088][SQL] Fix wrong results by stale partitioning and constraints when a checkpointed Dataset is self-joined\u201D. Each one is a case this code did not handle. Before the next change lands here, check that every one of them is pinned by a test that fails without its fix; where the same area keeps coming back, the durable fix is usually at the interface that keeps being misused rather than at the line that was last corrected. Counted over 2026-08-15..2026-11-13, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-15 20:39:13 -08:00\u0027 --until=\u00272026-11-13 20:39:13 -08:00\u0027 --full-history --no-merges -- sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"07e2e5edd2018e99ebdfc00bc2a9e9a4c8a94fc4ce2fafea68a4552327c0d748"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #1: If anonymized user #1 becomes unavailable, 48 significant file(s) lose their only recent owner: mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala, mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala, mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala, mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala, mllib/src/main/scala/org/apache/spark/ml/evaluation/ClusteringMetrics.scala, mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala (\u002B40 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"0484c493a0b320b25b150ad89fa987757c1e262e768182460acac6fc141c0e87"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #2: If anonymized user #2 becomes unavailable, 35 significant file(s) lose their only recent owner: core/src/main/scala/org/apache/spark/deploy/master/Master.scala, mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala, core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionServer.scala, core/src/main/scala/org/apache/spark/scheduler/cluster/StandaloneSchedulerBackend.scala, core/src/main/scala/org/apache/spark/deploy/client/StandaloneAppClient.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/objects.scala (\u002B27 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"4d6e29d63ae62efd29efea9753460dcefca93b01bd7a354318a5faeffc14a151"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #3: If anonymized user #3 becomes unavailable, 11 significant file(s) lose their only recent owner: core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala, core/src/main/scala/org/apache/spark/util/collection/ExternalAppendOnlyMap.scala, streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala, mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala, sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/STUtils.java, dev/spark_merge_footer.py, sql/api/src/main/scala/org/apache/spark/sql/types/GeometryType.scala (\u002B3 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"1cbcb8214eebdef1417b84d30c30feb22e2c644a1a9ad5e64c1d8669b56458a1"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #4: If anonymized user #4 becomes unavailable, 11 significant file(s) lose their only recent owner: common/kvstore/src/main/java/org/apache/spark/util/kvstore/InMemoryStore.java, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java, resource-managers/kubernetes/core/src/main/scala/org/apache/spark/shuffle/KubernetesLocalDiskShuffleExecutorComponents.scala, common/sketch/src/main/java/org/apache/spark/util/sketch/CountMinSketch.java, common/kvstore/src/main/java/org/apache/spark/util/kvstore/ArrayWrappers.java, sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/RunTerminationReason.scala, core/src/main/scala/org/apache/spark/scheduler/TaskInfo.scala (\u002B3 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"4004ec3de879ff7b2846cb458b5220dd8523d20c0af66346c47fd1c0f9f05cff"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #5: If anonymized user #5 becomes unavailable, 10 significant file(s) lose their only recent owner: common/network-common/src/main/java/org/apache/spark/network/TransportContext.java, core/src/main/scala/org/apache/spark/serializer/JavaSerializer.scala, common/network-common/src/main/java/org/apache/spark/network/server/AbstractAuthRpcHandler.java, common/network-common/src/main/java/org/apache/spark/network/sasl/SaslRpcHandler.java, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlocks.java, core/src/main/scala/org/apache/spark/deploy/master/ZooKeeperPersistenceEngine.scala, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FetchShuffleBlockChunks.java, streaming/src/main/scala/org/apache/spark/streaming/dstream/RawInputDStream.scala (\u002B2 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"61fb7b36368d27bf9eb41a3fd65299ec6cd28e40f52f23adca6be141a0766e95"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #6: If anonymized user #6 becomes unavailable, 9 significant file(s) lose their only recent owner: python/pyspark/eval_handlers/_udtf.py, python/pyspark/eval_handlers/_pandas.py, python/pyspark/eval_handlers/_elementwise.py, python/pyspark/eval_handlers/_base.py, sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfSerialization.scala, python/pyspark/eval_handlers/verification.py, core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala, python/benchmarks/bench_local_data_to_arrow.py (\u002B1 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"c300f307e903c48bc62aa7a5935064cd9eb08d6f134f6db98677a945825853d1"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #7: If anonymized user #7 becomes unavailable, 8 significant file(s) lose their only recent owner: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/LateMaterializationParquetRecordReader.java, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetStorageFilter.scala, sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetCrossReferenceOperation.java, sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ParquetReadState.java, sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetPrimaryKeysOperation.java, sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ValueCopier.java, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DistributionAndOrderingUtils.scala, common/network-common/src/main/java/org/apache/spark/network/server/StreamManager.java. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"304da6df38ba44fa61195175348a827884c81fe9e9afb908960bff36d02493d2"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #8: If anonymized user #8 becomes unavailable, 6 significant file(s) lose their only recent owner: python/pyspark/sql/connect/local_server_pool.py, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NameStreamingSources.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingRelation.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/SequentialStreamingUnion.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/streaming/StreamingSourceIdentifyingName.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/SequentialUnionAnalysis.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"ff7c9a12c553703de1ce306aed1920c21acabbd424e9c3512d5bf9d288940faa"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #9: If anonymized user #9 becomes unavailable, 6 significant file(s) lose their only recent owner: udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/ExecuteExternalUDFExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PlanExternalUDFs.scala, udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerProcess.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PythonInitAdapter.scala, udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/Termination.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"afed99e75a1592d99cf3d78e3b5b368a6242b9f13598ee8711c90f1e2618329a"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #10: If anonymized user #10 becomes unavailable, 5 significant file(s) lose their only recent owner: sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/codegen/UnsafeRowWriter.java, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CdcNetChangesStatefulProcessor.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateOrdering.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/RowBasedHashMapGenerator.scala, sql/core/src/main/java/org/apache/spark/sql/execution/joins/JoinHelper.java. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"01dc7ac483f97995f03340ecd6c8ddebfaa3e48620a2c27459591e46c74b5411"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #11: If anonymized user #11 becomes unavailable, 5 significant file(s) lose their only recent owner: sql/core/src/main/scala/org/apache/spark/sql/execution/python/ExtractPythonUDFFromLambda.scala, mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala, mllib/src/main/scala/org/apache/spark/ml/image/ImageSchema.scala, core/src/main/scala/org/apache/spark/ui/JWSFilter.scala, connector/kafka-0-10-token-provider/src/main/scala/org/apache/spark/kafka010/KafkaRedactionUtil.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"e3c3b0e0285a871f91ad8cc4c86ca2f7d23818829a072434b2e233a0328e6fba"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #12: If anonymized user #12 becomes unavailable, 5 significant file(s) lose their only recent owner: python/pyspark/testing/mlutils.py, python/pyspark/pandas/mlflow.py, python/pyspark/rddsampler.py, python/pyspark/find_spark_home.py, python/test_coverage/sitecustomize.py. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"1fccdfa89b37d789fb03a571132ce406a5f6fd72b01cea27bd8e89dce6121183"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #13: If anonymized user #13 becomes unavailable, 5 significant file(s) lose their only recent owner: sql/api/src/main/java/org/apache/spark/sql/streaming/Trigger.java, core/src/main/scala/org/apache/spark/shuffle/streaming/MultiShuffleManager.scala, sql/api/src/main/scala/org/apache/spark/sql/execution/streaming/Triggers.scala, core/src/main/scala/org/apache/spark/util/EventLoop.scala, core/src/main/scala/org/apache/spark/shuffle/streaming/TaskContextAwareLogging.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"45d6428626c61f6613c9209654a55388d99d493e1bfd40e76f252713bc715553"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #14: If anonymized user #14 becomes unavailable, 4 significant file(s) lose their only recent owner: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala, sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2VersionMap.scala, sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd1ReconciliationStrategy.scala, sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/AutoCdcSchemaUtils.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"57c56f5b43cbe2f2d85239496ccbd5453693d0499e5bd4a8bb9e799a153852f2"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #15: If anonymized user #15 becomes unavailable, 4 significant file(s) lose their only recent owner: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushDownLeftSemiAntiJoin.scala, dev/pr_merge_status.py, sql/catalyst/src/main/scala/org/apache/spark/sql/util/SQLOpenHashSet.scala, dev/next_version_candidates.py. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"50b3f2fe9f1acc6fc0a705d56dc34b3482545fbd097915096ab5810983c39ab0"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #16: If anonymized user #16 becomes unavailable, 4 significant file(s) lose their only recent owner: sql/core/src/main/scala/org/apache/spark/sql/execution/PushDownLocalSort.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PullUpProjectAliasThroughWindow.scala, common/kvstore/src/main/java/org/apache/spark/util/kvstore/KVStore.java, sql/core/src/main/scala/org/apache/spark/sql/execution/RemoveRedundantWindowGroupLimits.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"960ce05ddd37b84e5c87c78ff706fdf210bf8a4c6dfd71c2feddfe8a7ec38e10"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #17: If anonymized user #17 becomes unavailable, 3 significant file(s) lose their only recent owner: sql/core/src/main/scala/org/apache/spark/sql/catalyst/expressions/ParseSql.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/SubstituteParamsParser.scala, sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/CharVarcharCodegenUtils.java. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"abcda38891702cdc879e4f5992f44ea47aecb09746aef291b90a738592a510e4"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #18: If anonymized user #18 becomes unavailable, 3 significant file(s) lose their only recent owner: sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SparkPlanGraph.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileDataSourceV2.scala, core/src/main/scala/org/apache/spark/ui/env/EnvironmentPage.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"60745b30fb58a74904fe253ef50c30d76755e171a12c73d15f66272ff2f3dd2b"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #19: If anonymized user #19 becomes unavailable, 3 significant file(s) lose their only recent owner: sql/core/src/main/scala/org/apache/spark/sql/execution/BinByExec.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BinByResolution.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveBinBy.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"fddf5865c5004f2a3b618eb243ab33aa12d6089971a76085c7ac2f4a5f3883dd"}},{"ruleId":"D16","level":"note","message":{"text":"Further sole-owners (lower concentration): 44 other contributor(s) are each the sole owner of a small amount of code below the off-boarding threshold \u2014 folded into the bus-factor score and metrics (237 single-owned of 2863 analysed files in total, counted over production source files of roughly 2,400 bytes or more, excluding vendored, generated, example/demo and scaffolding-template trees and test files identified by path convention, largest first; 2863 of the 4700 production source files in this repository met that bar). They are anonymized user #20 (3 file(s)), anonymized user #21 (2 file(s)), anonymized user #22 (2 file(s)), anonymized user #23 (2 file(s)), anonymized user #24 (2 file(s)), anonymized user #25 (2 file(s)) (\u002B38 more) \u2014 spread or document their files in the same way, at lower priority than the named off-boarding risks above. The files folded here: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/AggregatePushDownUtils.scala, sql/api/src/main/scala/org/apache/spark/sql/types/AbstractDataType.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/IntervalMathUtils.scala, core/src/main/scala/org/apache/spark/util/LastAttemptAccumulator.scala, core/src/main/scala/org/apache/spark/storage/BlockManagerMessages.scala, sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/CLIService.java, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecisionTypeCoercion.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnStats.scala (\u002B44 more)."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6eac528f2429e724e1a97ed868f79eefbcf1888dab4af9a9e673429369bb5b2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: add application-level gRPC flow control in a follow-up,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/grpc/src/main/scala/org/apache/spark/udf/worker/grpc/GrpcWorkerSession.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3da57ef36d384fe51d61c28c5256088a5a875134f15c33f3f044fa524440947"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-57324]: expose queue depth as a metric (early warning for a"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/grpc/src/main/scala/org/apache/spark/udf/worker/grpc/GrpcWorkerSession.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac05175fe4328e4a606bf4f2508239a08a15bd3bafb05e8b859a534f7203f2dd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-57640]: close() is a finalizer often already on the task"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/grpc/src/main/scala/org/apache/spark/udf/worker/grpc/GrpcWorkerSession.scala"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"352452713b3a957485aed2ad59ac992d2299e9dfe7d010c643ef45897e4af91b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Connection pooling -- reuse idle workers across sessions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"717149dfafadf3f34e00d8245747fcfdf1a8a827f2b72955861d97d03c703988"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Security scope isolation -- partition pool by WorkerSecurityScope. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"42e94add5b9587001f0386e9575b18bae6ddb12f3575855af2b6fd1c2906066b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: extract the env state machine \u002B JVM shutdown hook"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"c35860bcef5aece5620964e626f36047ae462c62d61c12d396f55ca51090faaf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: Cleanup sessions as well?"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":376}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7e2c977c8aef256f553d81f729205683cd9386f2b9350c63e11dd17137fa377"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: close workers in parallel -- today shutdown is serialised at"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"584e34bfb42e167b76227d3336763c3c08c6965537de4083c2a83c3582d134e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: distinguish retriable vs permanent environment failures. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"83a13e5151d00abf9fade2e6e3c219e6e85fea4697050cb55dc47be61a566971"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // the future predicate (see TODO above). \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f33270dd1aff9fd4809998d1306c497287577d10f6bd43e88b338d29e37871f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: share one JVM shutdown hook across all dispatchers in the \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerDispatcher.scala"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"d78d3abc74521e1344dffd9934d49dd5ae43d204db5fa03d69547202ed209142"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: idle-timeout tracking and concurrent session capacity. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"udf/worker/core/src/main/scala/org/apache/spark/udf/worker/core/direct/DirectWorkerProcess.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1f5628cde706c4ca3ca36aca0cda5bd23833d23234492b2fd0215ca56ef96d8"}},{"ruleId":"D17","level":"warning","message":{"text":"XxxComment: // XXX Checking every block would require an even distribution of messages across blocks, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/test/scala/org/apache/spark/streaming/ReceiverSuite.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b89db1fbb1a8778b5e8160bb7db8733659071d579ac85075941a1da6c86001e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // events (SPARK-12140). TODO Once SPARK-12140 is resolved we should set it to true."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/StreamingListenerBus.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"3308b0333ab00794807a3f00fca8b7aa35ab3abfd1c91a2151df9bd629c3b3f2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: merge callsites with scopes so we can just reuse the code there \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala"},"region":{"startLine":412}}}],"partialFingerprints":{"codehealthFindingId/v1":"4766dff01ad96ccac7af849ee58b7375f6252db571f818df3c81aff851ec8c24"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-31499): Needs to add a column to describe arguments and their types"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/gen-sql-functions-docs.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5f3f0fae3432de3325c800ce25d91fdbc79ed78e8a7352ecbd9a016f5c557e0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: streaming file data sources in SQL is not currently supported. If and when it is, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/test/scala/org/apache/spark/sql/pipelines/graph/SqlPipelineSuite.scala"},"region":{"startLine":476}}}],"partialFingerprints":{"codehealthFindingId/v1":"a592e468dc0aee6b63c28fa4b362931cead299b4dcf76ef8e570d956ecc227b3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-59268): don\u0027t drop changes to comments and field metadata \u0060desiredSchema\u0060, or"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/util/SchemaMergingUtils.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"4612a41ee8bf72e4f11a24e2c326e1958504267b7c98bef1c0784526f8d84b09"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-57670): Property removal is intentionally not handled here: a property dropped"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/DatasetManager.scala"},"region":{"startLine":697}}}],"partialFingerprints":{"codehealthFindingId/v1":"199fc1d0986b2a04f9149198f1f40a112bf37219002d406779435d26d111e88f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This GC triggers a full scan of the aux table; revisit whether to GC only \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala"},"region":{"startLine":1350}}}],"partialFingerprints":{"codehealthFindingId/v1":"baba8f4ee8a037962b533650a870148eebe0d90c6357e6e51e34ba95928f2ffa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Need a better way to drop the view. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala"},"region":{"startLine":1480}}}],"partialFingerprints":{"codehealthFindingId/v1":"f280ebbb258e7cdbd2e896c8d309850a8249bdea802062e3d381f3f093bb900b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-33219 Disable GetPrimaryKeys and GetCrossReference APIs explicitly"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/SparkMetadataOperationSuite.scala"},"region":{"startLine":690}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba512554e77f3001de755bf68558c546f7adcbc3284da152ecd0e2a985a6f651"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-36180): add hive table here too"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/SparkMetadataOperationSuite.scala"},"region":{"startLine":713}}}],"partialFingerprints":{"codehealthFindingId/v1":"383c434b8a1895765f5a1a249037f1ba64742b9da9fbeadaa80488e149800ec4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Shall use TIMESTAMPLOCALTZ_TYPE, keep AS-IS now for \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkExecuteStatementOperation.scala"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"16d25b0c70980bcf9426a4c369b00ceeaaaa556a97362c311aa668d0a8372fd5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: provide STATIC default value \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/CLIServiceClient.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f627f16f765be89b4989cb2c7871e329cb34ba92c06ac415fad5a07a9ee5da3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Should this really default to FETCH_NEXT? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/FetchOrientation.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c7957030b0a9de8ebf98734937c9f8da06fb04c001d2442e3dd80c64b4f5b10"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: set correct vendorCode field \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/HiveSQLException.java"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fd473e93ecc564d33e923ab1da8691436e3f2c7ada8d3178b9abf5b4c113fac"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: convert sqlState, etc. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/HiveSQLException.java"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb32c06941c8f4cdc776bbe0c5d3c20dedebca6c9479f12f759a2d80fbe69eb7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: replace this with a Map? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/OperationType.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"85c714cac4d2ed1ff9b1ef0aaef06f5ed1d87ebd60de22993b2a6689ba201119"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove this constructor \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/TableSchema.java"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9420b38e4036f25fd634f93161cf4cc23eb1e20a9f12cb2945bc5fc6f41cd07"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: set real configuration map \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a9f1409d811b08d4070339c4e8e506ccbea3354d2ac7893293bb16f51299ff5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We don\u0027t do anything for now, just log this for debugging. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca85ec05a0472484e8197a9ad1d24ed82234813f594b384be030922c76a4706b"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME extract the right info type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d778d225b6a6671bab1375a12d08b81bdae7072dd2cdbb3355297bd82a2b2b7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: set the correct default fetch size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":403}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5543aee04a866d77abe89ba19ced1baf8484696dc9551409715c8a8c42fc75d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: check defaults: maxTimeout, keepalive, maxBodySize, bodyReceiveDuration, etc. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftHttpCLIService.java"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b287ca7ceb27b5e54242a8945ddca1c99e81f58d215dc7d67f03bc3ddb18138"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: make this abstract and implement in subclasses. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/Operation.java"},"region":{"startLine":300}}}],"partialFingerprints":{"codehealthFindingId/v1":"dedad783946b0200c55898879f0e7435db732d1da24aaa10b599695ea87570e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"63bc3c510857bb492d66c6420c5c85edb9be4db61f2f366752c5915ebc9aadcf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ecc5850d6ff996ba8bbb82ea4057cba2c187a35210361ef4013676c40c2cbe3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":769}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ffbe0e200c3dee20740f92394777a334bc935076897e7c5c8892001c89e7981"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":695}}}],"partialFingerprints":{"codehealthFindingId/v1":"96f7bc8646fa873a64afb19f4ecadf8d0cc5ac7ddb2cd7c69cb329058a905196"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: //TODO: Since OperationLog is moved to package o.a.h.h.ql.session, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"92acfc087d59c167a98d9aadfa99934d5c66b119cef726853613cf99c29b6e22"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-34440): Allow saving/loading datetime in ORC w/o rebasing"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/sources/HadoopFsRelationTest.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"7513839a34f6916e218cf8eff4672f2e25b5944257201d636bb2ca62328463e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO In SPARK-46302, the env SKIP_SPARK_RELEASE_VERSIONS has been added to"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveExternalCatalogVersionsSuite.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"70cc84b43a1cf3e04f62e10b59982ad7f8792aa9f08320100d0dd4cb87f0a583"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO in ResolvedDataSource, will convert the schema into nullable = true \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala"},"region":{"startLine":479}}}],"partialFingerprints":{"codehealthFindingId/v1":"40f9cd1057186a51fc20a3011533dc36000c7f74396d93eeaede126769221e96"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Re-enable it after can distinguish qualified and unqualified function name \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/UDFSuite.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"20f6f30e0c81e3b4d54ce8e8d384e178313a31731d8d8c45371ffd4a74df7bcd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Pass this automatically from the table to partitions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/test/TestHive.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6441dcd2d4c668228087cd96d44ddbb314867a7a2a9e487c9af31371a9bbd33"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // HACK: Hive is too noisy by default. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/test/TestHive.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f43561778104ea5b60b1e7cd3a554ea9273ff22ebfc73ed30842c31261f1b4e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50244): We now isolate artifacts added by the \u0060ADD JAR\u0060 command. This will break"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/test/TestHive.scala"},"region":{"startLine":648}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b255358bad1819ddec7c301cf5f94b11b916edf833770cb444224b059e259a2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: remove it? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/AggregationQuerySuite.scala"},"region":{"startLine":1086}}}],"partialFingerprints":{"codehealthFindingId/v1":"08ed8aa903d56228df34d678ac2d143d1a2fbbde0d3a12846a1f0485220ba73a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Auto download the files on demand. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/BigDataBenchmarkSuite.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"485eb3634d243b0f069e9ab855ab592178a3663f9f8022852b6da05a5fc92658"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: need a similar test for non-local mode. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCommandSuite.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e1058c178e548b13a9926d5e61f643be7f3f20741bed86928ff7d427d812ab3"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack: Hive simply prints the result of a SET command to screen, \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"4dd6a585556b24bdc15b59fa5dd762962527eda3371f2add571e9fb25015d660"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Instead of filtering we should clean to avoid accidentally ignoring actual results. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"b389d76ff0dff08a453fb541422a665dd5b6fc0ed4003c464cdc4074484e5d0a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: DOCUMENT UNSUPPORTED \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"d80f67b2fa4436c6ebb4f301c1293f94c34bd50f46580e4e6150a0c146d4d530"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(ekl) this is causing test flakes [SPARK-18167], but we think the issue is derby specific"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala"},"region":{"startLine":1586}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cfc94546c006425574c396e695c22d44a1c91cac7725b2fbbfac3ce087f6512"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to avoid SEGV on some JVM versions. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"304883a1ec808da05ab52c611fa63281b0595717083ff5ed5e0e8831a3a91ddf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add the other logical types. For details, see the link: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala"},"region":{"startLine":863}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ea979f0d6b9bd94ec6cdca152ee758f197498e4af9d9ed490e1be58f3ea8ca5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add more tests. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala"},"region":{"startLine":1025}}}],"partialFingerprints":{"codehealthFindingId/v1":"a272ed34c25b5239ba74b85891b1a7a5196dd5f92d9732200fa84df50f1c41be"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: currently only works on mysql where we manually create the schema... \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuites.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9979c7a08d6bca3688e6062f4e42e49448244c3f52e025fedbbcc3761c83174"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: actually rebuild this jar with the new changes. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/resources/regression-test-SPARK-8489/Main.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfd959447af8e78c9adafc5f4904954e62528a9580ebabfd9c548da1ec84753d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-51957: Fix partition column and EMTPY_DATA_SCHEMA naming conflict"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":368}}}],"partialFingerprints":{"codehealthFindingId/v1":"04995cc42fa3cc87294a9b322e1a01d28172b973cc4ee6ef35971546ee6d9bcb"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // !! HACK ALERT !! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala"},"region":{"startLine":556}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3bf01ea24a9017b24697e927fc6fdbf48dd5bc9648f9d7a3799893cd22befb1"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // !! HACK ALERT !! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SchemaMergeUtils.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"d73392bb1c9cea8b12b52954c4b16e2f6770c78ebbbdd3fb8488377dec10c67b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: hard-coding a list here is not very robust. A better idea is to have some kind of query \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1170}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff8f8604976971cd5e9d6de6e6b2a44a86c108fdd42dd787d3c74eed32643081"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO precise, scale? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala"},"region":{"startLine":1466}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9e7caa401b5b08f83c1d5c5c2dc083599fd4c1ca1178ad3308f2732490691c6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Support for loading the jars from an already downloaded location. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b961d78d957ec7eb83fbddd8fe4cccbc09a90b3e659a4c28aa247949ffb1157"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Finish input output types. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"de2d3725ceb14442006672f3d056d57db602e0d9069f0e50461604fb57a796d2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Check if the paths coming in are already qualified and simplify. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"a84fd072ca4b850606d074730014cab8252a31b44c1583be4695e49764cf2291"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO ideally, we should get the output data ready first and then \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateHiveTableAsSelectCommand.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d9e6ae0a613ada0acb299f5b3b8870a45c9480ef906c9abb3953c98036f370e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: implement hive compatibility as rules. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7116e97818a76d5af889c526ed8c4c91fb76e75db1b3e59cc8962042c9c0d63"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: URI \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"26d9326172a44d8aff90b4f490951c4e26db8d29fd874d358867997304c4cb6c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO URI \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClient.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"050810fc22c631c47c54726ef9469a937f312a4352744a41247c8478361e3141"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO URI \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1051}}}],"partialFingerprints":{"codehealthFindingId/v1":"655d733f36ce5cececa836a82de4f5e7a83473e5ecef956ac427a1a5c034daf3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: In future we can have Spark support columns sorted in descending order \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"5643b37257d391607425b9ee8ac58c007e09e1cbe971229993b385f6f759e4ad"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: figure out how to drop multiple partitions in one call \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":737}}}],"partialFingerprints":{"codehealthFindingId/v1":"3caf49c897195054d5b297b394e57b00884475e2b7a782e08c952ccfb11df2a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Use URI \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1041}}}],"partialFingerprints":{"codehealthFindingId/v1":"559e165dfb662d6f31c2ab2e4cef69456bd9b6096185a562e58d033ea5309c8c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: stats should include all the other two fields (\u0060numFiles\u0060 and \u0060numPartitions\u0060). \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1427}}}],"partialFingerprints":{"codehealthFindingId/v1":"85bfc1c3b94a885d7e382ef3d3dca8fe0ea39d0232d0fcbc9251a8859972f8b6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: still fill the rowCount even if sizeInBytes is empty. Might break anything? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1440}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac69f651fc324669314e9198a6db43b75fb74a47efc9da087eda891e15b67909"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Now, always set environmentContext to null. In the future, we should avoid setting \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala"},"region":{"startLine":1031}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfe541b59df8fbf0d0ddba6791b45ab0f8d1481c5ec271eac066ab0016b5f1b9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove copy logic. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"bda184f8c8d05a820521975e16644f3e69362aef982d04f5638a259280cf9bf8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: bundle in jar files... get from classpath \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"684c5f2640a5911428774b7e9d3d7220209bf4081345377a557a21b0c68424f1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: When we make a threshold of splitting statements (1024) configurable, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala"},"region":{"startLine":1921}}}],"partialFingerprints":{"codehealthFindingId/v1":"16319c2ea5f3f047260f397d18f700d5ccb4903b6eaf62abe015d8416a8fab3f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: \u0060DataSourceV2Strategy\u0060 can not translate nested fields into source filter yet \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameWriterV2Suite.scala"},"region":{"startLine":866}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c49589c94ce830e53343941fa6b75bc857cab525ea59e817d83d37a54fb0d7b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Test CSV V2 as well after it implements [[SupportsReportStatistics]]. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/FileBasedDataSourceSuite.scala"},"region":{"startLine":687}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc89102fa8f16c634ad80b20048897200621c4b5ca2ccfa34103c44cebf726e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: more tests on LCA in subquery \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/LateralColumnAliasSuite.scala"},"region":{"startLine":575}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaabaa89c5e75aab13ccdd3a782f0bd79d7b02766ad095658728b5e2bf0408c6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(anchovyu): When having is supported, re-enable the tests \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/LateralColumnAliasSuite.scala"},"region":{"startLine":1072}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4933e5e66ef04d71e70f83cd6976292c82bb7667862adbd392cf5f9fb608314"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(anchovyu): Remove this tese case and re-enable the \u0022Window on Aggregate\u0022 when having \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/LateralColumnAliasSuite.scala"},"region":{"startLine":1170}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3c81823740d50abbe60bf8cf79555ab2e3a515c70432253e9b34b2c766320bb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: catch exceptions in data frame execution \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9fcbd860abe25e0f7edcc5e05323479adb27bb9c692e7b31e50d4959c793e45"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support other numeric types besides Double \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala"},"region":{"startLine":948}}}],"partialFingerprints":{"codehealthFindingId/v1":"9eb130e9d4543f8877641ff075baa3109f4f0275b750de73d0f60ed5eddbe3e7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support struct types? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala"},"region":{"startLine":949}}}],"partialFingerprints":{"codehealthFindingId/v1":"0085f307edc1b364d6eb6a8ccc0f733ab05624db9f70de3f6a3b6b72ff7ac136"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Ensure true/false string letter casing is consistent with Hive in all cases. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala"},"region":{"startLine":1110}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a134359e3bd8d86c8fc71d6c94cb7056e5126e78fe331a7ee261746916b3626"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support subexpression elimination in whole stage codegen \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala"},"region":{"startLine":1964}}}],"partialFingerprints":{"codehealthFindingId/v1":"0674c09d337cd9275abc6a0c82412862d9938ba87f2b9f5ae672cb726c26392e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: completely fix this issue even when LITERAL_PRECISE_PRECISION is true. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala"},"region":{"startLine":2971}}}],"partialFingerprints":{"codehealthFindingId/v1":"740e202aceaf1e8254ed9cb24435374ab68502e8ba79ac705429d6cd75cb937e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-33718: After clear sessions, the SharedState will be unreachable, then all"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/SparkSessionBuilderSuite.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"e902f9a154a90343de589d85e5dab8510bd1520eab7043fe9c431db269864e32"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-48779 Move E2E SQL tests with column input to collations-basic.sql golden file."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"c91888661e0eac8f498772f536df1c28cb07ea8b725ce6a57c54b43b207d2d87"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50887) Re-enable q22-v2.7 in GitHub Action environment."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/TPCDSCollationQueryTestSuite.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"7019fb9e88cb1f1ac815031fe14a23719560fd15361e0051eb916c785ee9d0a7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Currently some LongSQLMetric use -1 as initial value, so if the accumulator is never \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/util/DataFrameCallbackSuite.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"a99a9b893d325538386db69fb15849a32b184ed4e4a457e720ab6d42e1fa64db"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: test partition pruning when file source V2 supports it. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala"},"region":{"startLine":953}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee8de77b923d40f55630cf39e3e4e6ed1a8278b244db223bf7b396ce567d82cb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove after SC-206585 is fixed"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQueryListenerSuite.scala"},"region":{"startLine":309}}}],"partialFingerprints":{"codehealthFindingId/v1":"48dd2be1741dd6d4ebcebfd153904fdf800fcc46476b4bb243c768025d0a2df8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Probably we should disallow DISTINCT or rewrite to \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQueryOptimizationCorrectnessSuite.scala"},"region":{"startLine":494}}}],"partialFingerprints":{"codehealthFindingId/v1":"350745d28f9d2f5e32135fc0315499cdd001e9f917ac35aa4aa179f9efa36dfe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: currently the streaming framework always add a dummy Project above streaming source \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala"},"region":{"startLine":551}}}],"partialFingerprints":{"codehealthFindingId/v1":"7df87ec012f4a2f6d7fae228553dcd1ee1dff73bb3b53a8c18714c56ea3636a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845] Re-enable tests after full-rewrite is enabled."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2258}}}],"partialFingerprints":{"codehealthFindingId/v1":"c73524f430b678a6a6a69c0c4d7dd8aa8968daabbd725d06088811cb5d48e0e5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845] Re-enable tests after StateSchemaV3 threshold change"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2350}}}],"partialFingerprints":{"codehealthFindingId/v1":"da6fed0d13df7c9c089e6d0323f7fb6a260311632c818581f351237ea2e5a18f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845] Re-enable tests after StateSchemaV3 threshold change"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2569}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ed6fc971c226968cbd460cad24a8c70dcdc4c0a0b13a0a525b6604dd21374ab"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845] Re-enable tests after StateSchemaV3 threshold change"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2645}}}],"partialFingerprints":{"codehealthFindingId/v1":"73431c9f975ec66ee6496549530012d94c9565457d3202ec540fa003fb04da35"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move the corresponding TTLProcessors to this file \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/util/TransformWithStateTestUtils.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c884211f13c3ffed3d45673144753199707dbd578ab2500c082fada1e885749"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: ideally there should be no difference between legacy and non-legacy mode. However, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/internal/CatalogSuite.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c7d8bade770a3ec9a3e739d6abf30528b6e9dfeff6db1dea2a185c45eaadef8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: aggregate node without aggregate expressions can also be a final aggregate, but \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/LogicalPlanTagInSparkPlanSuite.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"d56b6c4a1b28cbe950840ddad9c743c52afc3b2f038f8cb2dc586fc9f72d55fa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: fix this test case by reimplementing the function ResolveAggregateFunctions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/SQLWindowFunctionSuite.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b7d3d67aa2422fdb6f4c420bdf6e5e2bcccd1ccf73422e2c26f17aa1ce277b5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: there is a big (2x) penalty for a random access API for off heap. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchBenchmark.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"99f4f4e36bb26f3a8ec9ed300b8035b0db58363bf73016b459bc58a961926c32"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO[SPARK-55301]: add test with changelog checkpointing disabled after SPARK increases"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/OfflineStateRepartitionIntegrationSuite.scala"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"e778b66c196a96b68f491a88c4fb475d969dfb2052f1d3a970c67db5b7e71067"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO[SPARK-55301]: add test with \u0022avro\u0022 encoding format after SPARK increases test timeout"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/OfflineStateRepartitionTransformWithStateIntegrationSuite.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"fabf2f92c2198d5da1b84a8fa00171121b58a075874151240cc5551ff955a2cb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO test ifEnableStateStoreCheckpointIds = true case after it is fixed. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/RocksDBCheckpointFailureInjectionSuite.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"493ca04bdb7fecc64a39f8c45287e9db0393fb83bc82baa6a22bd246274ff1c5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO after the error is categorized, we should check error class \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/RocksDBCheckpointFailureInjectionSuite.scala"},"region":{"startLine":474}}}],"partialFingerprints":{"codehealthFindingId/v1":"04bd858dd3b1c38dc1fc07fdd87e3134ce237de2ec0a0fc4dc269104fc7304c0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove multiple col families restriction when we add support for \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateStoreSuite.scala"},"region":{"startLine":1321}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3d0a635f77d6d755d91c7ca23e992600f94d37b74c790c3c74fc2ab30801aa4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: update metrics in generated operators \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/metric/SQLMetricsSuite.scala"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f8b3faba0e14c35e3465fe4e1f9731a230c497d5613b9ca9d30b31dadec7606"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Change \u0022\u003C=\u0022 to \u0022=\u0022 once we fix the race condition that missing the JobStarted event. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/metric/SQLMetricsSuite.scala"},"region":{"startLine":799}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca9a7754893968512db64a9b5efc35653283df86e034eab415f8f9fd24acd646"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: test file source V2 as well when its statistics is correctly computed. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/metric/SQLMetricsSuite.scala"},"region":{"startLine":843}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3bc799cb3720af422321de8ea405a599481e361b4d33f5525ec659e1e44bcdf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Change it to \u0022=\u0022 once we fix the race condition that missing the JobStarted event. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/metric/SQLMetricsTestUtils.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"421d10e0d2cb79fc0fe52f20a2c721e7ec17a55d75310ef32f54f5586b143201"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Remove this \u0022else\u0022 once we fix the race condition that missing the JobStarted event. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/metric/SQLMetricsTestUtils.scala"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"93885c3e1e85672d4959128102d3f2109f76f86e49fa3c3f3338a9430daf4c65"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-51381: Fix the schema pruning for nested columns"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/SchemaPruningSuite.scala"},"region":{"startLine":982}}}],"partialFingerprints":{"codehealthFindingId/v1":"f64dd2fdb2ff4a9b7ac50cd0fe0ea7b83f12d333d2de5dcd5a1c2d55aed355f6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-44185): INSERT OVERWRITE DIRECTORY shall be qualified with current working"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/TableLocationSuite.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ea44133f926949c0a6cfbd3aaf94e9678ee0743db4643bb34fff9fc89ab353f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add tests for type widening \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlInferSchemaSuite.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"d508fe450ab672612aa30849b02cb48a25e07258d343c55da68a10414d699680"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we don\u0027t support partial results \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala"},"region":{"startLine":1202}}}],"partialFingerprints":{"codehealthFindingId/v1":"584b7613e2c733c02341bebcf11dae3921e9b422d505cba7f8c17d29e74d8121"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable \u0022legacy\u0022 policy when the backward compatible parsing is implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala"},"region":{"startLine":2560}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1b3ab0cf51b1faca36f7eab5b357a9039a5fe0fd92a3bba494bf900b9c9aa57"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: Move runCompositeKeyStreamingAggregationQuery to this class \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTestBase.scala"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"4398a282d68f48a5357814dc5070d93236a26413a8ac09c68d40a9a0a6d1a013"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: Move run DropDuplicatesQueries to this class \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTestBase.scala"},"region":{"startLine":555}}}],"partialFingerprints":{"codehealthFindingId/v1":"3976de9e1ee40b557edfc20eb9f1fd19e14db04407a870152c4af380f1371098"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Complete this test case after upgrading to parquet-mr 1.8\u002B \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetAvroCompatibilitySuite.scala"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bce196c01ff3c0b94a9d7ed9776bb0f216237e0ece744180e89faa3b37c73d4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this needs a lot more testing but it\u0027s currently not easy to test with the parquet \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetEncodingSuite.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"5198f1929bfa389d1859ebbd1a4b9926c05011011235080ba3e313c63c19edca"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40059): Allow users to include columns named"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileMetadataStructRowIndexSuite.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e31436a34fb92906aa7bfacea03f58a30a32283bb7b488423dbee591b7d4a8c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable Parquet V2 write path after file source V2 writers are workable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala"},"region":{"startLine":3282}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd840e170328bcb1be2619a02d9214e8e9965ef9fa80799c1b606b9c28e87428"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable Parquet V2 write path after file source V2 writers are workable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetPartitionDiscoverySuite.scala"},"region":{"startLine":1468}}}],"partialFingerprints":{"codehealthFindingId/v1":"04c95bee1afaedac5a302461524fd335feac889e1bec25a29f6c3e0a25d60799"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable Parquet V2 write path after file source V2 writers are workable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala"},"region":{"startLine":1379}}}],"partialFingerprints":{"codehealthFindingId/v1":"d42443fce19e5460075478c3df2b0c5d309489437f53acb5bf765b16daca2c43"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable Parquet V2 write path after file source V2 writers are workable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaPruningSuite.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"52ae9a7d93aa8c5d6e80f622fbb03ff5e6ca8333776d11e20db42b6d2c80a7e5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: vectorized doesn\u0027t work here because it requires UnsafeRows \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"822658f50bfbfe867798e9203b3d38668a2207d82f702f832bf63cf0ba63e245"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(cashmand) re-enable once we have support. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/VariantInferShreddingSuite.scala"},"region":{"startLine":533}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd3505f33401a01cb67a358da282abf8b7e828a2c634a7ee91b06013fe6199e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-32325): Add benchmarks for filters with nested column attributes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonBenchmark.scala"},"region":{"startLine":644}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc2e9e30a17213fbc42e0a244da707221c4ac6108dd7008d97ed21a0cfaf8c1c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-37303): Uncomment the command below after REPLACE COLUMNS is fixed"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/AlterTableReplaceColumnsSuiteBase.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"d187bac3faa92f1157b189a1cc47b6c95d7dc462b27b8679342a7ac77ae194e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-33902): MOVE TO SUPER CLASS AFTER THE TARGET TICKET RESOLVED"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/CharVarcharDDLTestBase.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9f21095e0ed7ce6dbfc95126419eb0e30123444adecf8c340c1f0087645eb74"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-33902): MOVE TO SUPER CLASS AFTER THE TARGET TICKET RESOLVED"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/CharVarcharDDLTestBase.scala"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"e30975ddc1b4ac608efd565372c51bc0dfc3e531b6f979fb30341595513632cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-33903): MOVE TO SUPER CLASS AFTER THE TARGET TICKET RESOLVED"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/CharVarcharDDLTestBase.scala"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b59a591e7b5d8c9c4e844b29d15008f8aa62be18db9e34711d433ef89ae44b6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This test is copied from HiveDDLSuite, unify it later. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"a18d1febe118b0ee4e582c38500758d7ddc5fed86f075ee09a8cb5af8cfc5eec"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Right now, partition columns are always treated in a case-insensitive way. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala"},"region":{"startLine":1374}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c66bbaeef3df6ddebd84e4aed7cd9823141070a8e08dd72b3c9573c244d1cb4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50244): ADD JAR is inside \u0060sql()\u0060 thus isolated. This will break an existing Hive"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala"},"region":{"startLine":2292}}}],"partialFingerprints":{"codehealthFindingId/v1":"b997492c0f649bf05836d683950de55b0f8f7a0ee114cb7ce39dbc6859a6c739"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The v1 in-memory catalog should be case preserving as well. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/DropNamespaceSuiteBase.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"a583f695f5bffc0cac33780c61745f4a6211e10ea96c8ce87a0afa4b5720883d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The v1 in-memory catalog should be case preserving as well. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/ShowNamespacesSuiteBase.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7b1dbcbec336531859dacaf4fc5ba409d10f714e40917fb46ea2d6cc78e6032"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO will be SQLText \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/PlanResolutionSuite.scala"},"region":{"startLine":3016}}}],"partialFingerprints":{"codehealthFindingId/v1":"370e447fd3376d58b5642732961f5eb0a02db98dae17dede09a35eb35df31dc9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO will be SQLText \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/PlanResolutionSuite.scala"},"region":{"startLine":3067}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ba795e1a539bbb4af8eafd45558b787ef8530a70fc4e6134c64f13c9913af29"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO will be SQLText \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/PlanResolutionSuite.scala"},"region":{"startLine":3090}}}],"partialFingerprints":{"codehealthFindingId/v1":"56baaf7d0cdc632291774d4d866f9584ea33a2860f0b294f070f17c2bc2fd9f0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO will be SQLText \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/PlanResolutionSuite.scala"},"region":{"startLine":3133}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac4017d1c87f07a7400003ddc9b681723402cf06dd2ea54c093739398bd325d0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add tests for more commands. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/PlanResolutionSuite.scala"},"region":{"startLine":3806}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9be254017d26f9bf9268a6815f0f5598cb7025d1b641d875dceb89fc91323c2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move this test to the common trait as soon as it is migrated on checkError() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v2/AlterTableAddPartitionSuite.scala"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ab7843efcde04ceddc1c736f54f2600d5405b389d70c4cd1523b68f00d48377"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move this test to the common trait as soon as it is migrated on checkError() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v1/AlterTableAddPartitionSuite.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee63869b276a5ee5fa8cd6f5be4ca17172b9e9a5ed77e867e4a53701b16da493"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-34397): Support v2 \u0060MSCK REPAIR TABLE\u0060"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v2/MsckRepairTableSuite.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"477996393f93a4656636cadcef266355af0c3bd6bcee9f8e99fa357fcc9e9ee3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: After SPARK-37517, we can move the test case to base to test for v2/v1/hive"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v2/ShowCreateTableSuite.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"558c946733ee7993cd7467bade44a9b57eb27fef5e8daa91896795ead6250543"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-33393): Move this to \u0060DDLCommandTestUtils\u0060"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v1/CommandSuiteBase.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ef3413d02b14ed0ebb805bd4e457d8ad553b81a378e9b2aff86325d24804a51"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this is unexpected and temp view should also use COMPENSATION mode. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v1/DescribeTableSuite.scala"},"region":{"startLine":582}}}],"partialFingerprints":{"codehealthFindingId/v1":"f35c341e4c51a3f8a1a614fa95c911fb59defa533c3f321b4d4480fa2a9067d9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo After SPARK-37517 unify the testcase both v1 and v2"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/command/v1/ShowCreateTableSuite.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2407ee562904ebcd421bac19bdfd08e9bb7ca91738d4e19cf21894cf3114927"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Improve this test when we have better statistics \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"964ca350a22c6d19fc1b592fa604e459cf33f7bb8ec42bf43923b66b2552f5b9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(ekl) seems like the json parsing is actually the majority of the time, perhaps \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/WideSchemaBenchmark.scala"},"region":{"startLine":207}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bbcec4bac9db08925692970bc2aecfbd81f74c5b4d7d66aa6a5bc200b275bdb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: when schema level collations are supported, change this test to set the flag to false \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/errors/QueryCompilationErrorsSuite.scala"},"region":{"startLine":930}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fc95cc7bf094149eb69dfa6ae12fb2a7e56aadeb895755b141beeb269f53899"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-46951): Spark should not re-try tasks for this error."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionAnsiErrorsSuite.scala"},"region":{"startLine":472}}}],"partialFingerprints":{"codehealthFindingId/v1":"95bf74047ab37db05348ed99f85d49ff3bf141692ae25ff08510fed17b16b939"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-46951): Spark should not re-try tasks for this error."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionAnsiErrorsSuite.scala"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"edcc70d6e45432a446a6784a5a185dd172e47d613a87d321e43e9652758e8044"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-60811): the query should succeed once generated code can see the jar."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/CreateV2FunctionSuite.scala"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa60e9eeb8e2fa86c47b29a96c9474c6f7efe59d3793328eefbc64d46bfb1800"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move the v2 data source table handling from V2SessionCatalog to the analyzer \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2MetadataTableSuite.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fafdb5eb738d7c88ccc5a8198cadeb73f2ef08259a0991b9266fb2b2bf5d2c7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: ignored by SPARK-31707, restore the test after create table syntax unification"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2SQLSuite.scala"},"region":{"startLine":1199}}}],"partialFingerprints":{"codehealthFindingId/v1":"07f31fbc904641f72fa12b6098fa9e3f97b816cfc426584ef3f37b220897bc21"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"e994bfe07f8c47dd0b67707598698f60b51a75dd7dabd6003761141a06551077"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"e530be2d761ea276282756fe3c2a38b58b4b08d381392860c6b3106f1d5f24e1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":209}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f758d1af0388e2f08cf65cbf3f320a840e0bcc254f91950e8fc53d81c09511e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c4050f8450812039bbd3a2698687845c9939f9a02e27a8da058893deec7ddc7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"41257d40b8c332b8b640ef9edde6cefa29dc1cd55a5e8d1735774fbb2978793b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update the test to reflect optimization from AQE. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/WriteDistributionAndOrderingSuite.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae8b010da924b5ad3ccadc59a341ae28b81bef2f6083ba69783347af7c1b3829"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Try to make this a bit more random. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/CollationExpressionWalkerSuite.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"d250b6791adcede30a4540d59e4261390e8fd264722f0bee9cd225fafab43668"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Try to make this a bit more random. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/CollationExpressionWalkerSuite.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"6aac026708bf609eed33df86f9511ea30d3b63944095a5952b8987bc79c8f031"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix the following test for char data type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/DefaultCollationTestSuite.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4c087c52060b76eb2394cab024049724962f397056b506549808a569f22b580"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix the following test for char data type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/DefaultCollationTestSuite.scala"},"region":{"startLine":1009}}}],"partialFingerprints":{"codehealthFindingId/v1":"803c3cd69e7fc58ea178a7c68bfdfbe7dbf88ae6b6116a725d955f20cad4deff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix the following check for char data type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/DefaultCollationTestSuite.scala"},"region":{"startLine":855}}}],"partialFingerprints":{"codehealthFindingId/v1":"25b598b6016d3722c315b6f5316ce78ef48744766299a0a6f643345e201945b0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix the following check for char data type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/collation/DefaultCollationTestSuite.scala"},"region":{"startLine":873}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f609fae6aec32392dad440261dff06a5cd6602f51cb8aae9af118966531402b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-46616): disallow re-registration of statically registered data sources."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/DataSourceRegistration.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd142a3d1b346b5e14975ca08111e52e6035a7c541b7720f41042459b2fa9d24"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: After introducing stored procedures, we need to handle the case with multiple \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionContext.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b219fbdd298ee149e7850fba048c3b2e40da82ad0022353b9c3631499bc3f34"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Introduce a separate class for different frame types (Script, Stored Procedure, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionContext.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c9431c85ff98032303b2cfc9fc2d98e9e1e0dd7d79c131feef75e08a1797235"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Variable cleanup (once we add SQL script execution logic). \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":396}}}],"partialFingerprints":{"codehealthFindingId/v1":"8801b6bed1eb8efedc4888879a378f31a4983f9434aef7d5d0576d2a20835534"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Variable cleanup (once we add SQL script execution logic). \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc54883a8f3278821a7ecd6861237638b4423649ea397303c92f04902170713d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add interpreter tests as well. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":397}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c5f9dda65bf2529c5a717b8e1c6e0ccdb9262f8d09e615908ae234f3cd8e6a8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add interpreter tests as well. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e2bb255dfce3e0a61021c7371605a6f4c952569280a1bdefd16ab5b22a1a66e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Update logic and comments once stored procedures are introduced. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingLocalVariableManager.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"3976c4e2b1bf7015d985ef51e5ec38809546f1f915f722a67c11f1b735e38aea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: protect only the lookup side\u0027s path, so that the other readers of a CTE definition \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala"},"region":{"startLine":567}}}],"partialFingerprints":{"codehealthFindingId/v1":"47e5c71a69ce7016585fc83ee6963b1deaec191f1ad4d30664ad28cf9615cfbb"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack because of type erasure \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/Columnar.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"3651ae5892915e91ca4f1223075cdcdf3e037f9a70dde82752da1f98e1ea6a7c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-24528 Sort order is currently ignored if buckets are coalesced."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee1f110e3f2a6248765b7a15c2a4f3572465481215e24683da9765e44bc37d83"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Currently Spark does not support writing columns sorting in descending order \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala"},"region":{"startLine":504}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cf2359c268e0625303646269da679266bddf412e27ca23a50c6659a7f4c38af"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Instead of returning a default value here, find a way to return a meaningful size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b4ef45e8a4be646fa0a339da8ed5e36797495dd7b5a6215c90d94fb55c29935"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Instead of returning a default value here, find a way to return a meaningful size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e089955361566aeabd7c8f6e57ae823b03b457446fb4f0b1b645b7e2aec303b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Instead of returning a default value here, find a way to return a meaningful size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/pythonLogicalOperators.scala"},"region":{"startLine":455}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f9c92865e288f76563c5beab3d2268eb326616db2ae83d629b8d8f01cf0f4f6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move the planner an optimizer into here from SessionState. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/QueryExecution.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"25da18a212bbed82ca33f4331661aa9b711973d2ea5f2797ef03b97ba05948c5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We use next(), i.e. take the first plan returned by the planner, here for now, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/QueryExecution.scala"},"region":{"startLine":926}}}],"partialFingerprints":{"codehealthFindingId/v1":"64e530f501bcfaaa5a0919b9644bfe7968e24a4f4061830cb4d041687b289463"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-36234): Consider mapper location and shuffle block size when coalescing mappers"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ShuffledRowRDD.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"286e4433a1805cd1a3627a636519cadb37391ec3ea42de8ea4da0d17ae892349"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO this check is based on assumptions of callers\u0027 behavior but is sufficient for now. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ShuffledRowRDD.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfa234c4c0bc5acd329bcc785ceb63bb9476d0a0b8cf7443e5f850bbf499959e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO this check is based on assumptions of callers\u0027 behavior but is sufficient for now. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AQEShuffleReadExec.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f63b5c054539c7990a0946af9454dce3da23a16e153b7121c4a9f7e4950f355"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO order by partition size. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ShuffledRowRDD.scala"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"d270354f4de28878f9040c9ed0279eb01ce4cce729d2d424795f8d80284c5599"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move SchemaPruning into catalyst \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e2b7d2d853f2413e938e8190075651d0e7fbed160b306d513f3f8cccc4eff17"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move to \u0060DistributedPlan\u0060 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"c10350199592b7f500a7828585a9163c68f48708bef11ecdbe247f58af842c17"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: WRONG WIDTH! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b5fcca89d4ede8cd1715de2644883935d9e982bce2be13d3b5a5f0988d44989"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: refactor and reuse the code from RDD\u0027s take() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala"},"region":{"startLine":530}}}],"partialFingerprints":{"codehealthFindingId/v1":"a207851fdfd3bf13af9b0de29151cad785a15228f2c1ff6b317c04786f537b29"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We will need to prune bad plans when we improve plan space exploration \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlanner.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"26417dbf11210dd58d182c0f8623fee3d69628981a0339bfd9c3829fb4b91bf2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Decouple final output schema from expression evaluation so this copy can be \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlanner.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fcd8c73d18ebbc3e36cd64d3134767d9519290492af4b26b1dfdac3440d787b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: what does this message mean? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala"},"region":{"startLine":1297}}}],"partialFingerprints":{"codehealthFindingId/v1":"39c3c2cd387ef627233128aa1960d9cee0f959779dbd878aa4b06cd2e0904f1d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40443): support applyInPandasWithState in batch query"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala"},"region":{"startLine":1151}}}],"partialFingerprints":{"codehealthFindingId/v1":"5be5a7a489cbef127dc3dc36ba7941e9c21e6f5016ad3d62c92d0356d35c58a7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: revisit this. We can consider reordering predicates as well. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/basicPhysicalOperators.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b14050aa974d73d5d2ce2bd0bb6118650fea209cea8cd4b861f32f02f18de4a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"a04484d059e8c8805535c7b515e23d4f534a0e1793d336811e71cfed0f01d2fb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3c9b824d6f2212b8314c594ff836fc8e657c366c957d417361df2f5012b689f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/CartesianProductExec.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c4830799037e3f2bd0a9baea651d43812e8788ecd6cf1be4c32de2526cc1071"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"338057488fc83772591e210b21c4aaaa3fb3464882dd0d326aa82f491c78e763"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala"},"region":{"startLine":1149}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9f633573bd413b3d0152a9bce4cd78ce8b61f4602eae3cfcf11d8497e824fcf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: shall we have a new config to specify the max in-memory buffer size \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/UpdatingSessionsIterator.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"42a2138514468c40e3b8080c967ccd8d9a800d75cebda44c4996b9b47cd2a0e6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add support for multiple col families with HDFSBackedStateStoreProvider \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"94bfd5da2c623993b2d507088779989bb650fd132b26bfa40678ce33cb533f4a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The validation should be moved to a higher level so that it works for all state store \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"69c89d5b8a4501aeadbe11ed8d68fd6c54179a729d3d93919492b2f8f330daec"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845]: Currently, deleteSchemaFiles is a no-op since earliestBatchIdKept"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/OperatorStateMetadata.scala"},"region":{"startLine":438}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f11215157f61fcea6ce277a22c81dce989b79f0bab42afdb22735a337e56430"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845]: Currently, deleteSchemaFiles is a no-op since thresholdBatchId"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/OperatorStateMetadata.scala"},"region":{"startLine":451}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc3294d618045cd5693ef32715c56c5f03292987af566d51c8a684349eabb65"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-50845]: Return earliest schema file we need after implementing"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/OperatorStateMetadata.scala"},"region":{"startLine":501}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffb95839537f9766eea661cd04fb88650ea5e251f9e0281f6094ec811d5a7755"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add metrics update for deleteRange operations \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1602}}}],"partialFingerprints":{"codehealthFindingId/v1":"7344f9fc7320cbdcde0206fe6560cc6e0e9f51c946a79a4f30c72ba251b92c81"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-55491] Revisit this to support delete range if needed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateEncoder.scala"},"region":{"startLine":1892}}}],"partialFingerprints":{"codehealthFindingId/v1":"dab3d31b45dda4e60adf9595676f0d3dfa77bab46fd2ae75eac29f968c4636bd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: reuse the key buffer and value buffer across records. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"240a30e6a8f6bef253480ab1898c42ebdbb00c108c6232a4c5078323d4b39b10"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO When state store checkpoint format V2 is used, after state store checkpoint ID is \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/IncrementalExecution.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"b44e852e0bb0772fda4d68ba8dceccce3123999930d26a9889b66f5af493e63e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Find out how to dynamically set the SQLConf at this point to disable \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala"},"region":{"startLine":1547}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aacfb7c624d4f95be59561feb779335f1282fb9c907acee8b41199f307a8643"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Restore this from the checkpoint when possible. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/ProgressReporter.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"05d11a4ffb2b1dbd53170c8147e7bac16fe9265c4e4d49068297317c8646a79f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should do this check earlier when we have capability API. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamExecution.scala"},"region":{"startLine":808}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e5b3c42bc3388cb44a70f042cea266cc8146df5fb0067ac710b7abfe31a3f03"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should do this check earlier when we have capability API. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"61b5f62bcf21256a48da85b2894275699bc9f8ffab96c6ab2d07caeedcee20d3"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME: How we can prevent this to be called? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"4706ee343fdccda74f85cfb02f35145be14642e38862c4e7b08c150dca44527c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make this work for Stream-Stream joins, where we use multiple \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala"},"region":{"startLine":324}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7fab670ca27a7aaf0f58462923c5b06a7d45827d7f3024e65c8b318ec0a0645"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: validate places that are trying to encode the key and check if we can eliminate/ \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/StateTypesEncoderUtils.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e38e03a31b25bf22a1600dce5645c0ef61fa3e914f6e0bd978aebd83cef065b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-50180: check if we can return true only if actual timers are registered,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExecBase.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"dca79fd5703b4c258af1b6da7ccc18ee16e09076a2ca40bdc4abd865c24c735a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-55729] Once the new state manager is integrated to stream-stream join operator,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"2faed01a2536aa6e375e470464af3d65d298d8d6243784d18d5fd6ea2ee0f654"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-56536): This could be further optimized by also considering whether the state"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":266}}}],"partialFingerprints":{"codehealthFindingId/v1":"b45d2ce58cb735d484d3db43118cdd5fb41c8a17d8befb3214b9454141865ffb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-55732] StateStore.putList should allow iterator to be passed in, so that we"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/SymmetricHashJoinStateManager.scala"},"region":{"startLine":722}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc908d78df2e2c00016a69c9c57c22c50c83dd70fa7c23b66fd047068827ce13"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-27484): we should add the writing node before the plan is analyzed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousExecution.scala"},"region":{"startLine":119}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dedd6ac08fbdd83deb1eb28c6a36ab024af0ebb6ff2f2ac70fff09471b88502"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-27484): we should add the writing node before the plan is analyzed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataStreamWriter.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"83adaeaddb0da55e86be0da936dd6ea5ed6a401fe7a029b1402c00301281d79f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The obvious generalization of this logic to multiple stages won\u0027t work. It\u0027s \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousQueuedDataReader.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"0978fce8ce8ef31c09f17874b0058362a278af15c67741f77d7bdf453e226b7e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-52009): Make the checksum algo configurable"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/ChecksumCheckpointFileManager.scala"},"region":{"startLine":467}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a575042a5fc88d32ac9f5738e820c07bd8430a3834fb30aa015ecea93800f63"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-52009): make the checksum algo configurable"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/ChecksumCheckpointFileManager.scala"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ceb045a8aa335be2ec74b854107ecc7394af3fa9ae68794090af301323dd3d9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The proper way to handle this is to make the number of partitions in the state \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/OffsetSeq.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d7e5942b6411604c6cee86dc54579ea3e70a6f5e876e35f501d0cfbec372262"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(davies): we could improve this by try to cast the object to expected type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvaluatePython.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"0bac99c46758eb4e57ad42a14b5516c5ab0c7cc892fa732fec5683af7810db0c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add support for transpilation with Spark Connect and remove the default value. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"b692924b2a252cc637f87bcb7146538970901c00f63ac59279146dd3ad5667ba"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40444): Add the support of initial state."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/FlatMapGroupsInPandasWithStateExec.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"1afdb601e8573f43108a60e673dec0d603245e2bb700ada2c213ab6f8ef4a210"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-49603) set the metrics in the lazily initialized iterator"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkExec.scala"},"region":{"startLine":328}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ddbba154ea474da82fcc6779d18d82da9847427b56951d1cdeb42120052ad33"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Check whether we can safely remove fetchWithArrow without breaking backward \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":528}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c6105370c8b4af53e0e27228d394b47ab042473487ee096457886913c30ca5d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Check whether we can safely remove fetchWithArrow without breaking backward \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":564}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0be6bbe904a51c7da26117e4aa99430e4a7188a048bf2e860cf34735fc687ee"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Also check whether fetchWithArrow has a clear benefit to be retained (in terms \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":530}}}],"partialFingerprints":{"codehealthFindingId/v1":"d85ca75d28976782bcbc84a55c2b95a9f621ef77e5adf0a340c3fa9917194a91"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Also check whether fetchWithArrow has a clear benefit to be retained (in terms \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":566}}}],"partialFingerprints":{"codehealthFindingId/v1":"da2ae633dca8d7308f39df5f8688ae80cef26422c1e2382614b87093ac3160ad"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support BooleanType, DateType and TimestampType \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala"},"region":{"startLine":881}}}],"partialFingerprints":{"codehealthFindingId/v1":"63e73de606efdbcfc8c76160f4ab435d1e893120ae76d2156b95d6c562b8738e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move these into BytesToBytesMap \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"c56db6db636c6876a15bc757137d3980e674c6034cf944e67612da836b0d7169"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(josh): This needs to be revisited before we merge this patch; making this change now \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6e218e4c6172d14d9315294fc52702f25dd8e6cdca8eb728da755f88fbc8314"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(josh): We won\u0027t need this dummy memory manager after future refactorings; revisit \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd9d21a61bf3007a078b00ab7f1a020c53ea9e70b5aa45608feb2e8c534d1c00"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-59364): Make this node language-agnostic. Its dependency on the"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/ExecuteExternalUDFExec.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bd6dd622197a03a8b4bee5283742b98bf8efa0abd381789594820b6d4cdc521"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: Implement unified mapInArrow support."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/ExternalUDFPlanner.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"d510d99451451251b4dae6ae6954beb8daf55238dbc69c4172bcfcee6a0527ff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-55278): Stream rows to and from the worker through session.process()."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/MapPartitionsExternalUDFExec.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ccc646b3106d75fa1053894afcc2de7c4ce44c5b7a62e774b6a41f48763f11e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-59745): Preserve named argument metadata in unified Python UDF execution."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PlanExternalUDFs.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8692cfff2c82f46c33f340f9faffca6c01cc990f25f023f02a36cf577d759f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-59364): Share this context mapping with PythonWorkerUtils when Init message"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PythonInitAdapter.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"728f2a01fbc4ec1880766b552d764a81c912ab7a0b09a28d3cea451e9c541dcf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: Enable this on the python code"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PythonUDFWorkerSpecification.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d946f10207263891bf02448f19700a6c39c3dab531613e3f8ec462cb2b93305"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO [SPARK-55278]: Add additional, python specific env vars"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PythonUDFWorkerSpecification.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"eec0873c53b94e2f79817ef8e2edc2e9e6df68f2ea7d0f51c96d569af069a7b9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Handle BroadcastPartitioning. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala"},"region":{"startLine":425}}}],"partialFingerprints":{"codehealthFindingId/v1":"3350202c2503c58ef0df933814d18e1dc49452b105e2f96438f6e18907f631ff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Throw when too much is given. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba991eb76158661da54a6c0ef631ce5f2876b30684964495fc71bb49299c8aaa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should have a better separation of row based and batch based scan, so that we \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"519374e50914216d929c36c3474bf076d4bde969d69d1f15fd1020a753bd1c89"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We should tighten up visibility of the classes here once we clean up Hive coupling. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5d00abb25dd39d3a5e7c1c796b477d2cf5b43a15e273b071ba68b9ce3ab7357"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Selective case sensitivity. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ef3ea904684c08b16feb8eaafab608e6bafefa37f38da8a9a223f0612070f88"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SHREDDING): non-null default value is not yet supported. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PushVariantIntoScan.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b4a00bc0b407263c0ec5ddb0faab9ecaa851f005aaf9e96813af490bb5574e9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Check that options from the resolved relation match the relation that we are \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"da7bbf39376af0b8052e9716f617f35997eb68f3d30fc9783a65b8f0d79499e7"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hacky, is there a better way? see if the type is known as a custom \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f5eedc066974a73bc40b01ac0bde0b2873d7e126f136ad6c7583a0b76db320e"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack: in the uncompressed case (see more below), we must know how much the \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"39758c5897e67999d78647e68819f61f84df166bdc9d49a1607f9d4a1771b9cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: unify the equal/hashCode implementation for all data source v2 query plans. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/BatchScanExec.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c4cd215f0bd4a20332098fcd17e78a1dc812338bf370fdd1b97c28e814a0188"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: unify the equal/hashCode implementation for all data source v2 query plans. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ContinuousScanExec.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"98365b9475feb642d57ae2ba830293909752ccf6bd0d1dc424302db868c2a0a1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: unify the equal/hashCode implementation for all data source v2 query plans. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/MicroBatchScanExec.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"e47b5a25d9eda5cc60e2a5ed237b741d7e2bc2c44ab155a928d5de77afb7f69d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should have 2 RDDs: an RDD[InternalRow] for row-based scan, an \u0060RDD[ColumnarBatch]\u0060 for \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceRDD.scala"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6a384b36bf82e9cd48cfd38991b1fc3619e7995a119224654f67ba79d797c11"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-25083 remove the type erasure hack in data source scan"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceRDD.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"60276acd54094a1ba66e4026ce76570606d18bea9250b7bf11fe0f5903f1afbe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Non-catalog paths for DSV2 are currently not well defined. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Utils.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6366dd600875b6311604551e1b45c66b75759b60e61aecd9a83d57997370d00"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-28396): Currently file source v2 can\u0027t work with tables."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Utils.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"35a1327a7725d2284aed5e1f358567052833f4a201ed9b102ced8385ece7dcf4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: To reduce code diff of SPARK-29665, we create stub implementations for file source v2, so"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileDataSourceV2.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"94229286ca013d0ca552eb70076598ec55d188157b04830c3e2b6613f8643b8d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: implement a light-weight partition inference which only looks at the path of one leaf \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileDataSourceV2.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"faa4f47cf09f18664b5b8d5442260f91f0a4709a57d95671d09d2d859b1cd694"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-36340] Unify check schema filed of DataSource V2 Insert."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWrite.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"d38d21ff9e087f9e012283cd8f0491d49060ca42b5ac236a735283b505dddbc9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: after partitioning is supported in V2: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWrite.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"39f00ad0d164d2b8aa64544df8eb88335a523e08c02e9391d952254eb76bef6b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO We need a new listTable overload that takes a pattern string. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablesExtendedExec.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"21ac9357b349067ba41ac5f6492bde3509954cd5d04bff957fbafa5ad4a571e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u0022Created Time\u0022, \u0022Last Access\u0022, \u0022Partition Statistics\u0022 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablesExtendedExec.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"203754d384b8f045d614c8ce8f66dfb05a625bbad71bbfa9236d7b6dddfad5f7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: check STREAMING_WRITE capability. It\u0027s not doable now because we don\u0027t have a \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/TableCapabilityCheck.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c3e06d5230663154e551f82d6f956e747be335df666d68619dca68348b36666"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO list. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"924affdb65d8a6e41c9255ce1ddce099fdc86b2a67f6e8d273720e1a3366efdd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: for cascade joins, already joined relations will still have the name of the \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc7be98bf68c9d3469f43649f54accb9574a5a51d2666c5ab7483004f5472a96"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO after we persistent the StateStoreCheckpointID to the commit log, we can get it from \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StreamStreamJoinStatePartitionReader.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d360d3bdd1a0e77074520d6d9db2e299acc3aeb4a21b0003838c3984ecee458"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: currently we check that all the options are same (besides dbtable and query options). \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCScanBuilder.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aa2740f3d31678e14a04647367a59921b2ff9127df51de8e9e2e394ebb9d22e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-32593): JDBC support nested column and nested column pruning."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCScanBuilder.scala"},"region":{"startLine":361}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f9e317fe2a916f18b7005b1c00930a4eb891afad5fa6753fa5d14d21064a104"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-32595): do truncate and append atomically."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/jdbc/JDBCWriteBuilder.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ac261e3ec5fbd391c301165a6acaa85bbb1499511e5f85e8726444e0ad5a063"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: if you move this into the closure it reverts to the default values. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc5c3427e12e0f7a2f2f7a231385b99758cd800a91de66dc1229650c1ccfca30"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-39393): Remove extra condition when parquet added filter predicate support for"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"51231e0e27a1b9f32bccf2652a928c808e10abc672d030667f5b751c9a034ca5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SHREDDING): clip \u0060parquetType\u0060 to retain the necessary columns. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadSupport.scala"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb4e478faee6c092102be4e583023fbefc7ea0e79e3eb010a45abf924b3343af"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-26174): disallow it with a config."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala"},"region":{"startLine":912}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a8c6aa7c2a29ab3b6a23810ab3110a06f5fc4a0897398265149981e5c87c038"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: If maps are ever supported in the shredded schema, we should add a test in \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetWriteSupport.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e91ae02a6167199798d482327a147b05d6043b7f3a5ac634c5b883f7648cd73"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: to reuse the existing partition parameters for those partition specific options \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCOptions.scala"},"region":{"startLine":177}}}],"partialFingerprints":{"codehealthFindingId/v1":"78e329627544c52b779ea9b3e373549983ca96bb785902197c4a0cb118017fed"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(davies): use getBytes for better performance, if the encoding is UTF-8"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JDBCValueGetter.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1faea81022be7074163986c78024f597058829e507ef7113a41cf1e441816ea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Generalize statistics collection. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb7295ba8b1c88dfd4939cd04a7ed82853530f15c421f74ca170c0386d64821a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Why fs.getContentSummary returns wrong size on Jenkins? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"c921a61f71768f027389a8f1bf4ee393fc0aa634cb51dc29d538f2815f9aaa53"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50698): use parsed expression instead of expression string."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/CreateSQLFunctionCommand.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"8843c0ee1478c0eaf732333952dbb3f2680d37f929d1f2da6f95104bc4da8729"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support change column name/dataType/metadata/position. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ef750ff363a5272ce63cfb92f5c3852b57dfe1b4587cae70bfed2c6b69b1314"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Validate the value \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala"},"region":{"startLine":866}}}],"partialFingerprints":{"codehealthFindingId/v1":"37f21fc29bb9aa4b9a86bd6cf6bdab6fdf590466f2694f83eddbf8a48a3e2a47"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move the rest of the table commands from ddl.scala to this file \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a80795b971fcf497a38ff6669fcf507d9561202c0a281080f578dd2bb474617"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-28692] unify this after we unify the"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1240}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fa741587bb2dedeeba8de8e166ed2ceab60573d99a75c038a03ab1bd5390074"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: some Hive fileformat \u002B row serde might be mapped to Spark data source, e.g. CSV. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1288}}}],"partialFingerprints":{"codehealthFindingId/v1":"018759fd7f127205115c423eb91fd8e7eaeef7f160d387a877e019c0625f4812"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: should we keep Hive serde properties? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":1304}}}],"partialFingerprints":{"codehealthFindingId/v1":"2990bf541a5b69743ced1590f2905fe6a1260fdc80c118c3c30dc3ee9cf95a60"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move v2 commands to here which are not data source v2 related. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/V2CommandStrategy.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa05046056b5b685f624bffa5fb5fc62a8218a9bea0e47525117599a21b8c8cc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this is not right for DecimalType with precision \u003E 18 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnStats.scala"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2b3fe9ee7278a449438f4b7d44833cf805b971d2f0c1e6a7439682158614b61"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider large decimal and interval type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/RowBasedHashMapGenerator.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"309119f5b7add386f66a2c24e8101dafe2f6a533e6b508e9a9a6eecef7d26bb4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider large decimal and interval type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateUnsafeProjection.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf53f7bdbc24736cd17839fb7920570c59e233c2599c7f3e29ba7c09499bd221"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: merge these 2 implementations once we refactor the \u0060AggregateFunction\u0060 interface. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TypedAggregateExpression.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"394bc5820e4a06066213a220e098078160cbe26a46faf0741b9321264b0645fc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we can return the original query plan before broadcast. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AQEPropagateEmptyRelation.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"736a022cacd69aeec2fea04900b5fd19e3b319825e545ac5809561d6593136c1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: match more plan nodes here. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/CoalesceShufflePartitions.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"391bf89c6f7b853203a5c3b25ff7f4a64d0691db28d1e7b62710a77c03a474a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we can potentially include only [[QueryStageExec]] in this class if we make the aggregation \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStage.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"43b97be63dd2fc18f19dac7fa0c8a43d9a9433b143bb3a4ef9ea8709e80bd402"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO this is not accurate when there is other physical nodes above QueryStageExec. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStage.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"90b408c058ffe0b50f4e53a2ded825c7e74690520e9e712fdb6031530d2f8f1e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this method assumes all shuffle blocks are the same data size. We should calculate the \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeShuffleWithLocalRead.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1c5ef0ff33873c3569a2f510e52c739885ccad29da2f414b98990f185dd9a4a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The SHOW FUNCTIONS should tell us the function type (built-in, temp, persistent) and \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d64a21fd25f709d252ac3df03a75a7993eeca8382f7fef337debd5c34535f42"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-28396): File source v2 write path is currently broken."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriter.scala"},"region":{"startLine":643}}}],"partialFingerprints":{"codehealthFindingId/v1":"5353a376e6d27cbb59e50d731e4951a6aecef22b122ac24d64baab935548da38"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-22947): Fix the DataFrame API."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":836}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bb072cffd9f55376ec288bcb87a01e355ca3bcaaa553cc26b867ca9daf69f7c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-22947): Fix the DataFrame API."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":854}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaaccde30a1e3d215a3a20029d5848fcfb134597214e567f9ee29442c07b5784"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO handle the metadata? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":1404}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7f9aee292093919d915d82bbcff6982013d0c70580c4edd0ad90ffb4ec69739"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: streaming could be adapted to use this interface \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala"},"region":{"startLine":1787}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0bb8b85335a2a6f6b7d1c4fe3ebd777297e1f19303111efda9d3c208de3946d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move this logic into SparkSession \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SQLContext.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"95e95a7473f4f0c11bf71a7d0e91fea79a0fabacfd403f7b2bc926031c48daf1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use MutableProjection when rowRDD is another DataFrame and the applied \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":332}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ea97c9cc1d6a704f8e3ace294554fe9153ba7e0a8601127ec5bb4fb10acb245"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use MutableProjection when rowRDD is another DataFrame and the applied \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"c73aed71ce48b5d3a4427e15ee1f1f49c9daed38d3c55a2c8db49e4f4eeca1e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50244): We now isolate artifacts added by the \u0060ADD JAR\u0060 command. This will"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":1001}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bc5b91d045beed7b2753df55f0e347c3e6cad054770251006374738bd89ebd0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-27483): we should move this fallback logic to an analyzer rule."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDataSource.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a5b05659e395a2ec6b743e3c2ce7e96038ab07103177401e931c1ad2b588a71"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we can avoid boxing if future version of avro provide primitive accessors. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"d15bbf7e2bb9d8cccf2c3fda73b5c1243dde6df41a6bab25f596978a559eb34b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move the following method in Decimal object on creating Decimal from BigDecimal? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"db74a77498ab64f5dbeefbcff22da46b2343e4836f4ff23db101552d37b9fce4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Removes this check once \u0060FileFormat\u0060 gets a general file filtering interface method. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"d803942e3810d60ad72954b19a1f79008668c5e339c1c4e23fca088b4390f2e7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: introduce a user defined type for serialized R data. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/api/r/SQLUtils.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"7217a7f73167311139694a212baeffa1ecb507251cb005817b7243c10241367b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It\u0027s possible to change UnsafeInMemorySorter to have multiple entries with same key, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/UnsafeKVExternalSorter.java"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"b06a31b13567027bfd86bd30d479427e0dac1bc9e5577251f3f40b7823495568"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: best perf? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java"},"region":{"startLine":494}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1ca92a1e51094660c5bd13a2575de3800ab96f1918af3a964493b03630133e0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider pushing this in ColumnVector by adding a readBytes with a stride. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java"},"region":{"startLine":451}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b8fcaf12c2c34f665aea747a42fc89b361df76dd561dc8f6fdd06da05849ef4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable below by SPARK-49487"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/test/scala/org/apache/spark/sql/connect/ProtoToParsedPlanTestSuite.scala"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc4eefbe6b5dbf3595f3f86c38fa90585b4855237ad76fd03eab9ca9edc2a839"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Once we have test error classes with breaking change info, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/test/scala/org/apache/spark/sql/connect/service/FetchErrorDetailsHandlerSuite.scala"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cde8cc2ae2d52d075727ee868591bef9456872f05a24991679b09a56fa35e56"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add support for specifiedSchema \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/test/scala/org/apache/spark/sql/connect/pipelines/TestPipelineDefinition.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ae384ef67420efd695798232e1a27e4d1e9a04a085aa78db23c526320a59ca3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make this configurable \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteEventsManager.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"075f4e8c79fbf939861236b36c3a08fd9e4fa28a97e13bcbf3e3519d80e02229"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO this might be too complex for no good reason. It might \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6e3cb2c45ad815b6fd99a21193a294a04d2ba1eea3e94a03c715cefbec017d3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Better handling (e.g. retries) on exceptions like EOFException to avoid \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingForeachBatchHelper.scala"},"region":{"startLine":324}}}],"partialFingerprints":{"codehealthFindingId/v1":"98740934f462d359dd92955964045ed4802f4b87cb65eff3349e765502f54d6f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Reuse the same method in StreamingForeachBatchHelper to avoid duplication. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/StreamingQueryListenerHelper.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"084b1f88c563322c87765445363d2db5d5b8f274f6fb68e7da2f6ff699044484"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-57092): apply_as_truncates is declared on AutoCdcFlowDetails but is not yet"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala"},"region":{"startLine":449}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf7114b5e6a6398fc463011a02d3459a94b33fd55e78bd3cce993544685882f6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we need to have a proper way of stabilizing the input data. The current approach does \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":862}}}],"partialFingerprints":{"codehealthFindingId/v1":"09e9049307be5fa60d09d0ba20077852b38622ec24fa78e5c8dd45d12392271f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: implements all methods mentioned in the scaladoc of [[SparkSession]] \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SparkSession.scala"},"region":{"startLine":824}}}],"partialFingerprints":{"codehealthFindingId/v1":"fed5a0d4cfa30a994604de54cb8b4d3c248e8192c737bc3882895b475d64b0cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO support Any and UnboundRow. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/UdfToProtoUtils.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbdbceb0aeeb9bad63b09391588fb72b0058d4efe900957ba36c8d78b648d2ed"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50846): Consolidate Aggregator handling with and without arguments."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a5677f946cc0b45dffd00ef116603a9b7e451636733f00cc8d8424589b3cc53"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50846): Consolidate Aggregator handling with and without arguments."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfd5d36d116cfa9aa878db0fd3279b2b71096db8087f657a083e58e9e690d76c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we should probably \u0027just\u0027 detect this particular scenario \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"52cf4868f4770b83324d9c53997c8faec79cbac9ab2639c47e642964bc1d5347"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-42658): Handle responses containing CRC failures."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ArtifactManager.scala"},"region":{"startLine":430}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e25f76e852c2b4218610d9b95e9b61898331a2905d270db611c456273d75461"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO throw better errors on class cast exceptions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowSerializer.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c1486b6a2e0d59a3b1f03bbf9e2241493bd09f9af987fd09c734e239d0fecdc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO API is not consistent. Now we have two different ways of working with schemas! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala"},"region":{"startLine":298}}}],"partialFingerprints":{"codehealthFindingId/v1":"949b46cd3352edf0ae5ad0e4fa9417712be5e45ea1f72c613191022bcd78abaa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-45030): Re-enable this test when all Maven test scenarios succeed and there"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala"},"region":{"startLine":3777}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee28482c418d2d6b50bb43c953e944565fec3ea6b8b640b5bbc94a56918ca313"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-45030): Re-enable this test when all Maven test scenarios succeed and there"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala"},"region":{"startLine":3783}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c54183d6a2fc475015be77d5d997ce97a89acb03f71e0977da6cd51564ffcad"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO test large result when we can create table or view \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/ClientE2ETestSuite.scala"},"region":{"startLine":594}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1f26b7200f7e5f9ca88736599b49beef3d072245fe32c3522d32912830c4ef8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-47749): Dataframe.collect should accept duplicated column names"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/ClientE2ETestSuite.scala"},"region":{"startLine":1019}}}],"partialFingerprints":{"codehealthFindingId/v1":"628a964115026ce80dd43fb9eaf0cf68e2ebc908c96de81647982e199a584248"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this long again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f6f726129f8b03eff61b3395bb8fdf3b06d54db8abb04f431c7a771419636cc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this long again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"60acd6576deef6336762e02f68fa4486dafc2fc4e0c4a96fada5d44ee1347f19"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce4dfdaf1f4e7e803f40dbb155e40e64de674726690baac81edbe3311cb4f2e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"6890fb47e3bbcd5465bffeb116a3d4fc7c885d63dce19274f7cbffddcc111e6b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":324}}}],"partialFingerprints":{"codehealthFindingId/v1":"a37f1b3b7ca95547f935398b9919a4b18ccc11f3daba232cf5d3fe63bee6810b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":335}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f2f530b291b1a93488ab81bfc7f3a735afe175cf481509ae83341fd07cf717b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"43037f8ee7298015d3a0dbb9a937340732bed2e7d38e3218c05f76c30f81b4d5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":368}}}],"partialFingerprints":{"codehealthFindingId/v1":"54e2128f3cca871ae602eaab1adfd6aad4ba2d0f9bb3bdbf81b4acca181f99cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":386}}}],"partialFingerprints":{"codehealthFindingId/v1":"885744224e5321bf90f9a423fdb6161bd437aacf963aaeced75f2a0f82b1db55"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-44449 make this int again when upcasting is in."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"74a84bb8608ed9cc39bd79a0bb6572dad907828cf781d93292f5d6ff8523b41b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-50837): \u0022ds.schema\u0022 is wrong: the column is named as \u0022iv.key\u0022."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":508}}}],"partialFingerprints":{"codehealthFindingId/v1":"5794eacb841d25885dfe5981e387069d19f18a01b632ed57af9fe575bd878dda"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO re-enable this after we hooked SqlApiConf into the session confs. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/UserDefinedFunctionE2ETestSuite.scala"},"region":{"startLine":326}}}],"partialFingerprints":{"codehealthFindingId/v1":"20884fa9e102d7d409af30189f1e61605f7a29bab0cf01d414417dff7d08c698"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-49096):"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/CheckConnectJvmClientCompatibility.scala"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"861f1a34a968cd50697e4866fb3c0cfd1ddfd0425b5598c64ac344a907e1a8aa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO follow-up with more null tests here: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/arrow/ArrowEncoderSuite.scala"},"region":{"startLine":828}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b148172cea1920c0b7d0878345d081cb4002f2a7aa50bb235097a7ee2a624cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO fix actual Null fields, e.g.: nullable: Null \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/arrow/ArrowEncoderSuite.scala"},"region":{"startLine":1363}}}],"partialFingerprints":{"codehealthFindingId/v1":"524edc99912537a8c881292972a55fcc6fbdce497aa1df72701b69df88ce2170"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO verify the remaining attributes \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaDataSuite.scala"},"region":{"startLine":735}}}],"partialFingerprints":{"codehealthFindingId/v1":"1afff0f75bfd3b89e9423517aa9083a314d2a9b2abec29048aa3f11e88a12dbd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: do empty structs make sense? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/RandomDataGenerator.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"542994e018616f807a420accfd416adc70c5206c5062e6278dafbca25357758f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove this once we find out how to handle decimal properly in property check \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/types/DataTypeTestUtils.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"9081237ea942814f19fed26b36b14d1a1bca0e16cd9b0a2d61ba6d6acaf9eb1b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Currently not transactional. Should be revised when Atomic CTAS/RTAS is implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/connector/catalog/txns.scala"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ac53aace662375fa5fcedcb60e9c6a708891cfb0c03fabd3f2d65929097ffd9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Currently not transactional. Should be revised when Atomic CTAS/RTAS is implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/connector/catalog/txns.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"dae17b53854b72729e3a4c6b1bc8d2e37768ee1f16f9c4f2d8b5f2e43808ed90"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this can be relaxed. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/DistributionSuite.scala"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"288416fa45e82979f66b5963730358cbd77d88a8eb3fb45bdeb2a7fd79e67d07"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We can have an optimization to first sort the dataset \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/DistributionSuite.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"294d1209cb0157361958f89c0b8020ad5dc0d1b0b81bba6760770bf4733a6889"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO add the JIRA-ticket number. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"4af54496cc52ca4b87b7e86ba5525dfa9a677421148ffa2670b2ba1dde1be56e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO figure out if we shouldn\u0027t change the ParseUtils.unescapeSQLString method? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala"},"region":{"startLine":1011}}}],"partialFingerprints":{"codehealthFindingId/v1":"08f01981dfb787c6ae39c2c7943e49920f00ab04769373ff0873e25df44403a2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: to be removed once the parser rule for top level compound is fixed to support labels! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/SqlScriptingParserSuite.scala"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"72135780c60d7e7f0b409bf3f7889c015cb991226be40796a02f4bbfa9d4017e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: should collapse as the non-cheap accesses are distinct: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/CollapseProjectSuite.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"c68d1eb8750f6d75396aeb1fb3b7e36253564512cb6b2f7868e36f41f64f0bc2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // Todo: in Analyzer, to enable it, we need to convert the expression in conditions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala"},"region":{"startLine":2147}}}],"partialFingerprints":{"codehealthFindingId/v1":"724acf3662731cdb3da192443f538db94c8a28122d2c5f259c0bcabc741dfef0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-32687): find a way to make optimization result of \u0060CostBasedJoinReorder\u0060"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/joinReorder/StarJoinCostBasedReorderSuite.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9e3b6a62016bc82d85da4f39219b1ea79b5a0ee14f07af4745880f3c1a8277c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO tests for decimals \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSQLBuilderSuite.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"a81d8231f7b1d03c8d73d01f988fb1a49218b2cd2015f6de379934cc59269ac0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO cache the generated data \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/LiteralGenerator.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"323fb3b9dabf86d3d03099c79d92fc270041fc58168e4431d7b648fbafb4b2c5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support accessing columns from outer outer query. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"44b3215ad02cf383ae8268de05922aff627ee1617ea905d7747dbb624d2a3afa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: once all configs are migrated to textproto, this can be replaced by \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b1bc2d6c76896534e4832aa0524edeca97341cb129226e16799a19886b98f2b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: design an official API for streaming output mode UPDATE which can do the upsert \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/connector/SupportsStreamingUpdateAsAppend.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd91c2b17b1329ff7e28b11d12f10e3098959fd460a6d93009e2bf8fe8ebee27"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Override validConstraints to return ExpressionSet(pushedFilters) so that pushed \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cb9db401fcfd837ef0fc979064534446f12a08b4f6d4b8d11cb8fd31640aa0d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: for off-heap UTF8String, how to pass in to arrow without copy? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala"},"region":{"startLine":344}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f83e8b5a6bb667d669557ac23815f538100d3fc77241e6fdb75a95d03684799"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: for off-heap UTF8String, how to pass in to arrow without copy? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowWriter.scala"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d2c6b7f0dd8bbc9272cf3c18fa950a5d1581cd02a7336818e66905105c16aab"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: all commands should look up table from the current catalog. The \u0060SessionCatalog\u0060 doesn\u0027t \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogManager.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"4884c4b1c3319f14f36bb5d3a8c3035673eca529d2ffd7719957a5aba2b34ca0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: create a real SYSTEM catalog to host \u0060TempVariableManager\u0060 under the SESSION namespace. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/CatalogManager.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"78fe2bcf95884fa51e88fe11531c0f38efb6f0e1e698c0493a540d1b9f07300e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (hvanhovell) this is can be improved. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/DeserializerBuildHelper.scala"},"region":{"startLine":388}}}],"partialFingerprints":{"codehealthFindingId/v1":"6712c3c0be81e7af7717013b779197426657fdb3aff2518583e15469fbd94722"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO replace this with \u0060createSerializerForPrimitiveArray\u0060 as \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SerializerBuildHelper.scala"},"region":{"startLine":518}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b4aa3b69c56e367ac2006049c7438d9102ed9cc413a4fedb51be2f08c88bca6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We don\u0027t support array value tags in maps yet. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":486}}}],"partialFingerprints":{"codehealthFindingId/v1":"6195d4bc68131f162e24d4432daac8d0d3088a2e79338a42022693e2d7d9c094"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This method might have to be removed. Some logics duplicate \u0060convertObject()\u0060 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":571}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b2b2a9579a2fb583f69da799b6845dcdf32417e83aac486e6cff1b18dc303a1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we don\u0027t support partial results now \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":693}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b76de3323ebd9e1245cfad382168866554f7a578234e43fb7030df9b4c2cdc1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: find a more efficient way to convert ArrayBuffer to GenericArrayData \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":707}}}],"partialFingerprints":{"codehealthFindingId/v1":"24c7a1409fba16ee8cef37919dbd10b0c4edabbf859135ace7333ccc6277cf14"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This function unnecessarily does type dispatch. Should merge it with \u0060castTo\u0060. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":790}}}],"partialFingerprints":{"codehealthFindingId/v1":"b39c4d5323a1acf8fe0eacf63076cce136eedbdd12edc4a196e4742fc6cc611f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Optimise this logic. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":870}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a734291e7f839f3aff502fbf2f8e97fc4a3a8a8f2ba0c9ad880aa09285ec5d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: specialize it \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ArrayBasedMapBuilder.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"325b62f80ed1f9c1347fe8279f0e216f7d738e326aa4551be496b4fe2542a4a7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This is boxing.  We should specialize. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"df41c871b334613a8838294daedf2c6f2edba80836b26d9d3dd0a74d340c640f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(tjhunter) more tuning could be done one the constants here, but for now \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/QuantileSummaries.scala"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"d955de76a9b09627922b2ddf1d223204e551529757b98f43a58da3d5f9650617"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO supports other expressions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":382}}}],"partialFingerprints":{"codehealthFindingId/v1":"65bf212cce4ae24c4dde1dd6b995af62634400555cf76d690920771b86cabd8e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO supports other expressions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/util/V2ExpressionSQLBuilder.java"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"12bebb9de3495b3f1c096a20ecfd226c0769ca18451b532caa3b0897b65ca27e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO supports other aggregate functions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala"},"region":{"startLine":465}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1d7fe14dbc37b79b5ad5bcd079567d5b1ed686b516b6e4be43ce41731189157"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-45891): Support comparison for the Variant type."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/PhysicalDataType.scala"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f7473bfaa5de6874dc9f7536c76411ff5f07fd3b1482687a28f1203476816aa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: currently if the class name ends with \u0022$\u0022, we think it\u0027s a scala object, there is \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1351}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfc1dd8b7e56bdd7bf29e91db3794bac10533740f722e7fa04dc9adc082c0bea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: pack the UnsafeRows into single bytes array. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/broadcastMode.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"06784ff29104d3ae8d415883f8a1819187dea72777ad0cb704f66ff6e42421bf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-53428): Support Direct Passthrough Partitioning in the Streaming Joins"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala"},"region":{"startLine":1828}}}],"partialFingerprints":{"codehealthFindingId/v1":"21c7534baa3dcd391cb6657126b9bbcac014a3879ad8ea80ce211ebca3057377"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Expand distinctKeys for redundant aliases on the same expression \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/DistinctKeyVisitor.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e6ef2b8cf3a78ecac314ec1dc6a23c5201a6272afe2cbff44c6439f7c251bcc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Disallow updating the metadata once we remove the compatibility flag. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/EventTimeWatermark.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"6819d440427c672fe71d6b155530856638faa9df3b53061c169fbcef6a43d99f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-59049): Support UDF chaining before allowing nested UDFs in one node."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/logicalExternalUDFOperators.scala"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"287b31e7ec708d5aff10f2ca450cb09289be8b7b949271622326c86ab58b84dc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-44225): Move this into analyzer"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala"},"region":{"startLine":818}}}],"partialFingerprints":{"codehealthFindingId/v1":"382da18525483420c1b7b7a3e59b99b88ba54e3c4a6dbf021feaee54ac49b8bc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-60830): under spark.sql.charVarchar.standardSemantics.enabled the scan wraps"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/EstimationUtils.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"2393d98334b65a2fdf93929dbace876a136ccc37210406c52561ba8c0e6d0470"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: it\u0027s difficult to support string operators without advanced statistics. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":253}}}],"partialFingerprints":{"codehealthFindingId/v1":"73c1e352a9f0a2d4a9902f4e3c0d97294ee2e36e85a1267baa19a8eb9c631470"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It is difficult to support other binary comparisons for String/Binary \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":332}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ce2a0d51d76eff8e8fe94c9e64aa233b5c8e02d9322248977dda903e3c01ec5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It is difficult to support other binary comparisons for String/Binary \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala"},"region":{"startLine":726}}}],"partialFingerprints":{"codehealthFindingId/v1":"2291f4c365bc14c5ddeb939de5f7b2efc732df3a0bfe0dfd3625320503649456"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support nullCount updates for specific outer joins \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":328}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1385797791356bacdc0b5e6aff015e1ed166c6c7e3ef5fdc68da189f50bd47d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It\u0027s error-prone to estimate cardinalities for LeftSemi and LeftAnti based on basic \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea78eff2b75ff26ce1e16ffc6e816f15ff483c48a7770bdc6f39b83053554c11"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO support multi column NULL-aware anti join in future. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala"},"region":{"startLine":399}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4e5241b5207670b6f1986179f6ff05bfb9a4327752a31d2d0c3648465ee29bf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO For v2 commands, we will cast the string back to its actual value, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1615}}}],"partialFingerprints":{"codehealthFindingId/v1":"026dc34e4bf368f87dbca5e877ab77e6c6c2a325767f09cb7db874d1e0b5bbbc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we should use the visitRowFormatDelimited function here. However HiveScriptIOSchema \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":2037}}}],"partialFingerprints":{"codehealthFindingId/v1":"70ba8d8181f67b2847ec5e14593672d2438b1cde9875aca138062570f5adc02d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we need proper support for the NULL format. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":6301}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbb79e6f11e83fc0ba31c0d6bfa4509b0e1561daf0f2d6f98155ae27be5bcb73"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO a partition spec is allowed to have optional values. This is currently violated. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":7803}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0daed5a27d0eb85628e379afb1d16bdf4cf92acd579285219729cd61f6cb278"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add a more general rule to optimize join with OneRowRelation. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/DecorrelateInnerQuery.scala"},"region":{"startLine":447}}}],"partialFingerprints":{"codehealthFindingId/v1":"7163af721c8fe9571092e941915526b595f1ed535c8806fb972eb07ff99461cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO revisit this logic: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/EliminateResolvedHint.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"b96621d35c022cff0410de53e4793fcdedf2eaf53f0269b175ec69a7e7a05859"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-34956): support multiple fields."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdfb39847d6221be19268eaf3bb36b44cebfff9059d641debb2b583924d89b35"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: ideally Aggregate should also be handled here, but its grouping expressions are \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NormalizeFloatingNumbers.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"106c063365adcd2d3700ce62aa4365d14fa6c834c3d1b8f553c47e0f420d0432"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: non-deterministic predicates could be pushed through some operators that do not change \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":2981}}}],"partialFingerprints":{"codehealthFindingId/v1":"621a9a7a60e4a5adb7a2e30f1d0489d1ce6757c30038fec6514c9bbf12728c29"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This can be further extended in the future. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/ReplaceExceptWithFilter.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f10d41d30d0570c99957eac823836128663022a6319cea1628ca902b45d7754"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: things can go wrong if the common expression is nondeterministic. We \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteWithExpression.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"d531a61b070ff1f88a5ea748c985870decbb9065a89e6e54e1320f4b69ffedee"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should calculate the ref count and also inline the common expression \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteWithExpression.scala"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1bf647bf2ee688986735270df36fc86d4152dcab7ee9007d805b279f140d697"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: do not reorder consecutive \u0060Add\u0060s or \u0060Multiply\u0060s with different \u0060failOnError\u0060 flags \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":406}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f692640f29ae2155e44405b9731c5c8bedb58c0999b9ab1191ba77fd58cf0fe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: \u0060EqualTo\u0060 for structural types are not working. Until SPARK-24443 is addressed,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":467}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef71f54dfb075c5e7d166102759867a670765300fdbd21eb49de4201e24c8482"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we exclude them in this rule. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":468}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e73cd0cbbe7d24267410d5f006ed68b0f881a7b16d1c07d87940d4b877f9587"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(cloud-fan): It seems more reasonable to use new attributes as the output attributes \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":1331}}}],"partialFingerprints":{"codehealthFindingId/v1":"73fa820b0b8969a3a086912e3a82fa9a23a5a5cf49700fc711a5e2cf12b6a5e9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: revisit it. If left side is much smaller than the right side, it may be better \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea45cc8f8f5ba56ab711af3e90a17fdbb900f5593fbe7ce6f56bef05e49c6dc5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: teach \u0060BroadcastNestedLoopJoinExec\u0060 to build the left side of a LeftSingle join by \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":386}}}],"partialFingerprints":{"codehealthFindingId/v1":"74d912ad21c978f02b81a74776624ea4219d9436825660fe78995b15ed9815c6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // Kind of a hack, but safe.  TODO: Tighten return type when possible. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BoundAttribute.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"29fba740bdb8dfed636351e6a1d1a63844fa4c4e990d40af6e7a53ab25815c47"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Could be faster? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1532}}}],"partialFingerprints":{"codehealthFindingId/v1":"62e162e3f851b14e3c217d8689666e0cda28819830bbeb338e84932cfdbb285f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Could be faster? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1560}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e5452149e66a7f6259352f1251fe716477446983156bb2989d647cd8e1a65bf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support whole stage codegen too \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ebfa61849c434ca089db889ea60eb13b8e9fd34f198e3955f56cf8d90be2a3d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-55278): Honor declared non-nullability once the worker protocol can enforce it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExternalUserDefinedFunction.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"effe64dc129507149fb6fe30261f507b55924eb6f398fb285d3edf52ae256f8e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support TRY eval mode on datetime arithmetic expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8fe4f6a23e7ccc5437a5114d876a2c4b431453b1cb649b1ed3e01cf5ac1d812"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support TRY eval mode on datetime arithmetic expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"1505953c21fb49cdb17ce34a39226758891b3757dd7652393b605a11fab6beb9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support TRY eval mode on datetime arithmetic expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cae70e96ed5bf68e1b52c14f9e44a88011aba905e7af043df2b44173310a50d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support TRY eval mode on datetime arithmetic expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"042f22eabb82dea5364465e073ae1f715e28782173a6cd9bfe469c43aafc28f7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support TRY eval mode on datetime arithmetic expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"26945cff0de7e1f93460e7b5961458b3660db5163ed4cb6f3831b89fa927c393"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: handle functions defined in Scala too - in Scala, even if a \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/V2ExpressionUtils.scala"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"083d07d3a2ba31abbc3dbe5aa4027e055bd0dd0f6c44a902b027ed103200ab00"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-58730): this serializes each element as a one-element array and strips the brackets,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala"},"region":{"startLine":1589}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1c95387174d438600a70ad1a9498de94c473d30c86191fd6d020430d2b4157e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: although map type is not orderable, technically map type should be able to be used \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala"},"region":{"startLine":1129}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a4133ff0bc2826a895583286678cca8dd8bd8f680b07c1f2a44a28f6a651e3a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: although map type is not orderable, technically map type should be able to be used \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala"},"region":{"startLine":1175}}}],"partialFingerprints":{"codehealthFindingId/v1":"aada16c8f54a7a0991b9e53f348873a2bc0304bc856afb95b42ae0327201568b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Merge this and \u0060NamedLambdaVariable\u0060. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala"},"region":{"startLine":817}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3ba07157a7ac6ba7c5f7ab6a4482fc18613d4db4d3278a84916eca04e27da6d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support whole stage codegen \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateUnsafeProjection.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"bed4438e9637e2898eece216512409b3cc594b765f5ff4f230d59351fc76502f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: implement support for decimal/date/timestamp/interval types \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/datasketchesAggregates.scala"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f7ae6bc2df161a12275250519940cf2adc33775b45c53343baad366bf41d7a7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: improve error message for java bean encoder. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"56c65e79b08a8a95474e709d554bd9e0fa06c5c90869597bf6cc21cddd6ccfa6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO more implicit class for literal? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6d45e7a0c7f15cab24ca24bc0e27d6ef3948cc5d6eca53151479a47513a2031"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should follow hive to roll back if one partition path failed to create. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"2490ac42f93d99fb348a4bf9ecb7c3f77e77a2f4ed48360612f5bcf8201b6566"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should follow hive to roll back if one partition path failed to delete, and support \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"de5e60c438f030d99b2053dfc19f0e819f634619be37e5b82696ac07cc426e32"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should follow hive to roll back if one partition path failed to rename. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/InMemoryCatalog.scala"},"region":{"startLine":535}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa5b34328a1768db670e7168bdde8c5678b23f19203c2166b1e49351f9972e77"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: views stored before SPARK-60876 can lack the CHAR/VARCHAR type of an outer column"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1216}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbce2df5c2787eb661823cf16168006c2e0b9bc3b259da4bcf4f424ce9424be1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We need to figure out how these methods interact with our data source \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":1480}}}],"partialFingerprints":{"codehealthFindingId/v1":"17631ed34bf5ddf8d5b87f60ccb0e1a9a31ad1f94cf04be4036fdb92f19ae957"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // HACK ALTER! Ideally we should only resolve GROUPING SETS \u002B HAVING when the having condition \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1003}}}],"partialFingerprints":{"codehealthFindingId/v1":"32d5127067d31e078e034b0a574115e2a05636922b2d9873cb4e94498f0cb23a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: mark Aggregate as resolved even if it has GROUPING SETS. We can expand it at the end \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1008}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8763a1f70e4ac6fc384825ee91a7a342b59eb2029d41fa833b8215e6f034529"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Support Pandas UDF. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1127}}}],"partialFingerprints":{"codehealthFindingId/v1":"13d9155edc6f379ed9f21e7e1f2aa1996fb3952900b7e45ff6241fdf1bd75733"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Maybe these rules should go into the optimizer. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BooleanEqualityTypeCoercion.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"918c4c420612322f45147130b8963e854a9c7df1c4251770c0a03b69eb4140ab"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-27484): handle streaming write commands when we have them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":424}}}],"partialFingerprints":{"codehealthFindingId/v1":"768612bf8dc950db7d778aac3115c2375ea22e80465070dcbd0067d545270054"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: although map type is not orderable, technically map type should be able to be \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":1129}}}],"partialFingerprints":{"codehealthFindingId/v1":"b84222eda7e65fef41c30f2a6427f9ae7f4890330311baab8060c04ab94ee62c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this type check once we support Variant ordering \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":1138}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4438cecc19c19565f8eed2d08a3adb5e5f9691832980429da2d7a3e3e212c11"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-44754): we should handle all special cases here."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c8f0ce501839e62be008d7f2738db6615e0934c65f2d6adc5f7d89f46acaa61"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: since the field name is already resolved, it\u0027s more efficient if \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FieldNameAndPositionResolution.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa9fc79c99127a50b17c0471f81a8c09b331a859ffb75e533c45dd08ab8b6a20"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Don\u0027t construct the physical container until after analysis. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/PivotTransformer.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"01a62c564bbcefcfeacc1f63292fe9503fbf10fa259572f21e70f25a84c5b4c4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: It\u0027s hard to write a general rule to pull out nondeterministic expressions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/PullOutNondeterministic.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a86af52a2d728023dabf5e50b8ac994a58ae6baa5f14361fea322d1cb0e0ace"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this condition only guarantees to keep the shape after the plan has \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveLateralColumnAliasReference.scala"},"region":{"startLine":297}}}],"partialFingerprints":{"codehealthFindingId/v1":"66eacb1771a51e89be63b5ef05a258d7aec75f8dfdc92dbd10a5495e7b04ff27"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: currently we don\u0027t support LCA in \u0060groupingExpressions\u0060 yet. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveReferencesInAggregate.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc9eec97da6ebc8cd5bbe7d15f55d1b6aebc161180330c382f851a52bc5aa2cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove operators from this list as support for avro encoding is added \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8dae076c6568ae18d636890c935d5562354dfd34c108d0dfe2aa90dca21e0a5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: check if we are resolving a lateral join condition once lateral join is supported. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/UnsupportedExpressionInOperatorValidation.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ee03481c755ad376ffcad899e85eea4beed91f79b35efbec74a9558e5028f19"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this is extremely expensive. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarArray.java"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"4396a130562004ad80e2f86529ad35f36e5ff01e980e33a56a5e81288274092c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO supports ZStandardCodec \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/util/HadoopCompressionCodec.java"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"856e153406fcb6aa8597931e28238b14423a157f8fa0a0305fb5d3d98e19b9e0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Use a more efficient format which doesn\u0027t depend on unsafe array. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeMapData.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6b2d3d988bba7b8a7ea64070ba59725ca52082b461a315027e15db1d47bd2b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move this to org.apache.spark.sql.util or consolidate this with batch API. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/ForeachWriter.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"81a63b42f52de3e59e0444d1a4a083ee41afea3c7fd98d68792a5eef105b84af"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Improve the performance of this if used in performance critical part. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"6eaa09c7b00ddb80e358b6c033797231fb1840c24e75c3f7da5293d30cafe11f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-45970): Use @static annotation so Java can access to those"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":18722}}}],"partialFingerprints":{"codehealthFindingId/v1":"853d98cb12f7d0dc5893bab97107a9c884d3489fa0b761f63c210c722a3fbbba"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // todo: support more types. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ArrowUtils.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"c471857ec77e40c61a0df30582b608c2c07b9ea348ee80e6fc1bd2a1f80ddd39"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: allow upcast from int/double/decimal to char/varchar of sufficient length \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/UpCastRule.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"62f33242a3a8516c6c27eb2386f4696a6a1f69605a912886360df45e0272d821"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-54391"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/progress.scala"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"c906ce861772b549334a95a2785db1e27c339077d8fe285c6308854b94f53567"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we should only collect properties that have getter and setter. However, some tests \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/JavaTypeInference.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a09b3326c8cae184e5349247b62aec3f58e4bf76ed19a94462c63765ea59cb0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // The following 2 lines are exactly what MySQL does TODO: why do we do this? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkParserUtils.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc2161654442439b44fb08d75a1b6428ed9354916bdefc2a03db9249a67d7499"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO check if this works. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/encoders/RowEncoder.scala"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecd3d64a3d1199b6dd9c225e42474503fc68d4fefdc693f803ef052e9ac05116"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Should I used @Documented ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/java/org/apache/spark/sql/types/SQLUserDefinedType.java"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf9b19bbbda7fc51ca7ea5eee261c2bf6db3c306167cd0f1b963828f3993ceef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-33481) This is a naive way of calculating numMergersDesired for a stage,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8984c4df79b4e8f422171006dff957fefa5d47ad36f15915e88d70546f920d8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we can use better heuristics to calculate numMergersDesired for a stage. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b06c52088cdf557a2eb3288ed303fdf7cd9b36ddff9b907f0bb9244430c18f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Currently, task to container is computed once (TaskSetManager) - which need not be \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"16b533adfb6755d4102f2a3e14ca7898b4cc0b126eece36786b79e626d83d227"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(davies): add R dependencies here \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala"},"region":{"startLine":752}}}],"partialFingerprints":{"codehealthFindingId/v1":"79d92206a4c27bd35d86f4994b0c66e5496dbd77c62550cdea2b80b11b959975"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: it would be nicer to just make sure there are no null commands here \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1170}}}],"partialFingerprints":{"codehealthFindingId/v1":"46164f9180662523971cb78df731cc5f2f099fb9ae1576b7e4d6fb8e6f3077e0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: it would be nicer to just make sure there are no null commands here \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"7017425ea2479e532bbde771b9667739f3396f590dac00c59580ce52f9fe4f2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add code and support for ensuring that yarn resource \u0027tasks\u0027 are location aware ! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"2584ef2554507a3b3124631608780c8b785f88f676d547fa372000cf7ab780b2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO - We need to update once Hadoop changes - \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocatorNodeHealthTracker.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"b781df35b4a8a83908184d600b1ecea325285d2091ab552d44bd809e708ab466"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO support windows \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/backend/minikube/Minikube.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"95150f829284ddeb2b40d1f69a3c0f0043cc9bae2c50e69da2b20a241f3ca776"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: with dynamic allocation off, handle edge cases if we end up with more running \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c9d2ff02b645ac7bf4eb407785d66b49c0a49b042ffa18b55e6d16084aad5be"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This doesn\u0027t actually work for arrays when we run in local mode! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"repl/src/test/scala/org/apache/spark/repl/ReplSuite.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"a93a88e09a8b96180a63c9073e5acac3b91a9010aa6b9940b1fd9bd5595dd096"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: revisit for Scala 2.13 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/run-tests.py"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cee3b011d8a8239818e0c82195bddf2f78e86b7692fa03ca05b836be9174125"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(davies): move into sql \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/java_gateway.py"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"64f3b9cd968099b88427d44ced3eb8d3b17ed82577e67abfd545b940dc29f3cb"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack namedtuple, make it picklable. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/serializers.py"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"30d17aace539588a5dbcde2db624fca2af5e5b4617a1d27c02e6eaa3ca33e933"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # hack the cls already generated by namedtuple. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/serializers.py"},"region":{"startLine":403}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ab091b23cedb299f010624e4900201d9876370e9627c2a264ca9aa5c0f50ed1"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # hack inplace \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/serializers.py"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cc5459dffce462a061d4d191828092cf9ad2e6d2d5e5b71003b25d106a41589"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support windows \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/shuffle.py"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"d15583b2f2cf04d216cf4e463cd9f32a37ad590d606ff6317c0c4d4b1f30b5f1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Remove the following two lines and use \u0060Process.pid()\u0060 when we drop JDK 8. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/worker_util.py"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"489ff0320895d260199e2dfab919f0864b12fe3eea67f955a8ac229572d19e56"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: uncomment this until we have ssc.pickleFileStream() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/dstream.py"},"region":{"startLine":366}}}],"partialFingerprints":{"codehealthFindingId/v1":"38f865dc53f89cf71e64343cbe13f941b800897c4ed33a39ec77826a233a6260"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # HACK ALERT!! this is to reduce the backward compatibility concern, and returns \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/column.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"62868fdbb877aacbb7a26244d3f8c1a034c73aa32fd9ac89d929d6946b591568"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # HACK ALERT!! this is to reduce the backward compatibility concern, and returns \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/dataframe.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"2af4f3e4fcb70685dc7f4d642e5918c99a16276e85330304cae014bb18480404"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-55324): Support complex types"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/conversion.py"},"region":{"startLine":2197}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba9129263a42fad8eb40bf4145e07894821016d15a8fca14b562a03efe13a75e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-22947): Fix the DataFrame API."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/dataframe.py"},"region":{"startLine":3028}}}],"partialFingerprints":{"codehealthFindingId/v1":"7bbeffcf400daf59146903103bc9ffc0b5cdfaf222b6e3f3e0a4567fdb00eaaf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-22947): Fix the DataFrame API."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":868}}}],"partialFingerprints":{"codehealthFindingId/v1":"1006a55c3144a7719a2f85f00f412fad81d153722fec9ec0fcb4280a88dc8473"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO (SPARK-55218): handle implicit-None return bodies like"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"cad27a626b7faed2cb7c7655bc55196e7545992b2ab36bd4a6081023c5fc5550"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # wrong results. TODO (SPARK-55210): add an exact integer-power"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":896}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b97c053fc64db7deb46db3c60d144c8e501497ebb7493b4a1e9c4511303816d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO (SPARK-55210): map overflow / divide-by-zero precisely."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":903}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce0cf17d8108ce02b2b56fe1e939561bcbc9645ca0981b6bb6410c59c953ba75"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO (SPARK-55207): Handle assignments, class vars, and closures"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/transpile.py"},"region":{"startLine":967}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c4414e8df6d089eb816f23da3c65204ed47dff3651551548ae753f0e672542b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: do this properly like on the scala side \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"d469e83ddecc0f4de220edf1f293686de37b62e4a73654b9b5f90346b74d6d14"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: type cast (such as int -\u003E long) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/types.py"},"region":{"startLine":3335}}}],"partialFingerprints":{"codehealthFindingId/v1":"375cfcd6a5618641fc224c09d8a513e5cfd09a29068536ea74c60fb1749be692"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-53286): Support analyze method for Arrow UDTFs to enable dynamic return types"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/udtf.py"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f2a502c6db22b22897e469ff78f8b490646a0d2c4e5c2c27c47c0c06be90de7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-53286): Support analyze method for Arrow UDTFs to enable dynamic return types"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/udtf.py"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"78159b9bb0cf4f4ea8bdcafa3f993ba9d0956fd170580791ba69b87ca4b5fcee"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43877): Fix behavior difference for compare binary functions."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/utils.py"},"region":{"startLine":473}}}],"partialFingerprints":{"codehealthFindingId/v1":"4532a1b46ad8965e15ccd9a617f5e9369c167f978d25aa8c04dda11b38c68767"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":399}}}],"partialFingerprints":{"codehealthFindingId/v1":"5bd0ea98353e165614bdfb5872ecab165e710a6718377693cd11668bd8c0feaf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":411}}}],"partialFingerprints":{"codehealthFindingId/v1":"6671fb2a05399ab74a0da031906abb8dae472d6bfa74748595ccf88a6e4f2980"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad90ed935d9bdc9b7f4d8139abecb0f40e91cca67e7ea88d91c8e1800492d1b2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f64897411da554cd2d972fef4faa08d86de0b1037ccef6e6d3042bb6f21a3d1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"f90828494e79478064b7f94f77922d9da2f736e7f932c15e5c907011b5d8e9e3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":456}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3772d4f9085ddc1c3ab7ac69f67355440ae34ccb730819ca4281ba21876e67e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":467}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2adb21c4618a7b796362963bd94b96d0ab74a9cf76a33c2f4d871fba430341f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf.py"},"region":{"startLine":478}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9823e3544d68a4077a5d27a90d9dade862f5c4eb70361b2a57e140111e24ee9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":3141}}}],"partialFingerprints":{"codehealthFindingId/v1":"235540af6e300e27bc6f8db9846def509d5e74b48251e3576a8758a4b83dbebb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":3154}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf31603cb443588d5659b705e080afc96d039aa8ccaab0d2187b92e358e7b0be"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":3173}}}],"partialFingerprints":{"codehealthFindingId/v1":"da3aa7facf1eaec973bba5915efef87c9aa90a3ac25f26378c09b0f47a35eda2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":3188}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d151ca1c09b2b6f5f9c7f10b3982dbe7d0176c1f6b2fdfc2427206984516579"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":802}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f80d67332f9a84acd614a58d976db9361a7ee7c50efbb627c865986e12d51c6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":905}}}],"partialFingerprints":{"codehealthFindingId/v1":"0903cb28df3ca53c08566ff6b9ad2f80414d2954f849848e7fb09ccfb632c337"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":929}}}],"partialFingerprints":{"codehealthFindingId/v1":"91442462d7dbc59512b54b62488639d65e27313eda3d36d07dfbc6c888a2c53f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":948}}}],"partialFingerprints":{"codehealthFindingId/v1":"68286557b45f3ae09563c9c17546a706ceb21bb1e4abb4769814fe7bb69c4f1e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":967}}}],"partialFingerprints":{"codehealthFindingId/v1":"3922836ad7a55584deba8d5bdb68c1038e3715720dbb5aed0afc64fddad9b926"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50284): Replace when an easy Python API to construct Variants is created."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py"},"region":{"startLine":992}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbe355603191aad6b7fb7c11c3f4dc95580e92f78f6184e6f04f323f4803ea61"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # Python. TODO(SPARK-55210): revisit once an exact integer-power lowering"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udf_transpile_unit.py"},"region":{"startLine":2581}}}],"partialFingerprints":{"codehealthFindingId/v1":"98fde3768fa7b611c3c52ed0e2114489581eccade1ecabb12ceb7d274ee77879"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43968): check during compile time instead of runtime"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":1215}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbf2472465f69d7fcfa49bd9d619006afdb2ee95949a957023d2f76715a82387"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-44233): Fix the subquery resolution."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/test_udtf.py"},"region":{"startLine":1534}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cb92abf9310b0c60d312a04c27e9f219743a5afcd0f2144f9e1ec0c75e98c36"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Verify whether original error message is inside the exception \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/streaming/test_streaming_foreach.py"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"79d78630c279a39553dd928cd9badf978bfd96f1de7e56e3c234c3ab1993ef45"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO SPARK-49046 this config is to stop query from FEB sink gracefully"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/streaming/test_pandas_transform_with_state.py"},"region":{"startLine":1643}}}],"partialFingerprints":{"codehealthFindingId/v1":"d88b0d24ff69cd01fdbde785c27ed79c797d5948fc790f1a5b5fcf67c4cbd420"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO SPARK-49046 this config is to stop query from FEB sink gracefully"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/streaming/test_pandas_transform_with_state_state_variable.py"},"region":{"startLine":993}}}],"partialFingerprints":{"codehealthFindingId/v1":"031a314d5b4624765b994f2131092e01791d4484d444b6c683db01283144fcb2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO SPARK-49046 this config is to stop query from FEB sink gracefully"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/streaming/test_transform_with_state.py"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9df67649af1a47622bd5bf5975d48d579eedaf7bf3118bbc80b5d9c24bcf780"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO SPARK-49046 this config is to stop query from FEB sink gracefully"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/streaming/test_transform_with_state_state_variable.py"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c6f302221ac508db635a8cbd1e4dff7ac708e28afff58499327edcf83f7eced"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO SPARK-50908 holistic fix for TTL suite"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/pandas/streaming/test_pandas_transform_with_state_state_variable.py"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"56bad8d94ae309d912efdaba35ed4bce2930b067095ce63a9c2bb4de34d83702"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Make toPandas support complex nested types like Array\u003CStruct\u003E \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/connect/test_connect_function.py"},"region":{"startLine":1202}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf25e77454548ad60ce9076031dbd17569feddfb87f08df45025f4f718fb7d5a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027cdf.schema\u0027 has an extra metadata \u0027{\u0027__autoGeneratedAlias\u0027: \u0027true\u0027}\u0027 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/connect/test_connect_function.py"},"region":{"startLine":1732}}}],"partialFingerprints":{"codehealthFindingId/v1":"49e216ddf91ee66e672428bcb9dadec9c167ea7c0e738dffba2bd0b7a25dd8b8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-41283): To compare toPandas for test cases with dtypes marked"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/connect/test_connect_function.py"},"region":{"startLine":2242}}}],"partialFingerprints":{"codehealthFindingId/v1":"858c203cdad2511b2975bb7780f0cd0ae3491984f437545e3c5a4d6d7af02b8c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: compare the return values after resolving dtypes difference \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/tests/connect/test_connect_function.py"},"region":{"startLine":2272}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce73dbe5606765fb917b48397c0110af32e30868cd877b91ce7c351c74fcb0eb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Add StreamingCheckpointManager to this when we want to make it public \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/__init__.py"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbac896e951835d8cd610bf6d114f71d397cb2eb20b8019f0af972c776433efc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0340eb298026e247153d27e2a48b1e0340b8e0d8429b63dcd59a54aa557e9b3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff3337578a1782b0de4c55be9812c6e435a2a00aa192aaef48a8385a2caacd17"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"7326acafea2cf11007b2d02953a249130b875e802011d1f9bf091d74644d584c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"796c7c146fd77621cb432175616649058ae559aa23305233fb68cd71a79e8715"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/list_state_client.py"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f21c7b9a36dd24440d06185c003e38c708a97d5592de60c063d1e6b459ca463"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba61b96e56994633138098fe6fdf7514f2eb77491c869e739752dcf2610feba7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d0c60bf2a0088c722b2475b503e89da2c01837b30821baa822295d6f2628d72"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6df6e520d3ffe171a57b84a94c00b0d816c5d6c20923afcaa8e776cd0ca0651"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"08105f9ecdc4f09f5091c5e676ed88272826389cb11ab916b254bbe10bdf564b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":270}}}],"partialFingerprints":{"codehealthFindingId/v1":"45937a3ae052702418cf2c49d6ab2c690c3ed63cdfdc469755aadba8bfef783f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ac77ff60491f3c21310d141f255486251d2a38c43b5deebab7835f5a3be673e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c34b4034e96af56671cbc8d6de190fbdabe788e92550e9aab9a291904138b6b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"700b1c11b32b1444f9ae58262ed161fbedbae641d14bcf3d735a9688c8303667"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"8919026832920417567d8841bc99be353705355ac9560780b9467a92f1ae6a5d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a991781f7c70810912c278f82aa28ceca8f6e0b7c9e07edd2b601829b9a0350"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":402}}}],"partialFingerprints":{"codehealthFindingId/v1":"efb6c05d88c76f2954ee780cc3f388e7f95b2be662cd08981846ee5267d1aa6e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"463361708cfaf5bd91a3531c2b9669b5f00853236b6180c1b9538e0f3a61198d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":434}}}],"partialFingerprints":{"codehealthFindingId/v1":"b762a1c1ff46ff2a49442d5b11e54817ed1cba43808fcea0161ed2222b9c1ed2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":452}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8c505998df837e04408f4c3847a4211a5349a198ac44504b264bb791e3c7191"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":604}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1eb322abf27bf12328c472b5dc028a7e61d4617b0c1a721905e6ff0c7a23763"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3e77d5abaed370913471981fa12f39cadea9d002e7aa5e51dd3543a76fbb7c9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8bd645001e20398778d788f3cb7d75d767b48b677a994d4bd351216db2ecac2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"783efd7613c39136c15fa2e9f82a9c6a9eb420a51fb487f6d17eada47371b558"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify user facing errors."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"77dee61f8c112d7a944dddbd3b3c7871a859024c5c2335a0d2521321fdc5d007"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Add StreamingCheckpointManager to __all__ once we add streaming checkpoint manager to the \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/query.py"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"c30f019fe3a781c6ffe5e2a71f13763e6baa1827568031dd1e5c8c09537810cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-40437): Support string representation of durationMs."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/state.py"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"f67eca87abd053963114ca2b297ec6c91bbc902fe0b39f9a6ed57327fe9cb519"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-40438): Implement additionalDuration parameter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/state.py"},"region":{"startLine":208}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0c74f85c7b397d956cb0da4b4a1c62d5ff2384e70a683ee01f625ca63eae611"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify errors thrown by internal methods."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"3571499874fcf3587d3dafb7df016a8791d86eddf98bcd44b44d0ab651411dbd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify errors thrown by internal methods."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"9467d2af71a52f0d3110d60cf68c8e61bf9b9075a4937b562af9cbaaaf37634a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49233): Classify errors thrown by internal methods."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_api_client.py"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"7dca9b12a80d0139cfd2c51be058da06a87199a3da084cd48d22758102399e1f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Use streaming quantiles in Apache DataSketch if we want to run this longer \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/benchmark/benchmark_tws_state_server.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1384d41c7e1a0f6e4c1eb461a1afd92b808177081fd4317bfde0b1a52d543b0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Use streaming quantiles in Apache DataSketch if we want to run this longer \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/benchmark/benchmark_tws_state_server.py"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"82c9352c8b5aac062dc9beb2ef6210d7fa24e7f3de9f7b3e818975073f2ff2bc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Use streaming quantiles in Apache DataSketch if we want to run this longer \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/benchmark/benchmark_tws_state_server.py"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e829351386403a106a21d51f9a73577066b1be8081f6dee18b5c4f9d90f7706"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Use streaming quantiles in Apache DataSketch if we want to run this longer \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/benchmark/benchmark_tws_state_server.py"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3df0d8d1ddcd8e263245201693e734b42d43460cc2a4d302e23b76544f16747"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43847): Throw structured errors like \u0022PROTOBUF_DESCRIPTOR_FILE_NOT_FOUND\u0022 etc."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/protobuf/functions.py"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"337d18827b4f78e446a8f3580dac15ddf425c5f53c3dd1dd0dcf8e04212c5c7b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: handle nested timestamps, such as ArrayType(TimestampType())? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":744}}}],"partialFingerprints":{"codehealthFindingId/v1":"560e900c468102223725587808fcea94b08b21094b502d7157b70001c3785c73"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: handle nested timestamps, such as ArrayType(TimestampType())? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":776}}}],"partialFingerprints":{"codehealthFindingId/v1":"e825b168ad6fa7c4b3547696049863494165a99001486d024bb749daffcde139"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: handle nested timestamps, such as ArrayType(TimestampType())? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/types.py"},"region":{"startLine":844}}}],"partialFingerprints":{"codehealthFindingId/v1":"595258ecbbe17924b0d1378fef8171120881e7d7d542b3daa43e03b3df9d2a98"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(HyukjinKwon): Relocate and deduplicate the version specification. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/utils.py"},"region":{"startLine":24}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f9757f422f40007bef6c92962eca071c4e3ec91c74cd5901a0107ae2f287a0c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(HyukjinKwon): Relocate and deduplicate the version specification. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/pandas/utils.py"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1e752c50d620f725736b5715bdf4bbbb70b82e66a03ab2f534c4d7620b5d913"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Fix and add an example for StructType with Spark Connect \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":24493}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f1bca236b8e6ecacc1b8cac299c4f5b5d8c2f6991f50400a01a6ea214734a72"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: reuse error handling code in sql.DataFrame.withWatermark() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1103}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd5d3e7fcd0c043d2465722a50df11724fd5da318ebdab4eb1feefa169692766"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: revisit classic Spark\u0027s Dataset.col \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":1961}}}],"partialFingerprints":{"codehealthFindingId/v1":"73f28761b97b6b840125142fb979ce2d5ba4814f64ef51ad2d833dfde7876bbe"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # !!HACK ALERT!! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/plan.py"},"region":{"startLine":773}}}],"partialFingerprints":{"codehealthFindingId/v1":"38a1211621ed8273c084a13437a23efbc37d7128fa5812e534c88ce7193435c2"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # !!HACK ALERT!! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/packaging/connect/setup.py"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ab2352ab6fae5dc8515c92b89ac9eb0ba16074f152b63f1b20d432ee3c121cc"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # !!HACK ALERT!! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/packaging/client/setup.py"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"62d257e9a2e21b5053b8ca5aef6765c5dc92dc96d7fab1a870717f5c5d408cd2"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # !!HACK ALERT!! \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/packaging/classic/setup.py"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7b0f360fc16489e8c6ab0c34884b1d7b2ce0c987bc94bd51b80d4dfd9e4aa5e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-40539) Achieve parity with PySpark."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"077443ea5f8f4c667fc6cd416ba5a31c6ed4e28acb8a048cf7a0f2d4e4b6ad10"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Beside the validation on number of columns, we should also check \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":794}}}],"partialFingerprints":{"codehealthFindingId/v1":"35633c9b0024f4054a5e95d7f34c3a31c7b634f5212c0f211f94556fa91ac9c0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: simplify the code when _invoke_function() supports None as input. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/protobuf/functions.py"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca41ecd7c3fa2e792df5a41702754bbb63801b8005360c68b85d0ff72791771a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: simplify the code when _invoke_function() supports None as input. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/protobuf/functions.py"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b40b48d8f19d0cc97ed03bf98032b76d2f22a05acf43e8c3fb1ea68b976e08c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Support directory path. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"32471ae74f438b144dbcb3c35f085f4bc341bedc3043c86b9c08f66f34736687"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-42658): Handle responses containing CRC failures."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"55be5efe35c8a2c95cc4668562cf23477b605258e1dd57884815f5b86c8353a5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-42658): Handle responses containing CRC failures."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":484}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dfa48113411c9e825d46ebc15ea8ea861b596dc2f77e724079c4c31d8c7fedc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-42658): Handle responses containing CRC failures."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"177e22269be9604b46a46cc1c7f0d900312870d8d056dbb8565931dd03960565"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: use the actual type parameters. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/_typing.py"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2ed8ac4ea94afda454636eef0bbd09650f6f16298ad90423e91278e8849765a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: codes here partially duplicate \u0060DataFrame.apply\u0060. Can we deduplicate? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff0a6349fdd6ef4c8ba02d7e7f8b97bd93bd022abb8d05aab0a915f98163260e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Index will be lost in this case. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":627}}}],"partialFingerprints":{"codehealthFindingId/v1":"72b63edb8b173950c887485628f42a8f4771ca813e03f7946fa71a048f29a3d3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: In this case, it avoids the shortcut for now (but only infers schema) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/accessors.py"},"region":{"startLine":914}}}],"partialFingerprints":{"codehealthFindingId/v1":"713c96cb61075d7bc46405b5184b17e7de8e666d90992cd47c29ce48995a0c0d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: This is a quick hack to support NumPy type. We should revisit this. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"daf161e640ce2ca7f5e855f21e170f2ff7e456ea887d45a945e1caf94bbf34c2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support more APIs? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":564}}}],"partialFingerprints":{"codehealthFindingId/v1":"994091c823c04c0e2a8fc3b4416298b4b85ee12378182ad46cbb1cc9894ee2f2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: axis and many arguments should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1071}}}],"partialFingerprints":{"codehealthFindingId/v1":"556bdb16c077708849e1ec25e1b5e97b94e07b94108256ea4cfac1251a199a9d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: axis, skipna, and many arguments should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1160}}}],"partialFingerprints":{"codehealthFindingId/v1":"19b26ccc4c9736bac93e820b576ec081689219fdcf9c6aacafe2608df73f5fd4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add frep and axis parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1223}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0aa6bac3f272aed8a6cce7410d9316c39709eec8082f917bd4a934737c5574f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Update Documentation for Bins Parameter when its supported \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1298}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d49406a3eccd8e9218d513d56e08455068801d062285d725e60843a7fe09af1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Hit a weird exception \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/datetimes.py"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"3138dd9aed5148277db3275162a97e673bc9365f0625c940b89d7533f2bf417d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-40226): Support MultiIndex"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":602}}}],"partialFingerprints":{"codehealthFindingId/v1":"296b936ded39d8b93c5b3f576fd97f45d56fb027bd90ad92d7ccc680b71df7bf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: We can implement shortcut theoretically since it creates new DataFrame \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1358}}}],"partialFingerprints":{"codehealthFindingId/v1":"27b728cf25ba98166b854de43945b0bb33427565199eaf7a0ec8f8dc3d4d41e5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: We can implement shortcut theoretically since it creates new DataFrame \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1422}}}],"partialFingerprints":{"codehealthFindingId/v1":"032379d44d09e23a8bb8465637339121980e32ee37e5041d3d8282b14f3cf6ae"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-46156): add \u0060axis\u0060 parameter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1426}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ad6e5e6e1ec25723309ceda1c6c0d577c5b19ea54bd20b7ef8ac4f69be9adfe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-46159): implement axis=1"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":3937}}}],"partialFingerprints":{"codehealthFindingId/v1":"33d8b013db9c480e6661614e49e2db49b0ee593d4e1915825ffac0ca52f98991"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtypes? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4213}}}],"partialFingerprints":{"codehealthFindingId/v1":"f69af4fa94d703be88f8829e2ce91e7780c8967562489d6507fa50fe510f09a2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtypes? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2789}}}],"partialFingerprints":{"codehealthFindingId/v1":"72600f725fef9dda2d45c32299bc8d98974f82aad0fdff6a4a3c6c9db79fbefa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtypes? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":834}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cb14f119ad4d43ab950e40e10a9a05d916dfa7e8aae7560eb2c43fdf46328c0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-37723): Support tuple for non-MultiIndex column name."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4881}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a1f44510f550e2c6ad56fe695e53e9e9fc2bc28c579c19ee9eee0253beeccc4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-46156): add frep and axis parameter"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":4902}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e3a144e64fb350fc2e8a1b59df2625edc349a6392418a0319526f1ef2846583"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support other as DataFrame or array-like \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5383}}}],"partialFingerprints":{"codehealthFindingId/v1":"69e8cff3ac28ef9ca95a17ee7cf707d52cc6c732200d693019058018aac9394a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027limit\u0027 when value parameter exists \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6306}}}],"partialFingerprints":{"codehealthFindingId/v1":"e58a8705345e69dfe7bbc5c3b9ff2bab8be5b30be09fc2d0ec183d2d98503fbd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: need special handling for multi-index. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":8973}}}],"partialFingerprints":{"codehealthFindingId/v1":"10b562ba8f97394f294c8102ccfaecdda724b8ec5434491f14d30a96d37ca0c7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":9368}}}],"partialFingerprints":{"codehealthFindingId/v1":"a20e3319c4a70ba48a6f294f3da5d688ac0d85ff43a0cad75a0c6409f9c4ec0b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexing.py"},"region":{"startLine":684}}}],"partialFingerprints":{"codehealthFindingId/v1":"d15140ec2036e49c393048b99e5e3e3f6e143496cea467fb708c6a691af4d01a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2312}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a3987377140c9d053ca9c398db7aa9684b28b0e100f70deafb9769db7d1cb4f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2431}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2ad26beaf5d4369a2c4d27d9975070b7ee9773e030a1ffabd983ae507af3474"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5385}}}],"partialFingerprints":{"codehealthFindingId/v1":"9084ca4e62b83120f9f98845e0f957894d7ab5cbe470338372d4d4143b46eaba"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5468}}}],"partialFingerprints":{"codehealthFindingId/v1":"47707c620df959e20021234d9b6a5ba89f0bc50572af6004191ab2ba0a63509c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5485}}}],"partialFingerprints":{"codehealthFindingId/v1":"9140bfe9de4ebc9f9e8677956909b26c20bdf6af157a6d317eb6fce3b0b79ca1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5859}}}],"partialFingerprints":{"codehealthFindingId/v1":"d156121997f99ebcf7b8ae1c946b34fcaa05d00cc1bdc43c7c0f6b0af82949d0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5867}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0e4a5248865c8c89e002934bc15c2e92481b1c6dbe8722134a1b5b5a2547b85"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":233}}}],"partialFingerprints":{"codehealthFindingId/v1":"8575bf58a6e0eab0f3edb28f9a40dec26353155af9c89073a40883effd05e354"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: dtype? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":1096}}}],"partialFingerprints":{"codehealthFindingId/v1":"46c10ed132f02e049b7e491443ee1dc185bf616e9b3e4f0db81ea5bcfead62cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-46164): include and exclude should be implemented."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10023}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d7b5d798cc8241c6a3165b0d6b7d0ca33f002432efa5c355285a0f3ff2a93dd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Codes here are similar with melt. Should we deduplicate? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":11385}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cd709db71b962af2a8bddd2102c16fe1209465c508695e61e0683e20ec6acb9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: should we have corresponding pandas-on-Spark configs? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13010}}}],"partialFingerprints":{"codehealthFindingId/v1":"458a2ef955c667150b5b4a60b1838a3fbc4ea12c565eb2e1c39d45819d8d06f5"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # hack to use pandas\u0027 info as is. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13015}}}],"partialFingerprints":{"codehealthFindingId/v1":"9551c1600174a3b8912c570b813b450af78539ade0c866ae9f50cc90a338e2a4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: fix parameter \u0027axis\u0027 and \u0027numeric_only\u0027 to work same as pandas\u0027 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":13033}}}],"partialFingerprints":{"codehealthFindingId/v1":"afa93f4db2b42229a39a31361175cada1c64080f1ba420b65751acc5a045a02f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: avoid using default index? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14242}}}],"partialFingerprints":{"codehealthFindingId/v1":"eefe9cd9dff311f951703ba18b55215e49e90b852068f28c554bdc5514ccf867"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: avoid using default index? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":440}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0a229944fee4df7c7c6cdd93efa22ad4167be0ad4e392ae84f78fcdeb929ed9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-46859): specify the return type if possible"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14335}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2441c289ae1364ced8f7d6ea4e6c8f3d9ba961e3c54e47ed2dc359b678fd3b6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: is it possible to deduplicate it with \u0027_map_series_op\u0027? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14431}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7efbb27602bf60a8316609758dfd58e8462b262d2fc8aeaf5d3fbaba2037592"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027axis\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"37eb42385093472c5f680bdba2b8742e2b6765458b4888fd34ce411c76760a97"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027axis\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"41e996ce6754dbdee4a668d58f475d77fe980e2f97039b13287600e4b5ab92a4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027axis\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d2dc32d416a264da360e45d866359aa5056ee097c49c371f3ac1890656ff67f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027axis\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":337}}}],"partialFingerprints":{"codehealthFindingId/v1":"efc757cc996ffec08cc71c4cf682f70586a4ba7e0a598e74e1fe6083fefedc13"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: by argument only support the grouping name and as_index only for now. Documentation \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2393}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ac65af236bc9e5d763cf4e22fc4bc3ebd72a0da7d1d6abc68f6d7f4f3af4421"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027center\u0027, \u0027win_type\u0027, \u0027on\u0027, \u0027axis\u0027 parameter should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2797}}}],"partialFingerprints":{"codehealthFindingId/v1":"f59717ec6c14482e96bae10b04ba38ad0f755dcd0c87b12a712ec1044c229ebe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027center\u0027 and \u0027axis\u0027 parameter should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2829}}}],"partialFingerprints":{"codehealthFindingId/v1":"09573e9b9972eb4d5a85131aad470a973436c90c8a3fce1129927785fd9b10ff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027adjust\u0027, \u0027axis\u0027, \u0027method\u0027 parameter should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":2853}}}],"partialFingerprints":{"codehealthFindingId/v1":"c82ae9123eb0e7d7f148979b4fc521991481f49802ad7c8fd1564e65ebbd5d28"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027adjust\u0027, \u0027axis\u0027, \u0027method\u0027 parameter should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":3411}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a9b0a701229ca84e2567b490cf447dd69588fcc54d89a6a6b2fe5a40976f7ee"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027downcast\u0027 when value parameter exists \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":3342}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a34b3daae868fd45c5c4a13b318400d22eb7b68395dfac6cb3a80d767692987"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027downcast\u0027 when value parameter exists \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":3435}}}],"partialFingerprints":{"codehealthFindingId/v1":"e50f5fad6f714f01e76579d872134b6ac4e83fb89ca1a099b17fe797fca33e14"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027axis\u0027, \u0027inplace\u0027, \u0027downcast\u0027 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/generic.py"},"region":{"startLine":3528}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9fc2f2eb5fa4f4212d805a230c79b94eaa1e8559ce8153baa099fb9bbb63031"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Series support is not implemented yet. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"33250d8455b2e72ccd2a1e234c7d4e4ccf861e22a9531551a15c8bea536874ad"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: not all arguments are implemented comparing to pandas\u0027 for now. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd4c9614a0f4d6ae93f2972ae9bf5c6dd0d74d4dd79bf2d2fb12f9780834d6bb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: not all arguments are implemented comparing to pandas\u0027 for now. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":3907}}}],"partialFingerprints":{"codehealthFindingId/v1":"014b6324264073c00f1b284dcdf4c47759a0adfebd3a7cfe23ce9cf6fdaf6892"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027q\u0027 accepts list like type \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":703}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc3dd3cde78cbf9e2cbe95dd86a3fb1ede9d74024637478b748f95759f407585"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: sync the doc. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":842}}}],"partialFingerprints":{"codehealthFindingId/v1":"67340318c0831c51b309404a4ddc18673257aa586cb513eb8ffc23a0f13c8bd8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: sync the doc. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":977}}}],"partialFingerprints":{"codehealthFindingId/v1":"735b2275d85d01d0a3e532eaf4cdcefd6d3aadde9315d209afb8728e5b377b5f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: 1, \u0027n\u0027 accepts list and slice; 2, implement \u0027dropna\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1120}}}],"partialFingerprints":{"codehealthFindingId/v1":"79cd8ec6d99c37488ef8838fd4aa4102b3654a5b35d80020adcb993aa7f7a7fe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: skipna should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1386}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f633f723ef8587578bfa4bf2796d368bec61550f637cac04dedcd1ad753b58"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: groupby multiply columns should be implemented. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":1428}}}],"partialFingerprints":{"codehealthFindingId/v1":"81e7207450bc48184c3f9756e918c55817cab6d8205aa4d07900e21b41b9c848"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: implement \u0027dropna\u0027 parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":2194}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b0064f47544fed74a18d5ebfde1fc2317faf796660cd02a9b66f03db829941b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Implement \u0027percentiles\u0027, \u0027include\u0027, and \u0027exclude\u0027 arguments. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4010}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe80e7ec1996195421aa40386e90c929b6e094831fdb99de4256703ebed20a14"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Add \u0060\u0060DataFrame.select_dtypes\u0060\u0060 to See Also when \u0027include\u0027 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4011}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ab6d9fc64300fc33dab69539cb2c4e1fe808bbec85077c79e93336e45269292"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add keep parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4673}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd8b8d080e1de0894d7324b88745977940b1aecd69dff1e22db126c624348e89"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add keep parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4755}}}],"partialFingerprints":{"codehealthFindingId/v1":"f86cf640d40b8545450f5fa41ac7704f747753a1d3a02073f8a64b13ef6b3879"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add bins, normalize parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/groupby.py"},"region":{"startLine":4840}}}],"partialFingerprints":{"codehealthFindingId/v1":"48d53f00da98f0cfea5ad53b020ef44de4cc50f01ff3ace089368ab83dbb52ea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-42965): For some reason, the metadata of StructField is different"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":779}}}],"partialFingerprints":{"codehealthFindingId/v1":"2823ae03b1885b4ddd554a49be61e0d22f30ba7588462bf58c61ee27fe0e95a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-42965): For some reason, the metadata of StructField is different"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/internal.py"},"region":{"startLine":807}}}],"partialFingerprints":{"codehealthFindingId/v1":"49e6c4b35e32f01bcac0d60b9e947c2498f70a4b75e35d45680a9100ab5dfae2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: do something smarter, for example when there is a sklearn.Classifier (it should \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/mlflow.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"2654ade8f65520e2a8a8321b7721d78379c40cecc5a487209f318f7adef1ffb2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0060coerce_float\u0060 and \u0027parse_dates\u0027 parameters \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1422}}}],"partialFingerprints":{"codehealthFindingId/v1":"a57fe3dc48739c24c759b3fad28adea4f4b0a6c8298ce0bcac8266a5a3c5afb5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0060coerce_float\u0060, \u0060params\u0060, and \u0027parse_dates\u0027 parameters \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1493}}}],"partialFingerprints":{"codehealthFindingId/v1":"724c10a4d63e64f997aae83b9ea5e3d2e0489fc83b0017c95dcb50e230aa8bbc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0060coerce_float\u0060, \u0060params\u0060, and \u0027parse_dates\u0027 parameters \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1548}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3872ebd48b8f5fe81e2db2568bcbc3b9333c2d26e6b62cf4aadb5ac139e79f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: identify the table name or not more precisely. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":1603}}}],"partialFingerprints":{"codehealthFindingId/v1":"706f815f4a8ef748850f0ac94c8cc8d0d53e7e2a684e3c3dd868e5b05f35e761"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: there are many parameters to implement and support. See pandas\u0027s pd.concat. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2379}}}],"partialFingerprints":{"codehealthFindingId/v1":"8350b2269d50a4a8bf0db45226820d97fa5c9e95ba99bf07e503c397658d4154"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support dict \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2531}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f62939ac070dce02ca59bbee4db3eabe7d4650dc0f277d34fb27e643ab15141"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: # FIXME: better ordering \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2714}}}],"partialFingerprints":{"codehealthFindingId/v1":"91807bdc4c457670b555316a19c0fe11a370e5127b7de11ac92a8143410930de"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: # FIXME: better ordering \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2727}}}],"partialFingerprints":{"codehealthFindingId/v1":"c885fb70aa545cb6d24293f976eedfe434c80cfe4e3849a154fb9a0d84c31df2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: NaN and None difference for missing values. pandas seems to be filling NaN. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2734}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec0844cbfc6adb744d35881357511b74e1bc75c733abd7fed20ff486f624cefc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Add back: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2888}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0fee6c55fbf3ebc3e1ac172c535431c14296ae39bbda60dae5e0c9f0eead6d9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Add back: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/namespace.py"},"region":{"startLine":2962}}}],"partialFingerprints":{"codehealthFindingId/v1":"2862ca9a72183d2de516252415ac529cb5389d88448386d83b21c80f0b0aa612"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Support ps.Series \u0060\u0060arg\u0060\u0060 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":1124}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c379c3ebc817096e2f3e9f43f325f9f6c770124d830ec627eaa410dff800520"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Currently, changing index labels taking dictionary/Series is not supported. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":1267}}}],"partialFingerprints":{"codehealthFindingId/v1":"f59355febd922bc2def243884e511abc56aa325f40623cba43b27d145f3669d9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: last two examples from pandas produce different results. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2477}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbad2dc67bc74bf42e681b7b3aef8910330c2f5bfa82afe091a4c97526e5a76e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Categorical type isn\u0027t supported (due to PySpark\u0027s limitation) and \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":2932}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c4947067a91399bc9d530d4aa5801ebf2b8d4f3c1ca88a4ec2c5b395702cbff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027interpolation\u0027 parameter. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":4116}}}],"partialFingerprints":{"codehealthFindingId/v1":"282a177056548da7ccd65e9af0d2d885a8900beb2c52ad30452d6580c4279774"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: introduce \u0027in_place\u0027; fully support \u0027regex\u0027 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":5087}}}],"partialFingerprints":{"codehealthFindingId/v1":"82f6a6521b3664a920a4d75cc92af48168d6f2e3a5dbbc9c483d14a7dcd55c9c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-40553): 1, support array-like \u0027value\u0027; 2, add parameter \u0027sorter\u0027"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/series.py"},"region":{"startLine":6900}}}],"partialFingerprints":{"codehealthFindingId/v1":"a97a5fa0aaf4f234433a1691fb41da63262d07d2df0592fa2406be5bad042728"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Take into account that this function can create links incorrectly \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/supported_api_gen.py"},"region":{"startLine":400}}}],"partialFingerprints":{"codehealthFindingId/v1":"99551d6fa4721e4c02a7674f44f47bd0913ce7736521cf09f29e90fd6267bec5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0027min_periods\u0027 is not equivalent in pandas because it does not count NA as \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"c03758cf0f7e41d172940516675ec7f53a1817862c25aaa83e6d9c485564e4e3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: when add \u0027axis\u0027 parameter, should add to here too. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":1644}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9e47792419290dcdd3de2446f636fa9abc95dd14766186f0bc3d41ba1969d25"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: when add \u0027adjust\u0027 parameter, should add to here too. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":2912}}}],"partialFingerprints":{"codehealthFindingId/v1":"042a148155395a65079f89870f48066a956072bec624d6242d4924cbf10cd367"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: when add \u0027adjust\u0027 parameter, should add to here too. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/window.py"},"region":{"startLine":3023}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a028e89d46f1c7b257d21c21fe2dff1bcc13ab5154a298af4a6b8650002e950"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: considering the precision \u0026 scale for decimal type. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4091c6ff8eb0ecaa84964df96d4c4846791c820a8a64e18d986489262ea2996"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: once pandas exposes a typing module like numpy.typing, we should deprecate \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":719}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b13e2cb598234f8d4ebdcf7f4d1d94a1bbd486269449bb4885160ce673fb235"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Remove this variadic-generic hack by tuple once ww drop Python up to 3.9. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/typedef/typehints.py"},"region":{"startLine":745}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a08ca9bed3719ec3e44d34921be56f48eb501b1e78bbd325b62a7753c2c8604"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: The return type is still category. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/test_categorical.py"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"075933dfccce5d4518574ba1c3e98246cf3bab3ade7eae76699443ef4e6b81a0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: grouping by a categorical type sometimes preserves unused categories. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/test_categorical.py"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"727a92c8976dcf580e3534c3a6e25608ba8ee15e1111af2ed7551073c5679707"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: pdf.columns.names = [\u0022ABC\u0022] \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/test_namespace.py"},"region":{"startLine":342}}}],"partialFingerprints":{"codehealthFindingId/v1":"011ad1bf6f1fdd51fbd8f4bb79e14e1c5c38c9dad3e32078779121102a4f1ebd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Placeholder \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/test_spark_functions.py"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e51888785abba3b83b1999728e5461692c44558b5b9401041a9ab4695f242ed"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u0060std\u0060 now raise error in pandas 1.0.0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/window/test_groupby_rolling_adv.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5edf3b958d9cf242de456166c7918bb2b1f01481b11ec8a37f992879ddbfdc6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43432): Fix \u0060min_periods\u0060 for Rolling.count() to work same as pandas"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/window/test_groupby_rolling_count.py"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"eba86bff3e126f0317aee203e3dcbf6f117374b3d7622acb49d7fbf44fee08d0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43432): Fix \u0060min_periods\u0060 for Rolling.count() to work same as pandas"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/window/test_rolling_count.py"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f1708dd6676d4b6f7f9c32d907ee46367f38f6039fe8e85bce3fea7479239ce"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-43432): Fix \u0060min_periods\u0060 for Rolling.count() to work same as pandas"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/diff_frames_ops/test_groupby_rolling_count.py"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6f009a07625d6b7d14460235cb67578ee27eed772012a387627bc83e9ed8dea"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: # FIXME: MultiIndex.value_counts returns wrong indices. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/series/test_stat.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"df46672cafe0abf28949a57fb1c37baf478c18887d2ca4649073d254113d2391"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: # FIXME: MultiIndex.value_counts returns wrong indices. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/series/test_stat.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"f83aad75bc4a0581e92189849d4dbeab481ebce88af055faec5140c3f4c2e75b"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: # FIXME: MultiIndex.value_counts returns wrong indices. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/series/test_stat.py"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"c685f72f454f03784afd3f9b2bfdd0572f782e2e7f3fef971a8babce7c5cd4cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Fix the Series names \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/series/test_string_ops_basic.py"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"6054cbdcef66d42b6e1d2ba20b38a264a984059b504b2d2474fcec77750f59e3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Due to implementation difference, the output is different comparing \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_frame_plot_matplotlib.py"},"region":{"startLine":446}}}],"partialFingerprints":{"codehealthFindingId/v1":"0507c01c7a5f2ccb1eef93a1038ec1625477569e4a98506fa086d10755a4e559"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Due to implementation difference, the output is different comparing \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_series_plot_matplotlib.py"},"region":{"startLine":355}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ffa921eb9e31d56d3c84458a7fd0159522c372357164454d86350babef561df"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support multi-index columns \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_frame_plot_plotly.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"17d1a1f12905fd266663d9655aa38d223125e638efb23977299f75c1d09b1573"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support multi-index columns \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_series_plot_plotly.py"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ab7d6e1ea7128541b09829aade376079094275ee2a281b1fae29710330b1c17"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support multi-index \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_frame_plot_plotly.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bba3e471b5ad38d05e59aad597b8eb1bf88b6d6b29275bac2a7c6e6c8d27851"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support multi-index \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/plot/test_series_plot_plotly.py"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b5b72d69acd25d2200415c7c10b331aa35cc08e611ffd97948384092372b9d3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: append non-categorical or categorical with a different category \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_category.py"},"region":{"startLine":207}}}],"partialFingerprints":{"codehealthFindingId/v1":"37a65e562f8c34bb24da890bb667c28c91773d63362e7c42c03bffcacb0fd7dd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: union non-categorical or categorical with a different category \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_category.py"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"50236cfd849d6814b585aff30175fdac71d186f4b120d2a8c6b458f4400c510f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: intersection non-categorical or categorical with a different category \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_category.py"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"f97519c22bacc052c84d4a0995d2738f9cb891bd29881cfc553c8ecac6ddc2ef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011-01-02\u0027], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"edb1ddb2fa00771037e8f2f06b7a16c01c1a8d3ff021eb4b313260c66a5e685c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011-01-02\u0027], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb0dcf3e09991d71c4e2711a0949c946814470396cad498dd8d3234b3c15a902"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?:                psdf[\u00272011-01-02\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":270}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0262a3d2bbf65f91984341de399b493fe65d05d30cf774e5a1ffc1c64e8af65"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?:                psdf[\u00272011-01-02\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ac7f8ec86b0ac01cbfce112c5a19f9d5591065d5b5ad37abb729f32c4fc0015"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011-01\u0027], psdf[\u00272011-01\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"669229ca98295b659103337e5170fd2cbb5392bffabf914d86c1698379e1e5b6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011-01\u0027], psdf[\u00272011-01\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"f818ec85e0e38a2e0a122da831e61509184406b53ad55b2b37bce1101feaff01"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011\u0027], psdf[\u00272011\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"4381ea3b7079302c7a6ef314fe5aaaebd1169ccfb87a6a4b6eef00d7a0dd244d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf[\u00272011\u0027], psdf[\u00272011\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_adv.py"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"a786bd84a1bf17094ff455060de32d2b3dc89ad69b7db5f33605c5093f62219c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[3, 4, 1, 8]], pdf.loc[[3, 4, 1, 8]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"4324b7c6dc4fe47a9690660a256dc98ab434c09cfc864a0b8590ec61e88b5af6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[3, 4, 1, 9]], pdf.loc[[3, 4, 1, 9]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"f031ddfd519577f4d4bdf197514ac40c977ccc6c17c9f4578a83b26fb0861539"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[np.array([3, 4, 1, 9])], pdf.loc[np.array([3, 4, 1, 9])]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3fd4a5057ff3c1fe3b3a6e4e7947880e40a93930dd419ce651c03fdc2491cfa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.a.loc[[3, 4, 1, 8]], pdf.a.loc[[3, 4, 1, 8]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"187f9b977e658a483a94682453a6589d5893c82f0a79901087aa8c4975e7621a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.a.loc[[3, 4, 1, 9]], pdf.a.loc[[3, 4, 1, 9]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"d73c759a7d976498245fa0a15544f0ec289099b6ce893ea615331af17f0eb523"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.a.loc[np.array([3, 4, 1, 9])], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"79fdab709741810adf30c0c33c1fa87e41907b9a4ed1302aa2724fbe6d7332d9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.loc[\u00272011-01-02\u0027], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c872aaaa1975171b794e6f0a4dbd4bd6f8adc8f2bff7fc00b44a2d98b6cc2a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?:                psdf.loc[\u00272011-01-02\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"222f8dd6cba345163e47bb6b828dd130552be0b06ad9068cde0a003348514a41"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.A.loc[\u00272011-01-02\u0027], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6c3042407f9822cda34c408f3cfcc7174a618089bf2797753a81daad8f7804f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?:                psdf.A.loc[\u00272011-01-02\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"136785a43248bd4be661c52d8f18be33cd75ca35651514a752536111573d677a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.loc[\u00272011-01\u0027], psdf.loc[\u00272011-01\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"b66d4c1a7ca5a6dbd44b05ab1bc655dde1020882da18923ce332cd04b0befdc3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.loc[\u00272011\u0027], psdf.loc[\u00272011\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"2001ae17de9c494570fac877831dca29b2b49369b263f02be3256b06a293e692"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.B.loc[\u00272011-01\u0027], psdf.B.loc[\u00272011-01\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":236}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8b81d7a6b224eb913650b08686ea4a3cd11ce85887db0a483be1c8b58b77fa1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(pdf.B.loc[\u00272011\u0027], psdf.B.loc[\u00272011\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc.py"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a5e6e1d963d16c027518a4a6667af23d798ec07a98bce045355335fa52e0168"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[3, 4, 3], [\u0027a\u0027]], pdf.loc[[3, 4, 3], [\u0027a\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"e05ff52e66409d4983085977f4b21b6a10257079a845419fab22d1536af140d6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[\u0027t\u0027, \u0027b\u0027], [\u0027A\u0027]], pdf.loc[[\u0027t\u0027, \u0027b\u0027], [\u0027A\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"946b868cebfdf56d5081d589c3d7ada6fda234f7b80b47d0c06266e248a55afd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[\u0027r\u0027, \u0027r\u0027, \u0027c\u0027, \u0027g\u0027, \u0027h\u0027], [\u0027A\u0027]], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0b4f4bfa5ae1372d6a23623fd277eec534518924fe5bb08a08d580a75cd2ecf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?:                pdf.loc[[\u0027r\u0027, \u0027r\u0027, \u0027c\u0027, \u0027g\u0027, \u0027h\u0027], [\u0027A\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1d46d5188c927a35874efcea5ef207bae2cde84095eb1a740320f167cdf3b7b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[\u0027a\u0027], \u0027A\u0027], pdf.loc[[\u0027a\u0027], \u0027A\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"8adfb68ccfc71c98e5feceb02d268fc5d3c1b9e2bc7d728d5f12b725b30e17cd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[[\u0027a\u0027], [\u0027A\u0027]], pdf.loc[[\u0027a\u0027], [\u0027A\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"d68b002f63fef954cb7ea2b183209a564936bc9fa2174a15a3f44238cee0deb9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027A\u0027], pdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027A\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"95da6a677287c68e875319b33d7580975cad951570ad887ff599be29658c5d36"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027a\u0027:\u0027o\u0027, [\u0027A\u0027]], pdf.loc[\u0027a\u0027:\u0027o\u0027, [\u0027A\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8518cd3422c804cd75cab42a821be2572032b67f9fa430438944742707796b9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027B\u0027:\u0027D\u0027], pdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027B\u0027:\u0027D\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6fa1023c35197fd30211f407052dbe5cc837c6fbbf6f214d81d255a03de4f04"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027B\u0027:\u0027D\u0027], pdf.loc[\u0027a\u0027:\u0027o\u0027, \u0027B\u0027:\u0027D\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":222}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcbf91559ee96f4c196a3f6afbcfdaee0186e03a411f9d807047f3ebc4598d43"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027j\u0027:\u0027q\u0027, \u0027B\u0027:\u0027A\u0027], pdf.loc[\u0027j\u0027:\u0027q\u0027, \u0027B\u0027:\u0027A\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"477990d3566b2889cee3bc302cd0982483b077011dec1e46c9f22b25f6573824"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[\u0027j\u0027:\u0027q\u0027, \u0027B\u0027:\u0027A\u0027], pdf.loc[\u0027j\u0027:\u0027q\u0027, \u0027B\u0027:\u0027A\u0027]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"56845aca729a703545d32228b3d738a598e74d58d494e651d6d956abcfd3ab93"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: self.assert_eq(psdf.loc[psdf.B \u003E 0, [\u0027A\u0027, \u0027C\u0027]], pdf.loc[pdf.B \u003E 0, [\u0027A\u0027, \u0027C\u0027]]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_2d.py"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"639437559ffef4d0de8e125e0819e5ed2219a2341e8b0937703da75acea31af1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: self.assert_eq(psdf.loc[(5, 3)], pdf.loc[(5, 3)]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_multi_idx.py"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3d7e0c8ef3befa3bf2df9a64f9367008d22c5d486c8b7906d5552786e75f395"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: self.assert_eq(psdf.loc[(9, 0)], pdf.loc[(9, 0)]) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/indexes/test_indexing_loc_multi_idx.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"a93bd6319813a6731e21a23eee01c6cc9c9bcd3f53add0b4bbcf122c00d72d87"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: a pandas bug? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/groupby/test_index.py"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1ee4dd41be7f44e8e2df2ad12d340b10263a357d1f7744184766c3eea980a34"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-45228): Enabling string type columns for \u0060test_split_apply_combine_on_series\u0060"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/groupby/test_split_apply.py"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"dab835bd63a5a23ffcf1d0af8a07fcf72d7ed1e6f2bf6926b9499ac81ad7c90d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: All statistical functions should leverage this utility \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/groupby/test_stat.py"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a8d102a5f074b7e0012df2cde3db46a6e4acf2ed5360af70e7132ba91ac1d6b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-45228): Update \u0060test_axis_on_dataframe\u0060 when Pandas regression is fixed"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/frame/test_axis.py"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"66c51b422eec2a1d276ab6a9881062f273c1c76cd6448ad7b3bf3be86c73a698"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: what if with random index? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/frame/test_reshaping.py"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"001db57c9e4c18c532cd4c336333eb2ee2a66357e4c248db75197a5552a457cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: ([psdf1, psdf2.C], [pdf1, pdf2.C]), \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/diff_frames_ops/test_concat_inner.py"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5cf60932d475eadff004ded9ac425ccfb31fb61b92b09de415ce557586eb195"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: decide if to follow pser % False \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/data_type_ops/test_num_mul_div.py"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"89b478886083d044da8aad24d7023a204ac8b73f4adf48e7b6bcaf73eefcd838"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: match non-ansi behavior with pandas \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/data_type_ops/test_num_ops.py"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"11da2cc9f9a716d8698073c7f9a0d120e57042bd0c1bf0f37f060c4ef41d2033"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO?: fix column order \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_apply_func.py"},"region":{"startLine":496}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e08b8a1f8a8b7f2f4a818d78d56f90a94a5b1d87acbf6dc93f5b0684a31a928"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: when both left_index=True and right_index=True with multi-index \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_combine.py"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cbf1d4181314e849d092bb4c54ea3dec869c69c75753550ad03219426d3d72a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: when both left_index=True and right_index=True with multi-index columns \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_combine.py"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b108daf55fb7c0243344cb66bc02a7e17db1287b4e44cdea825fb4ac7612614"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # Todo: self.assert_eq(psdf.pivot_table(columns=\u0022a\u0022, values=\u0022b\u0022).dtypes, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_pivot.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"abeb573510e7ee7594b1decebc83ad63f3203bcd06656ab48c545c41b8fe4b48"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # Todo: self.assert_eq(psdf.pivot_table(index=[\u0027c\u0027], columns=\u0022a\u0022, values=\u0022b\u0022).dtypes, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_pivot.py"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"116f09c69c14a93430203c25c10b109ccb6941a806ef1f5efa7de593e08fc770"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # Todo: self.assert_eq(psdf.pivot_table(index=[\u0027e\u0027, \u0027c\u0027], columns=\u0022a\u0022, values=\u0022b\u0022).dtypes, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_pivot.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"92bbda7548145bf42fa3a554792eca6a08a0534809cc4a10d2841b7764e3131e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # Todo: self.assert_eq(psdf.pivot_table(index=[\u0027e\u0027, \u0027c\u0027], \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_pivot.py"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"c094f01a3f69d04d7891dd5267bfd9cd513e517e877c642bcf72c22df0154f14"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-35555): track and match the behavior of quantile to pandas\u0027"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/tests/computation/test_stats.py"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"41c88d39079ae1465d29252b1d92be5de32e03799b46c36336e0ad0401c80e6f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: this logic is similar to KdePlot. Might have to deduplicate it. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"892bd9491ec110c25d723f95da0021c60f4a2588e85d6189753019afd102e55a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: check if value of y is plottable \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/matplotlib.py"},"region":{"startLine":969}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fecfb341fce53462f08795c5caf8c852da7a721f91ef5abfded75bf0f90cf68"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add downcast parameter for fillna function \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"1178ec83bc854b4d678ac4a393cf81617ae70bbc8fef97c45d8ffe0fab0e936f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add error parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":1214}}}],"partialFingerprints":{"codehealthFindingId/v1":"47c17b51f6414056f3cfaac16c0b5fcae6e9076e645e18a6ea2c51cfb0d2aad9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: non-categorical or categorical with different categories \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2269}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c7a58ebda8accf4332d36a0e3b97161db56dfd4f16f347a2b85624eec546585"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: We can\u0027t support different type of values in a single column for now. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":2330}}}],"partialFingerprints":{"codehealthFindingId/v1":"9562659f23e4df05d1cde5ec43fc17782bf95c78c5c7baade4b62efeb2509696"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: We might need to handle internal state change. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":692}}}],"partialFingerprints":{"codehealthFindingId/v1":"35fc63db94675ef6b530372ade50a45f466e31f3b9bb7a0fc6b176baff176a79"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add \u0027name\u0027 parameter after pd.MultiIndex.name is implemented \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":706}}}],"partialFingerprints":{"codehealthFindingId/v1":"ece82c12f5b2dd50296c78025c25e5f0a6b241c3322b56cf5a8ee15320e9220c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: ADD error parameter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/multi.py"},"region":{"startLine":836}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b7ee107e88243a9d3bf6a1549bb0a2b595d4241bb639ffe636be0a1590ba869"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack for support float(\u0027inf\u0027) in Py4j \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/common.py"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"5acde156a44c73ff9cb47490b030a62cdd69385d7d74d95e208b2cd5451dfa83"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack for support float(\u0027inf\u0027) in Py4j \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b0231f0ed17578f8b5cc2a5eeda5000475c25449b9b8e7554fffbaaa3430941"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Allow small numeric difference. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/tests/test_algorithms.py"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"29b544a0037e951d4a4611e244f61eaee9ae88d3a4564ddcee546d1c499e22f6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: More efficient implementation: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/__init__.py"},"region":{"startLine":1545}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc82cfa3648f15b892609d30a6b01165b24e12a5be78da8b3b2748f3eb529fb8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: More efficient implementation: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1328}}}],"partialFingerprints":{"codehealthFindingId/v1":"b53897e04d12f25670c12bb0c43b7a7f4ecc2ea7b844539b657895891343fc68"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: need to set metadata \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":3906}}}],"partialFingerprints":{"codehealthFindingId/v1":"290ea2a3562671c9860f3d841a97a4407c6bd7d496b6ed808e7cf7ff30e1998b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: adjust return type hint when Iterator[Union[pd.Series, pd.DataFrame]] is supported \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/functions.py"},"region":{"startLine":776}}}],"partialFingerprints":{"codehealthFindingId/v1":"6583a8e9f7ea58d7f3c95e13661da870c477be505c123b77febf196fa8a9b841"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: duplicate evaluator to take extra params from input \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tuning.py"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"04eb1c745b6468004c226fb55d9305dfc1face5363a8ca83603c2ee25e452a12"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: We need to handle \u0060RFormulaModel.pipelineModel\u0060 here after Pyspark RFormulaModel \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":1158}}}],"partialFingerprints":{"codehealthFindingId/v1":"f878685d845cfba8bc64b71fc9edccb7d529e0a9868effb957dd536cddd89274"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: we can optimize this further by directly extracting \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/data.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"99ca6b78c1d58375187803007522d89bf7cf7f4648cce66448ea82d3cdb96e7f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-41589): will move the functions and tests to an external file"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"378aba0fc2f2ed1511d8db86faf2e3c838900f3521fdbfc09982f616d1298b59"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: need to do this in a safe way to avoid issues during concurrent runs \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":987}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa93d49343ffe32975fcf45df578eece94d17b2b496e72aaf2e64e1d4a3a1e79"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/log_communication.py"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"8430cd766d1f239ba593874a6f0efca133818b44cd806458b6130e6254652ec7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":473}}}],"partialFingerprints":{"codehealthFindingId/v1":"61f6024622fc7e9c41333993d9804d23ac9183c3864ce22669f507e9f38d216d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-41775): Cleanup temp files"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/torch_run_process_wrapper.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cffb26fdf21e40e344acb03b5fd10481caf8fc16335eea9da5b36a48daae37a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/tests/test_data_loader.py"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac3f92c24a5d2c8827433d7f696d75b26c6b4c8d0bbc4febfd6254548e76850e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/tests/test_distributor.py"},"region":{"startLine":568}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a5d95e0f183bb9ffefbdacc3d4a9cb9c2f77ae654dc3e92430450939fdbce41"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/tests/test_distributor.py"},"region":{"startLine":592}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2b63670bf8e5505b7e7c16d04bc412944aa12090b79216ee758396d3ca4a8e5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/tests/test_distributor.py"},"region":{"startLine":665}}}],"partialFingerprints":{"codehealthFindingId/v1":"633ef8a1e532e2c21a11271737f6590e583fb6869f0f5290ceb719bd3c3f8741"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tests/connect/test_parity_torch_data_loader.py"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"100f2c198e53fc9159eca6ceeff649d64d5cd815ee3442a98540bd5f3bddbdad"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tests/connect/test_parity_torch_distributor.py"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3161578a649a36dc430ffea9e2dfdb93df79b44009549de0035e538198941fc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tests/connect/test_parity_torch_distributor.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a2b4a93c8cb9c225192ff22aa322060f31698188152958168e885980d37e9dc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50864): Re-enable this test after fixing the slowness"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tests/connect/test_parity_torch_distributor.py"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd1c20c121c04e359998e9093869d3ef2fb7d53344bd87be93704373f127b336"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-50843): Support access submodel in TreeEnsembleModel"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/tests/test_classification.py"},"region":{"startLine":708}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2322d6bf81729b9a0536037ff94561271f12dde1eac9435d4e8b16581d05400"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: How to correctly inherit instance attributes? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/param/_shared_params_code_gen.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"051cbb019344ac24c6945ca2643ea1c566ca9dfd837a67be299df4ba81a34321"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: swap out with better test function \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/deepspeed/tests/test_deepspeed_distributor.py"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a406a9885f4c11684a1a68ab30b272b2d8d3ab5cd7ca2586fb0013f98f491b5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: change to better test script \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/deepspeed/tests/test_deepspeed_distributor.py"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5ef8396cd197f6570f909bbfceaf02c0e4adc48bcae42f587354afd5c15128d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add a setting seed param. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9f3b6ac659616b60b38a7df6913d36b75e1ad3217b8812aa80b56eab39be649"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support training on GPU \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"71ba2fa62620640ef11954b1c7f2badebe4541a7231b775a14e087c648612619"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support L1 / L2 regularization \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"276de1cdd71d3505c4f8240f5b27afee26e28cdaa77664d5d192c4858b8fb6b9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: early stopping \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e444c08ef46e22bf5c4c04eb94ba2090177b6b05dac82c392e771a2c4e1dedc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support pandas dataframe fitting \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"c242ba6e7c16c14e7ced39278a1500900bf027137d32163efba3ae23f110a356"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support pandas dataframe fitting \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/tuning.py"},"region":{"startLine":410}}}],"partialFingerprints":{"codehealthFindingId/v1":"db8f031e65c05fd01151116b76e22e63c607c81e34455a50a82303a6c8eb71af"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support GPU. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b7e68db41554bd009d326b360c84b7c9cfe75f4019b2c40e3d55f803278c727"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Use spark broadast for \u0060model_state_dict\u0060, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/classification.py"},"region":{"startLine":343}}}],"partialFingerprints":{"codehealthFindingId/v1":"13d9d8d89f2c1c4ec6e9aeeb545681717251265d0e0c4f976388589a6de26107"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: The type design of RemoteMLWriter is not very good. In saveInstance, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/readwrite.py"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0225f8e4ee043d91d7433739660c0a8c9c2a721187dc77e7b8e8cfb789963a1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-49100): add verification that elements in result_iter are"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":723}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b8802810eb0f26bf3ea1bc1d81dc1edc590e503497d57d1d1cd427f38bb6ded"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-XXXXX): add verification that elements in result_rows \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":839}}}],"partialFingerprints":{"codehealthFindingId/v1":"aec3c0aabaa673df4f0dafb50495bc81ee83a8bb8e5492e39155ea03ae6a8481"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-XXXXX): add verification that elements in result_rows \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":1017}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e3dfaf85a2ca36c8eb837309f96864dee0dbb11b52fb2e8a0e56763a1c8909c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: we need to make this configurable, currently using default values. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":843}}}],"partialFingerprints":{"codehealthFindingId/v1":"88d7fd9eff90a45d45dab4a606fabe7f16a62c2680c130ac41c2e1f91fc59bcc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: we need to make this configurable, currently using default values. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_stateful.py"},"region":{"startLine":1021}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4a922ba5a1cb859e27899b35427a4fe56fb1f61a295595bba820bc6f498ffc8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: This check is only necessary for the first boundary in each batch. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_udtf.py"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"16b9122f3eee018f01aa1d32989acf7d4a6223be7d466cf8ce1d7440ed552c4d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add log warning for when more than one iteration was run \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":1053}}}],"partialFingerprints":{"codehealthFindingId/v1":"52cd2ccb5b0f53a172755c42475dbd757649a379788d50b31ee2fa8d89e666e4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add option to control map-side combining \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":3669}}}],"partialFingerprints":{"codehealthFindingId/v1":"acccde067f5d3f638e2eb6493ab960ce93b5bffb123d26ec78b19e838c56550f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add control over map-side aggregation \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":3766}}}],"partialFingerprints":{"codehealthFindingId/v1":"fee6e354190568cde9ed21bff58b09ff7c7215065540b5390091784348811b5f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: support variant with custom partitioner \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":3974}}}],"partialFingerprints":{"codehealthFindingId/v1":"04444d46e52c8ba64c4b3d4bf3c69d03a8b21da6db5430b0e1c83fa5f5850fbf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add variant with custom partitioner \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/rdd.py"},"region":{"startLine":4192}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc8ea5a7c969cdba8eaf1fd412006a2aa6d2843e1e978de00d77332c51047d43"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: fetch them in batch for better performance \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/status.py"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"5adb629fa955746f93affb76bd9659bd7584d505aa339fa252db37f38b2ee17f"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack to circumvent non-predictable memoization caused by string interning. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"d853be452f9f5718772467d99369e29eba6d915b8aff2e8b824971a04d58aecc"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack to circumvent non-predictable memoization caused by string interning. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":715}}}],"partialFingerprints":{"codehealthFindingId/v1":"73a6b990aaeee781ec7d9e7d60d953802ecfb917d7edd371c8f4e94f71eabc2e"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack to circumvent non-predictable memoization caused by string interning. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":744}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7847719a268902d7da29ed314a819cca35afdca02f9c839c22fa24995866c12"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: # Hack to circumvent non-predictable memoization caused by string interning. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":834}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c1e450936349a379414ecb9de0263293a6893874269e3d4bc074cdfd1099640"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: decorrelate reducer_override (which is tied to CPython\u0027s \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":1349}}}],"partialFingerprints":{"codehealthFindingId/v1":"175e1e0f2a86b7fbe532302439ac7577384ee60988f95b7347c0879522729697"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(SPARK-32837) leverage pip\u0027s custom options"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/packaging/classic/setup.py"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"30da96ae2d9d00bcb7924fb5537d1b0c757e69f269ecddb716d0b88aa798c537"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: move this to its upstream project. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"project/SparkBuild.scala"},"region":{"startLine":540}}}],"partialFingerprints":{"codehealthFindingId/v1":"efa5fe3a321c6280ba092f938d3ae8e315081697f6691d2e24d82e11d3b38c30"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack: this variable is used to control whether to build docker images. It\u0027s updated by \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"project/SparkBuild.scala"},"region":{"startLine":1239}}}],"partialFingerprints":{"codehealthFindingId/v1":"440dd61a1bf813675f23031352fa10973bc592980a8162fadc32fdf272f19eff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add more tests \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/mllib/feature/Word2VecSuite.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5e56364bfd637edd8c8796c33031f1a18bf3121b9ed240f13913715133fb8bc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: GaussianMixtureModel should implement equals/hashcode directly. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"44f48c1cae429b58d3d7924a66e4cd4e59f65ed2cf56e3cafec9b15ce7fe50f1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove requirement to coalesce by supporting multiple reads. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/libsvm/LibSVMRelationSuite.scala"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"27ec79c0f18bcda096e9fa19c7b2c377bef40b967717482d97a0ae94ffe8c69a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40171): Re-enable the following flaky test case after being fixed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"b010bb8ca3a2721617da5a4181d282a312e6c5281d0081c0815ad840376bb6d5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40171): Re-enable the following flaky test case after being fixed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"6be8b476fd64ddb057f0e73fdc0d23d2bf376fc444745723704fe7ec9082a360"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-40171): Re-enable the following flaky test case after being fixed."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"77289785066893d268ec57ce1c56be0c54b65dc88a1b2da28e75d0e2c05d855b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Reinstate test once runWithValidation is implemented  SPARK-7132"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/regression/GBTRegressorSuite.scala"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e8423bc7088527a52b5c942764611bef3ed8278d5007fe469f3f0fb5c921417"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Construct model directly instead of via fitting. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/regression/GeneralizedLinearRegressionSuite.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cfe93a4d3e3bbdff8839b2284334deada74d5642a8998180ac97d9216ef4be1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Use a better (rank-based?) evaluation metric for implicit feedback. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala"},"region":{"startLine":465}}}],"partialFingerprints":{"codehealthFindingId/v1":"73de223602fce4aea766f81ac6fb0bbdc7c31bca58262b2892c0ae7cd359f167"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Validate the solution. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala"},"region":{"startLine":571}}}],"partialFingerprints":{"codehealthFindingId/v1":"50d3b57925abe19f7ac145bee71e69bfc3c600576af7edb0124983a436f006f2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Check that setters return self, which needs special handling for generic types. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/param/ParamsSuite.scala"},"region":{"startLine":427}}}],"partialFingerprints":{"codehealthFindingId/v1":"2775aea579991f1a1f4d1d5d005281686d5819afe5a30f002727e549d711ad0d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Once input features marked as categorical are handled correctly, check that here. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/feature/VectorIndexerSuite.scala"},"region":{"startLine":332}}}],"partialFingerprints":{"codehealthFindingId/v1":"0804a83577f5c3d01657f5831a97a3e7cf2f7d26fadf886ce18efead77b31d94"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: need to compare the results once we fix the seed issue for LDA (SPARK-22210)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/clustering/LDASuite.scala"},"region":{"startLine":355}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ffa1f58d69ccbe32423d30cb813cd5f5a86574a48cd4f476311aa81523b7e64"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Reinstate test once runWithValidation is implemented   SPARK-7132"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/classification/GBTClassifierSuite.scala"},"region":{"startLine":298}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e48fc4e678cd32bd3be66969571d6029c9aa4313d772ee7e8e487ea3348bd33"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: test for weights comparison with Weka MLP \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/ann/ANNSuite.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"4381c34cc6e0fc8574c93151c77e034a7c742e406c8718ab0b7e78f9e77e477d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add a test for SGD \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/ann/ANNSuite.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec1e4562439fb32357ab4daafdf2012705f0307d1ed1f51118f210665569f885"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: allow to specify label precision and feature precision. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a82b891bcba8748ce92568adee1cf21958d75e3960620607458c70296a8bed8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix this issue for real. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala"},"region":{"startLine":204}}}],"partialFingerprints":{"codehealthFindingId/v1":"785fef516613261d5f77296fb6a87340d8c08ecdcb3257c82a5e5fcb7f87c205"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix this issue for real. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala"},"region":{"startLine":402}}}],"partialFingerprints":{"codehealthFindingId/v1":"aaab28c2b75921facf4bd3d2aaaca492c96e209dead2bf8884c8f7cf8e677437"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: predicted labels are \u002B1 or -1 for GBT. Need a better way to store this info. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"da4aaf342a978fba968b9ff475e07aa64159a2e22cf0f7b992404beda509443d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO remove once covariance numerical issue resolved. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/PearsonCorrelation.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"102a7006f3161d984625a1c16ffdfcccd3f515a28f7e9ab1b17bd3460d5f4847"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Apply feature scaling to the weight vector instead of input data. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"63af8b3806c85736653f3fe29fffa61fffd002eef48fa22de924274b20f52c85"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Override methods such as aggregate, which only requires one Spark job. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/rdd/SlidingRDD.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"0047a5b94fc0a6c066cb9da09d7e7d7119acfb782518c6f2faf125632b864ae2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Generate RDD[Vector] from multivariate distributions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDs.scala"},"region":{"startLine":439}}}],"partialFingerprints":{"codehealthFindingId/v1":"5aa6721bf724e9a4421ef73031903f935ec8644280382ef855dcd1b5ff72cac3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove this function and use eigs in breeze when switching breeze version \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/EigenValueDecomposition.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1686d03b443aa1be5e5652f2ee93e3548342f54dfcb38f42564fad3f8df2528"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Try to use aggregateByKey instead of reduceByKey to get rid of intermediate matrices \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c9ace6c3e2a673432200726ff607af3d8904b945ad2ea65ec0df8931581e6ae"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: find a fast and stable way for sparse data. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cfd8c9819a141dc6b7845c20e6268aa5dca4a8dac96d5b0dab978cbfca4c924"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: The conditions below are not fully tested. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b901438bd753ebd46837b3d7030c7bbc9090bbb926d81d75e26060e76959131"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support unbounded pattern length when maxPatternLength = 0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b0954264c10a8d75d4df9e3044f6b5e23a7d75f4a8283f1d56f414ccfe9a6f0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We collect projected postfixes into memory. We should also compare the performance \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"20351ff6d222039153f97990d3ca6a34d6fa77424500a95b1e9333670404ecc2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: of keeping them on shuffle files. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"d02f434a5cafc366c5790bafeff592fe435f218c57beeb4ff8135b5c02920e78"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Sparse representation might be ineffective if (newSize ~= newValues.size) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9add9cf7dd1e69e9794dcad51f7723a45f407bbf94bbe8c27fcb2148c5cbaef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Sparse representation might be ineffective if (newSize ~= newValues.size) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"1dd3c5280ad16d7fd8d2213943aea00ec21cb2405bc80f16f39deb04a4f3b01c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Sparse representation might be ineffective if (newSize ~= newValues.size) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala"},"region":{"startLine":472}}}],"partialFingerprints":{"codehealthFindingId/v1":"075e22f0daec606fd07514bf0cedb6a3f010279271d9b5992fbf9d5b2c94bcee"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Allow different IDF formulations. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ba23d12e58307d737b97fed155259f1b6943d5269419475ae66db98ad3911f3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: skip computation if both withMean and withStd are false \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb32411c4a6c5bc67b613cccd89d948d97f5e747bb9e485e9735c92aed1b9411"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use a numerically stable approach to estimate cost \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2d5338f3c2d328282ba71368da7f266638d32504005252dabc1ac4776f312ef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: computation of statistics may take seconds, so save it to KMeansModel in training \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4a4670b7b5aebfae66761ecc8d64401e6ff7743880509e43166ea60eed1868c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: declare in LDAModel and override once implemented in DistributedLDAModel \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"b867fb6bc6bb4692d3b5c5851cd29c0f75e291c466cb2c87be5be12ee6a834f3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: declare in LDAModel and override once implemented in DistributedLDAModel \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ce3c22decd08fce1e1454d593b2cefcffa6bf4e307fdbdbb194f94e85523821"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Avoid zip, which is inefficient. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":683}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc2cf8829a707be085fd77ec7e4796d0cc4c704e20169b69189ec49900c209de"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: generalize this for asymmetric (non-scalar) alpha \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":710}}}],"partialFingerprints":{"codehealthFindingId/v1":"4350330af369d9f422bd1b7eef2bbf562b935aa3d5cab63143deb3d8c6b720e1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: generalize this for asymmetric (non-scalar) alpha \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":737}}}],"partialFingerprints":{"codehealthFindingId/v1":"943a93eb5283771585dede258e8a5a67178379b476007e5583ea197dafe92a3a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala"},"region":{"startLine":809}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa64d3dac5c42567f1c64531fbd6672830d3733f4beab3c1affafc84bae45cbb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add zero/seqOp/combOp option to aggregateMessages. (SPARK-5438)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cb90691fa0784720fa774d4bdba8a789df580fb9ce0ba47f761c144cf7f2943"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Keep more values in log space, and only exponentiate when needed. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala"},"region":{"startLine":638}}}],"partialFingerprints":{"codehealthFindingId/v1":"be49a679e11c5c38872230304421521e5af486b96c2b1938f07eb8f849617202"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Support casting Array[Double] and Array[Float] to Vector when FeaturesType = Vector \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/Predictor.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"b37b9aa76166b8f66b57e4e5fb207d56d0b63eeb885e7ad7dfe1325614fb1b09"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: there is no RegressorParams, maybe add it in the future? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/DatasetUtils.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"23854caef1a02fe04c9a675ab1f1db37c1c540a1110061849d1809379d79c6f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Revert back to the original content if save is not successful. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":839}}}],"partialFingerprints":{"codehealthFindingId/v1":"565bca0f401e1fa4406d22245672f62c36e7ae7ae05aeb95605a7b345f8d74d3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Move the utility methods to SQL. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9bb9878fdc10856739ba94fbe7ca98313685815c834979cab9782199cfc4800"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: duplicate evaluator to take extra params from input \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfbce884e4df1600340d8decf839df49d2ad43e17a0f15fd2c7277a7548de935"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: duplicate evaluator to take extra params from input \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bc61b042e0525cd734ae8828542c427b38ff757a5cb64148922bd77e75d933e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add aggregate stats (once available).  This will happen after we move the DecisionTree \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"31b942054dfe388db035fb972537c32289d02481b7ba796d57976756666ec18f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Once the implementation has been moved to this API, then include sufficient \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"123169176c3b96924f6152016056a800c74ce56c9e70ac9b83a29f8469ea4f3f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: In the future, also support normalizing by tree.rootNode.impurityStats.count? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala"},"region":{"startLine":268}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed03c9383a2629f8304b09908f7d5e8f980bf2e6fa3d9c123aac8490df9473af"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: implement weighted bootstrapping \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/BaggedPoint.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6731bff2bca22c7114d39d81533280d21699fea7290c9d73168bb7ba8af0f2c"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack: If a categorical feature has only 1 category, we treat it as continuous. \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"19ad8cbd9b53065ba15e90c06cd8b5e66558ca8f5833c79acad1f0cafed1b1f8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-9957): Handle this properly by filtering out those features."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d651c92082c831384a6470db9e587dbb6639bf4d034cec39c46d7cad16ec880"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Calculate memory usage more precisely. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"e42e794f8f8727989543f502a851e4275a4f9c62e399235ff69050f42de5d34a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Use ByteBuffer to optimize \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":432}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd21f7f12135bb23c7fb543a1afea61017d669d2879b528c4ad900023e305241"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Use ByteBuffer to optimize \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"766017fc097722c0b3614ca59475de32f0ee1903b0aa5749eb529f0de0e17afa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make standardizeFeatures and standardizeLabel configurable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala"},"region":{"startLine":410}}}],"partialFingerprints":{"codehealthFindingId/v1":"7938765618fffa7bee9b90c4d81171dc0553aa301653638ebd94f519cba3974d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make standardizeFeatures and standardizeLabel configurable. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"f407362368cf3c003f458963675763267347728c8460ea5e997dbac92465e549"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: defaultEvaluator (follow-up PR) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/Regressor.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e3b8fef302e6e86332d2ec101be0fef7eefd57e496fe81cc2d7badad5d228e6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: defaultEvaluator (follow-up PR) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/Regressor.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"96bc15aea8737c6578d0d7274d5828d0ae2355f0e47dfba10b0854226fca41be"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: defaultEvaluator (follow-up PR) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"de66600d74dd7eb1be6b9b92349f1c2064369ae91f8b591031606bb90543aaec"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Generalize PeriodicGraphCheckpointer and use it here. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala"},"region":{"startLine":1098}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a471af3d275e8ffe9122453c06170712578be56e9aa871d76e9471b56fd8f70"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Support dot operator. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/AFTSurvivalRegressionWrapper.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"4737f226d9850d5004c14f8460d946b0142787b5dd1123dfc04369391620f2cb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Provide a better method name for Java users. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/params.scala"},"region":{"startLine":1062}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec380d9e3c9faf39a7fd7fc70ecb02bca73a9a55a78c98b787624a86e1f58dbf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Provide a better method name for Java users. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/params.scala"},"region":{"startLine":1071}}}],"partialFingerprints":{"codehealthFindingId/v1":"71323bd85fa76f922c783bb7a4d60b556e67aa22f8eece885cb09cf562389b34"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: more rigorous on doc \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b6dd0377bfdfcdc37d366138610ddc894f965103a9e93e0e8c8550ccedc9bc4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consolidate aggregates for summary statistics \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala"},"region":{"startLine":354}}}],"partialFingerprints":{"codehealthFindingId/v1":"005e777ea393b17164a1382b3f0586ac4e27d88fb5902d4d827296142bede1b7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Output vectors of dimension numHashFunctions in SPARK-18450"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala"},"region":{"startLine":236}}}],"partialFingerprints":{"codehealthFindingId/v1":"416da24cd558601eb3804eb325c84f9f46f9e5601e8225eb442617e6a2805ac0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Output vectors of dimension numHashFunctions in SPARK-18450"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala"},"region":{"startLine":231}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc662bed1a921c8e200a702b697cdee1c9cb15bda3a20b1099cfe227312d4cb9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Save using the existing format of Array[Vector] once SPARK-12878 is resolved."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c8fd19d3e19bd290e54eb8549145003cce48ab2dc6d10e4043c290cb33fee9d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix the MultiProbe NN Search in SPARK-18454"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/LSH.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f60ba6da400def7bfa7807140fa01542dd886a6232c794c1c4f15c1611fbaa2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove recreateCol logic once SPARK-17154 is resolved."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/LSH.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"f824578a8b4a97f69b1ad84e48e179a65d77278faf710b1fa76197b848ca7d78"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This hashDistance function requires more discussion in SPARK-18454"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"034de10302722cfb59d29be69bca3d26db246819a4891bd3d92e163a08bf3a61"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Define a rigorous naming scheme. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"971c1f2fdf84b577d47e3b0ef4ea0de07add5f64d298f830046d1726c19403a9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This might be able to handle 0\u0027s more efficiently. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8b62dc28ec25546a3e3988822c01474bd2feb672325edbf179b183aad9b6fa6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-15785 Support users supplied initial GMM."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"25165a82c50128e949377bf37bd7db55d94a9a5943287db9ec47295f1b9f4559"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Allow the user to vary the number of bins using a setBins method in \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/ClassificationSummary.scala"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe8bbd72d7323a8ab8a24fe58cfe32f42bfd4ec56771140ba92ea01a66d960fa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Implement SPARK-11543?"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"b81d0bb58c7d228b190e035a0d438afd6756b4855c1208e715f58975d8df2305"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: for Multinomial logistic regression, take numClasses into account \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":564}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0416c44fd145b58e77fcfd963f1a475d32f37880dabcc89851e715f54ffdd0d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: get numClasses and numFeatures together from dataset \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":1038}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3da4dc9fb6e904f00cda76cfa3c0ab5bcb38a0b2a5ba21dfdcf8e037c74235b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: switch to MLlib BLAS interface \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/BreezeUtil.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"fac03b70c74cde328789d6d5970cd63f38e48fa3aa367e4591a134643935e053"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add code if matrices isTranspose!!! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/BreezeUtil.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e5da4f11eaf04f8df0ca0dca745f2d9bbaf4f377beecbbd9d250a0720fcb1ed"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use Breeze UFunc \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec8acbe203c536c2e7e4a6bc72966af89c57dbdd2a1cd90c8e1dc10a0359f0ff"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use Breeze UFunc \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"84cf63e2b1af19cdca1196c7bb52cae9b677c0b5ed3e892e77b47ef61521ec8c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: squared error is more natural but converges slower \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"d455311e25f44ff9a6aa8b47c9a3dfe0c7f094509dae1269821805d5857c672e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: allocate outputs as one big array and then create BDMs from it \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"f581dd3923bfc822cd188ab3189f1c003a0b1c50268cb31fa13f8c31f3285cd2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: allocate deltas as one big array and then create BDMs from it \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":526}}}],"partialFingerprints":{"codehealthFindingId/v1":"57379cd4ad50543263d59f92f65af0cc66c2169025bd3b4b5613635208810b55"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: explain why delta of top layer is null (because it might contain loss\u002Blayer) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":537}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f70fccca3db19fe3ed313fa68188034be9f5af580480a9000504638dac0769"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: will make a copy if vector is a subvector of BDV (see Vectors code) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":846}}}],"partialFingerprints":{"codehealthFindingId/v1":"de841498a1035ffea49a2a62aae8993c1256c0fc5e786cd96c4c0a78e050c2f3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: deprecate standard optimizer because it needs Vector \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb6a366687248c6c44bfa585a588a28cd99c03f6754f0e6de3e4e9a6e3174b5d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: change to the correct directory once the assembly build is changed. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/CommandBuilderUtils.java"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"f47c06c290a9efb2f29feed8ce0e34367a947f7d4462628279a85ab053995d3a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Consider using Char. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/package.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"a24f1cb2b8a0d6f28e5e0e74815968523349af6df7444e630b3d94e82cc87b71"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use a fixed random seed \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/SVDPlusPlus.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7bf0cb1efed6a7385f7b03f2d9aaf89d2a9d5ebcc3940c100df9d508e0dbdbd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: unpersist the replicated vertices in \u0060replicatedVertexView\u0060 but leave the edges alone \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"b26e744244877b8e913e184dad048e1cb1dbafef0bf0901fb665a1f3a3771b63"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Because we only have a clustered index on the source vertex ID, we can\u0027t filter \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed85b8a46a1a326288ae3d3f85ef7de0c651902ac5227d0c620a1444d0f5bfb0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: When Python 3.13 becomes the minimum supported version, migrate \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/sparktestsupport/modules.py"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8f6e66fdaa9d1de99a88f5cc77737fa2076d63b9f6a422971a741bab62bd7fd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Update API docs to point to their own llms.txt files once available \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/create-release/generate-llms-txt.py"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e6c3a2d1317037483595730d52fde30bd05150fe3d104fe4220dced32e063ba"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(ekl) we should consider always interposing this to expose num open conns as a metric \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/DebugFilesystem.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1c724246c3c96e30f171d5ede53c21eff678f62e94b66a5097e68d8406cea12"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Need to add tests with shuffle fetch failures. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/FailureSuite.scala"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3a21f612fdc11c000f1c099eeca33c9b0cb7312ad5e149de272879eaaae70e7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use these classes to add end-to-end tests for dynamic allocation! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/HeartbeatReceiverSuite.scala"},"region":{"startLine":312}}}],"partialFingerprints":{"codehealthFindingId/v1":"d04e29a1b5a4cd1455f09e7f6f63702ee396d2593f8da0dab17dae1ea70f63e3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: If we sample 100 elements, this should always be 4176 ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5ab7296477980d1282f227a656cee27ad30071928afcd61b021cfe11895671d"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to try to ensure that both future tasks are waiting \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/storage/BlockInfoManagerSuite.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"88da19f2a75ba171ad033c6f8d4bcaef42c7da6dfe33701ebc1ecd7bd14f4bf3"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to try to ensure that both future tasks are waiting \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/storage/BlockInfoManagerSuite.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"49210e86a74e82e87cd6d1f0f3dfc644cd96fd125071748690214e233b7085d4"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to try to ensure that both future tasks are waiting \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/storage/BlockInfoManagerSuite.scala"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd5bbb60ae1a502e3fbc1d7d05848ba9adb71ab16f20c342feec558238d6d90e"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to try to ensure that both future tasks are waiting \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/storage/BlockInfoManagerSuite.scala"},"region":{"startLine":299}}}],"partialFingerprints":{"codehealthFindingId/v1":"133c804be7658fffb174dc29728af561032623096c91a65a8cb998f725417372"}},{"ruleId":"D17","level":"warning","message":{"text":"HackComment: // Hack to try to ensure that both future tasks are waiting \u2014 a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/storage/BlockInfoManagerSuite.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"93874d2d5fc06574266da38138017f2827ae5203c398df0b581f84c754fae8ca"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME: this can affect other tests (if any) after this set of tests \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/shuffle/sort/SortShuffleWriterSuite.scala"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"887623c169c2eb2189e86193ba72a2d4039dc097b98288deacb3f05814b705f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO assert this: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala"},"region":{"startLine":2637}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a3df4970a8a000cedf2cf462633cbbd19cb60ea28512a1c0534c7cb6f7e9218"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO assert this: \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala"},"region":{"startLine":2663}}}],"partialFingerprints":{"codehealthFindingId/v1":"d35d4f2c092eecfcd51a8995b5f62839705579e6a25aef8671c386e1d1739c1f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-9603): Building a package is flaky on Jenkins Maven builds."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala"},"region":{"startLine":903}}}],"partialFingerprints":{"codehealthFindingId/v1":"3124d08bd8e6639edae98a6361c99ebbe2e6e4fdb44a0ce1002cc6bab309bb0a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-25030 Create a Timer() in the mainClass submitted to SparkSubmit makes it unable to"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/BarrierCoordinator.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f4e37fb4f58511b0a06cae7f601e4a1cbcd2e97079577937f0a1fcff97c2006"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-35547: Push based shuffle is currently unsupported for Barrier stages"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/Dependency.scala"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"08fe8dfce4733a35fae7c2e6032f557dc955b9a2a4b2841f4ede562ba6d32e65"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-41192): We simply need an Int for this."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala"},"region":{"startLine":796}}}],"partialFingerprints":{"codehealthFindingId/v1":"734258a6de19af9101ffc6b82478b63e86339486141cc737a3aa38dc99abc142"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(aarondav/rxin): Check Thread.interrupted instead of context.interrupted if interrupt \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/InterruptibleIterator.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"adad81321d823c3c3cf208122895b4e64aeeb5538a6bd9a3dd76daa89a6a9bd0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO support updateMergeResult for similar use cases as updateMapOutput \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef3331d0c1fdb18f284edf19ffb848005afd9245cc689d1f9e756e4a289c875d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-35036: Instead of reading map blocks in case of AQE with Push based shuffle,"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1914}}}],"partialFingerprints":{"codehealthFindingId/v1":"b52c262aa9f31c781d8b381cd23b40a81e8a057693605520a1bd704295b95cbc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: improve push based shuffle to read partial merged blocks satisfying the start/end \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1915}}}],"partialFingerprints":{"codehealthFindingId/v1":"eeeba80f14106f15291585c560e1e410010451e80e71c69e2b03a25e9106605d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: map indexes \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/MapOutputTracker.scala"},"region":{"startLine":1916}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeb6ed88c95ef1b928e0b8cf8deafecdde2e3fc6258ea1dcfc70cd404bbc4c66"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this really should be abstracted somewhere else. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SecurityManager.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cb5c159657b6491966b8d0b226bfbb3333d5c2707c3ce8d258cac72b760057c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(xiajunluan): We should take nested pools into account \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2417}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6584e56a1eb68924e6f613dd0da35a62b379a99900c0e43beb75eda247bfdcc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Cache.stop()? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":2713}}}],"partialFingerprints":{"codehealthFindingId/v1":"85b66755a031fb377f52232fe62755443bb14210221b56ae35ef402a25e43d8d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove this MultiShuffleManager clause once MultiShuffleManager is removed and \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkEnv.scala"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"605dc0b986eecada29346176b10da17d8e62f1df927f89fa6e6bf75db1181598"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this file and put JSON serialization into each individual class. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/JsonProtocol.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"724f8f127accc51fd23fa75c56ca4842d19b2c6bfe3411feef527c71961e98e8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-39658): here we are taking a Json4s JValue and are converting it to"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/JsonProtocol.scala"},"region":{"startLine":803}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0bc0c3bb57d209aab82ebe63857f67bb273c713e40197f0373b73f1752de2f2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Drop the redundant \u0022Shuffle\u0022 since it\u0027s inconsistent with related classes. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/JsonProtocol.scala"},"region":{"startLine":1378}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3ccfaf8ab8827726d3caba52f089c4ab86ab2f41e3d7c369f0d60d1d764cc44"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Is this arch dependent ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/SizeEstimator.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"8230293c9f68f42683f6a5914bd40fc4fb84f30241a2e7049c203953613c69be"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-36744] needs to support IO encryption for push-based shuffle"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":2659}}}],"partialFingerprints":{"codehealthFindingId/v1":"5586f81a8d6fdd4a7751cd9f3ff21f8c10689716e3a624d66141b4b79b195917"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME: We copy the stream on the level of bytes to avoid encoding problems. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":3482}}}],"partialFingerprints":{"codehealthFindingId/v1":"80544f11a9b758a3aae204a158d04b7ebf86a22522796f89e1ca64ac9e6f054c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make it tighter. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/random/SamplingUtils.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"8108aeea0cb2c4d6dd30cef7e137acd10c68955a9aa86c913e496fb38ce3487d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO change this to the streaming version \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/random/StratifiedSamplingUtils.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"649003658074e801bcd152416ca2626babf5b4c2031c92c5de1c5deb26699be8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO implement the streaming version of sampling w/ replacement that doesn\u0027t require counts \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/random/StratifiedSamplingUtils.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b160ecec0470c5e4129e6727d44195970a4c5c16c83247cf9386363f6f20bf0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: stop combining if we find that the reduction factor isn\u0027t high \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"688c5413fc3382446aee35b3faa7eb26a37115f98f73af70ff1f519bba7d84f4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Making Buffer a real trait would be a better abstraction, but adds some complexity. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/SortDataFormat.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a950ce06048c58c02c7848128859515d4163ca2457c07543fc388c486fd0ec0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: differentiate between the intention to cache an RDD and whether it\u0027s actually cached \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/scope/RDDOperationGraph.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"71f50c6f419efcfe15a89508f882002fc6f9ca38a8c07e3ca9f08eda86050246"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We should consider increasing the number of this parameter over time \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6589b789daa42f004e350ace40743632958476a160320a131568db0b3c2ca6f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We might need to rate limit re-registering. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":838}}}],"partialFingerprints":{"codehealthFindingId/v1":"88d98baca342885a0892492f638ca763d020a3844582d8224a6813f3b97d0254"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: need a better way to handle blocks with indeterminate/unordered results, replicas \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManager.scala"},"region":{"startLine":1637}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ba015cf74a2c619fc66880b28b3736ffa9578f28de4ce81d3f277f60aa62b94"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We can sort these blocks based on some policy (LRU/blockSize etc) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerDecommissioner.scala"},"region":{"startLine":391}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d672aae90068fa6516f67af39e26c9a907c5c3c15889b71439508e3473bc4d8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: When visible is false(the task had failed), we should be asking the block managers to \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"71d4bbb69297ade0a32df82e60f418006c78678b9676666947ad3fb751b6aa8f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: manage the memory used here, and spill it into disk in case of OOM. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb3bfa594f4d0bad1ac8618068ef0cb6ac839fd2b65efc8defad319a1a8778ed"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-36284): Add shuffle checksum support for push-based shuffle"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":934}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c3da83434f6c8c529aa7095073f796c2709cbb997abdc5ac4f7bbff3dc5580b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: release the buf here to free memory earlier \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":972}}}],"partialFingerprints":{"codehealthFindingId/v1":"92afd4c88217bee68408c5744dbdb721893a67c563ef6f3df3fdd8139c6ef9c4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-36284 Add shuffle checksum support for push-based shuffle"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala"},"region":{"startLine":1159}}}],"partialFingerprints":{"codehealthFindingId/v1":"1565c04dba7fecbdae3e706240eae30a32866ab3a4daaaafc51937b379f2b5a6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: can this really happen? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":670}}}],"partialFingerprints":{"codehealthFindingId/v1":"1072eb3c0774e9601b57ca7bb60085e49fdebf20da246f54078266dd93a916ac"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-57000): once ConcurrentStageDAGScheduler is merged (apache/spark#56055), reference"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/MultiShuffleManager.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cd817bd8ced11e78dda540be2c6c1e1c1c2fee67b5e0871c330624a8a1c5fa7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we might remove this field; avoid relying on it in future development. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleClientHandler.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"83defaf468625c36582c5213e5e12d0dbd9e98bd54e3b62d58f36bc33cfd92a6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: in the future, the TransportRequestHandler can be modified to \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleClientHandler.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2da98d62d0b674b0cfc1caf043924f51fc4c2c75bc3ded04998ca3ed9c4d04d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: refactor to reuse a single client factory across writers. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleReader.scala"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"059995f381b0d1b1b9ba5055510514118ce512d66fec2d6e9820158be73a4331"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO also implement timeout \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleReader.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"69a60e7f31afad1a47fe1bb5dc0474e98dfce2fb548f3c33944fb94692a7b23a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we are actually not guaranteeing that a buffer used to send data for a \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/streaming/StreamingShuffleWriter.scala"},"region":{"startLine":486}}}],"partialFingerprints":{"codehealthFindingId/v1":"affc0cc6fb9e83544db32230349994932cca45847887974b661ab3dd7c6cbf5c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use this to identify internal task metrics instead of encoding it in the name \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/AccumulableInfo.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0fc553ffcc504e8e00b00aa668b3f325af1c134701a3fb83d0bc059ca170ee4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Probably should actually find among the active jobs that need this \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":2462}}}],"partialFingerprints":{"codehealthFindingId/v1":"16ced52cc3673cdd32e9e787228567757b048f54ef7d0439c232ecfe5254dc42"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Maybe we can keep the taskBinary in Stage to avoid serializing it multiple times. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":3380}}}],"partialFingerprints":{"codehealthFindingId/v1":"aec0e161dde896ce2e84f7bb53f28f1ca6b1711957411d3d53e8deb8f716004d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Refactor this out to a function that accepts a ResultStage \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4017}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdc81b0fb61d4a47ec60093ac1d83e8d50bc5aceba37ebaecf8ad49307e2a54d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Perhaps we want to mark the resultStage as failed? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4062}}}],"partialFingerprints":{"codehealthFindingId/v1":"770b4c6a1af8f93545d8327a9848b327e08d2c5cd6cee24f548c33809efc5f9b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-35547: Clean all push-based shuffle metadata like merge enabled and"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4238}}}],"partialFingerprints":{"codehealthFindingId/v1":"494d97136f1b3b62b096d22eb32ed5e331fcfa2e9c24295c66ac5f4f72dc4360"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: finalized as we are clearing all the merge results. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4239}}}],"partialFingerprints":{"codehealthFindingId/v1":"c24d7dc201df77f677425bd585a7df0f3f13a8a69331b98979eb6883d3f0c4f1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Cancel running tasks in the failed stage -- cf. SPARK-17064"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4284}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb8b7549cc7dfda1fc66b7c11c5542b7aaf625075ec53e3db3b4b1faaad3a66b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: mark the executor as failed only if there were lots of fetch failures on it \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4322}}}],"partialFingerprints":{"codehealthFindingId/v1":"d15ce25416dfd60386a26d0ecce01caf42cff49f2941ae19a9a97a1fcf92a5c3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: mark the executor as failed only if there were lots of fetch failures on it \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4877}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7f2b29a6a889d3359aad8a212068896e72c9b9d8760ffd6015dcd3a6ac727d0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-24877 leave the zombie tasks and ignore their completion events."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4357}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceb6c5ae151b5bb49033d3bbe9c254d0e630763a7b9be4519aa9e233dca7d519"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Refactor the failure handling logic to combine similar code with that of \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4365}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e176876c8bc262214abc92f360f9ebdd95aef8518583cfdb4ae216230174b0f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: perhaps materialize this if we are going to compute it often enough ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4445}}}],"partialFingerprints":{"codehealthFindingId/v1":"47850162ee8d1f1f9ba3ee9980116e0ba55fa9b60f533fa0f0e11758c53c0274"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support to rollback result tasks. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4510}}}],"partialFingerprints":{"codehealthFindingId/v1":"1504d7f3fe656498a08d20ad7bb51d01d25b803af454b4a65c41d28a52b1bef3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-35536: Cancel finalizeShuffleMerge if the stage is cancelled"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4659}}}],"partialFingerprints":{"codehealthFindingId/v1":"b430fe19f20eb46e42ec0b83177ec85c1f81bafceebb81b6699725e1da60405e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: during shuffleMergeFinalizeWaitSec \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4660}}}],"partialFingerprints":{"codehealthFindingId/v1":"425ab3266738f526fdc88931708681bc5f06ccf40b05fad099217b51bf006181"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Lower-level scheduler should also deal with this \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4746}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c651219266c85b9d9cef95961831b8a0e621740df77199c4f3c5d0098b6190c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-35549: Currently merge statuses results which come after shuffle merge"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4762}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cbfbd38105f4e05ca5967a45bf72af609f08b9487de67cf5361aab4f82f43cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: is finalized is not registered. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala"},"region":{"startLine":4763}}}],"partialFingerprints":{"codehealthFindingId/v1":"c834216bed16e5501c879d3911cfbb154a951945b838b3984f7f8f0fa30d6f61"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-24874 Allow create BarrierTaskContext based on partitions, instead of whether"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/Task.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"904f84d880bf83357a0987d8d535c79cc3e94319b069a7cd5a6d75ebabbc036f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-24819 If the job requires more slots than available (both busy and free"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":646}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3a137d46984d9eff1c4fd2636eb5f96e45f99dc4c24d8c81e8d1e7e80337177"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO SPARK-24823 Cancel a job that contains barrier stage(s) if the barrier tasks don\u0027t get"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala"},"region":{"startLine":821}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a67d8b8b6f481c96557dd873dd127fe210ce7822a787171d100de5fb204029c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use the actual number of slots for standalone mode. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f0304fc12de77f35fe7a5c2967516d7de257787de8403241690ad1b180a9ce0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We should kill any running task attempts when the task set manager becomes a zombie. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"05c503680f5bed3dd789562e0d080f7aa4a5e9b3923e9023efb3af22cb4f9fc3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Threshold should also look at standard deviation of task durations and have a lower \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala"},"region":{"startLine":1396}}}],"partialFingerprints":{"codehealthFindingId/v1":"7aae28f54e7d166210c6bc10806599a039b8b2bce28c6db24a95d2e22243d044"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Only track used files (SPARK-31974)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/dynalloc/ExecutorMonitor.scala"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"96fa9a0e044aa9a3d753f0708803da81a93a1859f37b116fa52fef15ff00d33f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: a non-blocking TransportClientFactory.createClient in future \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/netty/NettyRpcEnv.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"7006d228dd0d983e7af301d95de25f81c8afd24e3109f282bc4b9aaabfd9ad91"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-39658): reconsider whether we want to expose a third-party library\u0027s"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ResourceInformation.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"db6a5271a332af8bb6ff08f5d78df47b8c3468967639cdd6532485b73b81f022"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // must cache any missing partitions. TODO: avoid running another job here (SPARK-8582)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/LocalRDDCheckpointData.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"73e9e95a153787ec3b5d80655471c92f645936805207c6c61ef1ca4dd3e224ea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this currently doesn\u0027t work on P other than Tuple2! \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5a3f503772ac2f01edf1c337460e77b5b067aeb48b9fbaa87b36cb474ebfef2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Right now, each split sends along its full data, even if later down the RDD chain it gets \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"15596264418b2598beb17f5eb08118659f8c331497481a0b2f0e8b1447380069"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Handle changes of StorageLevel \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbc1c0bec017a14653d51fe95eb2a8751b44d5b6fd68e5bfbbce1d9f292c1db0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO We can collect all the RDDs that needs to be checkpointed, and then checkpoint \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":2031}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fa01e7bee3cbc0bbb60b29f3b7eb80d9ad1460d1bc30b32cb815627d0b87e85"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-34612): make it public so users can set deterministic level to their custom RDDs."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":2176}}}],"partialFingerprints":{"codehealthFindingId/v1":"48bb9ff238e4fd07899f778c4acc89d602b9d06201af7022b5e255a92d262247"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this can be per-partition. e.g. UnionRDD can have different deterministic level for \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDD.scala"},"region":{"startLine":2177}}}],"partialFingerprints":{"codehealthFindingId/v1":"702a49bbfa5e482964beab1ca11e51bcc90e89232c59c1eb5660c4644b977a48"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-25247] add extra conf to RDDBarrier, e.g., timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDDBarrier.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8618a8507646b40dd09a9732630ad4976a732ccc8539909bc63040840e2276a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: are we sure we need to use a global lock in the following methods? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/RDDCheckpointData.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"05f951be591e38ebd900acdef3b132327a23f0264276fa14072a9d6eec1c0763"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This is expensive because it computes the RDD again unnecessarily (SPARK-8582)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/ReliableCheckpointRDD.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"62d779c4df1859bfc2193f24f297e9380de12acfebfc37ebc076db263a189f73"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO We cannot force the return type of \u0060anyToWritable\u0060 be same as keyWritableClass and \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/SequenceFileRDDFunctions.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a94b74bc57d7a6368cef96ae183a96195332bb8a07d8b4882a3b9d6b4107085"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Make this return RDD[Product2[K, C]] or have some way to configure mutable pairs \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa5f7875603bff24b7fe05914d6dda46c264c922b7ef8f588eadde315fd5a004"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Don\u0027t use Java serialization, use a more cross-version compatible serialization format. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/network/netty/NettyBlockTransferService.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"37374df2e2f1087d6edf1f2ead68ee486be7df633a008a917c3ef9cadcb0ed1b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: clean up this clunky method signature \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/memory/ExecutionMemoryPool.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"0719cb25f4a539fc8323c978e4f55a9dd6cd76fd17d4256b31638a4686189e21"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: simplify this to limit each task to its own slot \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/memory/ExecutionMemoryPool.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"252b32deb8fa5a0601f3f4b4e27287ff7a9579e4f7215ec855be2c55bf8e1f89"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: these don\u0027t seem like the right abstractions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/io/SparkHadoopWriterUtils.scala"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9d4016fa23162874d8e369a3fd9c5b9ea0a8a13ab1e81b4755b1cd2998a0926"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: do not serialize value twice \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/Executor.scala"},"region":{"startLine":1009}}}],"partialFingerprints":{"codehealthFindingId/v1":"696813e85e4a39f6728910faa49195efa10d6a42a6396eeefe23bd516da2b078"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SPARK-48789: the naming is confusing since this does not really reflect the whole"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/TaskMetrics.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"89f8e2754265a7daafd7274bf021ab0e63185b8aa4622accc635a7d5a25f2e07"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We could add an env variable here and intercept it in \u0060sc.addJar\u0060 that would \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/Client.scala"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"dae3a9eb79edc8b996fb9eca66b04fa4113d4e305a4c0d529b1af9527027693c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It wouldn\u0027t be too hard to allow users to submit their app and dependency jars \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fca3d63e52fc704cbdc737b63ac6655a66e2d68cbed4607e0bfef36883c37cb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Support distributing R packages with standalone cluster \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":622}}}],"partialFingerprints":{"codehealthFindingId/v1":"2defd6006e59cb0a7434638e05f716cc7adb2a956de62b4a5b580746fdc09c3d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-42375): Should point out the user-facing page here instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala"},"region":{"startLine":1008}}}],"partialFingerprints":{"codehealthFindingId/v1":"54f6f81e5fd5d90bb4f0851d93210eab776da2f4aff28268aac4093b933a0209"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It would be nice to add a shutdown hook here that explains why the output is \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"735dfaaf5f5bdcbc4622ca5105fd81e3499a33f5561e3a963974e808ab0ca9f4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: If we add ability to submit multiple jars they should also be added here \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"802eac260c757831497718ad3efac40164dc36e593ab882f70e99247637b7903"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO Prevent repeated registrations from some driver \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fd164dc29e5102b4d8d49023a967227810ba34ad658228239ecb56c29756895"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It might be good to instead have the submission client poll the master to determine \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"db00aaefbd15ef90d38eb434e9e7a6584dfb265f82281b6b7b44ccd3ce918c08"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: It would be nice for this to be a synchronous response \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/Master.scala"},"region":{"startLine":459}}}],"partialFingerprints":{"codehealthFindingId/v1":"faf9bf7a4d57f4ee6bf144e046aa07410d91048553ad6bae235084e458bd2d19"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME How to handle the following cases? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/client/StandaloneAppClient.scala"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"4332f6d9ef75f20a5015089f149cd87f2046870b376ec139402f9af8d7128f41"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: optimize it to use one socket \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"75d4bf7bf37cace8b16546b0c8cd7062adc30d969f434478239a46b3aa1b8aa9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(shivaram): Read a Long in R to avoid this cast \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"fddc30562ca62d5cdcefa8a7f5a7b52e5eea10696f8324d1b13ae28888a6af0c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Pass a byte array from R to avoid this cast ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d84ea8078f24b468f8b0acceee235ef6e1a7602c479ea031dd6dc304b233c13"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We should propagate this error to the task thread \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala"},"region":{"startLine":207}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b0a314afd67896a707ab6b893164909a6c01c45dc8ad88dc48a19d1e8ce57c1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: find best method in matching methods. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ca01a57a871fd0f65ae371100e9eec4c1ccceaf485f576f732753df0f0e14a5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support accumulator in multiple UDF \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":676}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9f356dc670ce043f24179fc1b19617cf699a2eb0c09ad076358926b20971dc2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This has a race condition if interruption occurs, as completed may still become true. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1339}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcb1b789be9cb6d7f7ce74a57fb57a0bec83c3e88aa5211369d68d902bbec1f0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: When we drop JDK 8, we can just use workerProcess.pid() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"7aab7afe0daf36095f745a54c9b2a16fb11bcafd31e8338416fb2dbec0aaf33a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(ekl) consider computing all the counts in one pass. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/RadixSort.java"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbfe72e1014bea5ab3d4558d52db4e8d246cc4acd1f6e0381b97beb1949931fa"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: try to find space on previous pages \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java"},"region":{"startLine":458}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7ba81049d4958a359673bf15fc23350511d0cdec36a4b80f92edd10e6fc1778"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Ideally we only need to check the spill threshold when new memory needs to be \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d205c3ecd754fc0c4fbd5931441a5540ce3391923ccff751d8b85851c205114"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Ideally we only need to check the spill threshold when new memory needs to be \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"468f34b60610138ba54862c55609ae7601349f263249d60c48f501e4e448a14e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we\u0027re wasting 32 bits of space here; we can probably store fewer bits of the hashcode \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd08c5ead48d27fb51e4926c7dbb8cb5819ff583916f260628e4cceba938a029"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: use existing ShuffleWriteMetrics \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbc2bc0b887eb32cf67ba9bde0cb25b14a7554a74d515fc000c95a5ce6026c65"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: try to find space in previous pages \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":448}}}],"partialFingerprints":{"codehealthFindingId/v1":"91812baa6c4b5789b162421715c0db2282e2287e3071d98a18a5120ccbb220e9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-43578): binaryFileDescriptorSet could be very large in some cases. It is better"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdd212f618027053072ea888f767de281e3b0739fa2cc343fe4c4abf1be3d987"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: we can avoid boxing if future version of Protobuf provide primitive accessors. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bd9b751f31767f2e52b8aa6095d413bddb23cfa3614befa35a72a79f94d36bb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO revisit validation of protobuf-catalyst fields. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":466}}}],"partialFingerprints":{"codehealthFindingId/v1":"f301ed3c25e51c667f35ad0919e0d4242e3ecb5896a679c4309363cf2b5f9733"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: All of the code below this line is same between protobuf and avro, it can be shared. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":541}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7e7e1672f272d63ff591f80693f7f22dcdde1b7fe09b3804d98b445024de742"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(rangadi): A better way to terminate would be replace the remaining recursive struct \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/utils/SchemaConverters.scala"},"region":{"startLine":195}}}],"partialFingerprints":{"codehealthFindingId/v1":"77dd7cb888c4b230ace8e27ff1999c34e1d58ab215ced71e673b74e13b3a4367"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO https://issues.apache.org/jira/browse/SPARK-30037"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"f429bb2c94b858fd29597ac77d0d8f1f20f7c56ecc64c778bd9e075fb5abb8a8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-37973) Directly call super.getDefaultReadLimit when scala issue 12523 is fixed"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"a169470c30d8273cb934b778dbc4f4313e7949798e253881473a9562ff6ea5a4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-37973) Directly call super.getDefaultReadLimit when scala issue 12523 is fixed"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"c61d46254fe4a924ccded148baea7b3a1156a9148a5ae35be462ed4f32ef81eb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: revisit the relation between CacheKey and kafkaParams - for now it looks a bit weird \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/InternalKafkaConsumerPool.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e21248fe5b7351e7825023a5ccf5e55c4c2d9d70010ec4725400fc66844a7c8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO if the buffer was kept around as a random-access structure, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaDataConsumer.scala"},"region":{"startLine":103}}}],"partialFingerprints":{"codehealthFindingId/v1":"294736eaa3677a5d6296cb6a3865e353a28af3cc3a731dc622da4ec7041f8023"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO is it necessary to have separate configs for initial poll time vs ongoing poll time? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaRDD.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"02ea48994d9cb0a6ae09157b457aa98166f3be3cb7006214659ff26a07d337d4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO what about hosts specified by ip vs name \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaRDD.scala"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"011997b241dba26a3f0e3c4e63064c732b2d098005a5ad86b3d43106d55bd62a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Test locale conversion for strings. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/DB2IntegrationSuite.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"af0d417f8609f95900b83285f7e00b861c2d371aa37cb6266de4063f4fe7dd8a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Test locale conversion for strings. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/MySQLIntegrationSuite.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5b05863588c4f7604bdfb8a17b92ef60b202f73551bf0fa342adb8bd77a3368"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO testListNamespaces() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"69e880c71816f0909fc74013e6fe7e949882d49a19948cbfe7db9fc3e14b26cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO testDropNamespaces() \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a520d9dae1a325009e7274f413807cecc05352d9b55f23fc371b9bf38cba5d2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // Todo: push down filter/limit \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/V2JDBCTest.scala"},"region":{"startLine":840}}}],"partialFingerprints":{"codehealthFindingId/v1":"69be9f49c5b4f1268d156ad772a3c9dd655214c535c89f29462ce330e17e6c91"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO (SPARK-32328): Add benchmarks for filters with nested column attributes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroReadBenchmark.scala"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3d268014770b4e21e5f03066479797f81f9f31dc7e67799c21bbfcbfef83643"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: clean all inner closures first. This requires us to find the inner objects. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"a49ad8704c7608cea675f3306b8792db5fe789142fc0e4326c97f7e1d105c1ea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: cache outerClasses / innerClasses / accessedFields \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c7c9304fc3d8cadecbab5374bb480251418b14168af3a2878515c9134e33e30"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: maybe lift this restriction to support other functional interfaces in the future \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":769}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f0ac26e38b280399ce9d16cebac8ed3695b5d86034b424105b1e52b06a9ee2d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: maybe lift this restriction and support other functional interfaces \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":1097}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb20f2bb078bc3e7a12aa49d152e811dd4a63d310170856dd376b7c7b4050aef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Recursively find inner closures that we indirectly reference, e.g. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala"},"region":{"startLine":1220}}}],"partialFingerprints":{"codehealthFindingId/v1":"693a8137e4880523fc4aa10605472311069bea7288735f272bcd802ce5aa2fd4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: the value returned here isn\u0027t even quite right; it returns simple names \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkClassUtils.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"99ab1448f90cedd226a5cf934fc713a7f1d998c4d17356a5f9b0777f69235bd8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Also add fields for caching priority, dataset ID, and flushing. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/storage/StorageLevel.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"834698850bb19f49e6aebd938153943f433c5439c6250fa3b4600c91971a055a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: enable this when we find a proper way to generate valid patterns \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/test/scala/org/apache/spark/unsafe/types/UTF8StringPropertyCheckSuite.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"c58d879dd979ee84b5d968866438480371bf816561eda84d2bb5f81aea4ddb41"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Fix this behaviour (SPARK-48284)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java"},"region":{"startLine":1265}}}],"partialFingerprints":{"codehealthFindingId/v1":"d612c17fc22a65ff147cb1b36969ca9d518a82a0151cc455646098a5b7201e71"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add more collation-aware UTF8String operations here. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java"},"region":{"startLine":1744}}}],"partialFingerprints":{"codehealthFindingId/v1":"8116906064a3650ea509be74ffe2a5a5511e68deabc543897d5facce2ef0a0b3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add more collation-aware string expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":783}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc266bf1521f9050db8330d8d418765fe346b8460e7de5345c9d00243aa56480"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Add other collation-aware expressions. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java"},"region":{"startLine":814}}}],"partialFingerprints":{"codehealthFindingId/v1":"06c13dfb06d318339f4932db157c4f6d4c6b999742db2318ee79278ba6dc716f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this.bits can be null temporarily, during deserialization, \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b073bd8d744ac3c7c58baf0c38ac058d7ac03d68495e9549172fca35172288c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: the strategy of \u0060CountMinSketch\u0060 looks more advanced, should we follow it here? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9f721f8ac92014af58aa13cd4c08c4985ea014ceec9007666c73153a7d45ae6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(SPARK-42025): Add some error logs for RemoveShuffleMerge RPC"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockStoreClient.java"},"region":{"startLine":271}}}],"partialFingerprints":{"codehealthFindingId/v1":"142887050e3ff4280bbb98748fdd6c31afa7e55c75c3a86845f38ef537d01514"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: [SPARK-33236] Change the message when this service is able to handle NM restart"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"451f5feb349e3033553ce4e14c4336130e5777c09684ad03c8364158f7227521"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we may use a new exception class to include the finalizeShuffleMerge \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java"},"region":{"startLine":777}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ac5462118df1e04e7db90d4ffc183da4b4e9bf592fcaa22d7bcee3188ca27dd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: StorageLevel is serialized separately in here because StorageLevel is not available in \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/UploadBlock.java"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"609933139a60a2e47d079c595bd997bea1d2f7a2dae92313991bb8988888558d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: right now this behaves like the SASL backend, because when executors start up \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/AuthClientBootstrap.java"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3cdc3083417e8be4bc5980b57058d1e30b52a69f36a04ef14d2eaba0c6200a9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Deprecate this, usage may require expensive memory mapping or allocation. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/buffer/ManagedBuffer.java"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f6090e5fdbf9a3f1317631be9997ba282f2466059029ef40c0378417ff3d6b6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Relax this constraint once the config framework fully supports \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/config/src/test/java/org/apache/spark/config/ConfigRegistrySuite.java"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"0824a1bbc111bc62670828302f4b66cb90f30ea4a38b22d0a018df1871243024"}},{"ruleId":"D20","level":"note","message":{"text":"No ADRs found: No ADRs found. No recognised ADR directory (\u0060docs/adr/\u0060, \u0060docs/decisions/\u0060, \u0060adr/\u0060, \u0060docs/rfcs/\u0060, an \u0060ADR0001/\u0060 folder, or their siblings) exists anywhere in this tree. What was searched, so you can tell an empty log from a search that missed one: every directory under the tree (build output, dependencies and VCS metadata excepted), for a document that is either any non-index page inside a recognised ADR directory, whatever its name and however deeply nested (\u0060docs/adr/use-postgres.md\u0060, \u0060docs/adr/2024/0001-x.md\u0060); or a file anywhere whose name is ADR-shaped (\u00600001-use-postgres.md\u0060, \u0060adr-012-caching.md\u0060); or, when neither turned anything up, a document carrying the decision-record signature (an \u0022Architecture Decision Record\u0022 heading, or Status / Context / Decision / Consequences as section headings). A decision log that clears none of these \u2014 unnumbered files outside any recognised directory, without those headings \u2014 is not seen by this check and this row is then wrong. If that is your case, say so rather than renaming anything; otherwise, consider recording architectural decisions in \u0060docs/adr/\u0060. ADRs are expected here because \u0060project/plugins.sbt\u0060 makes this repository a deployable product (line 1)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"project/plugins.sbt"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ea8ed3a05e2d91bb078a16dc97d760db3de1c13a80af63b97ac551973da3b86"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060getClassFileInputStreamFromSparkRPC\u0060 spells \u0060RPC\u0060 where 36 names in the project spell it \u0060Rpc\u0060: 36 of 38 names in project repository spell the token \u0060Rpc\u0060 (36 of 38; unit: names in project repository containing \u0060Rpc\u0060). Peers: SecurityManager.isSslRpcEnabled (core/src/main/scala/org/apache/spark/SecurityManager.scala:300); SecurityManager.getRpcSSLOptions (core/src/main/scala/org/apache/spark/SecurityManager.scala:306); SecurityManager.getEnvironmentForSslRpcPasswords (core/src/main/scala/org/apache/spark/SecurityManager.scala:434); SecurityManager.getEnvironmentForSslRpcPasswordsFromSparkConf (core/src/main/scala/org/apache/spark/SecurityManager.scala:455); SecurityManager.isRpcEncryptionEnabled (core/src/main/scala/org/apache/spark/SecurityManager.scala:500). Rename to \u0060getClassFileInputStreamFromSparkRpc\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ExecutorClassLoader.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0f0a3f05ef2a0fe3c85fb6defc65e55925c01e52413bb6da3519913e66f050a"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060bitwiseOR\u0060 spells \u0060OR\u0060 where 297 names in the project spell it \u0060Or\u0060: 297 of 298 names in project repository spell the token \u0060Or\u0060 (297 of 298; unit: names in project repository containing \u0060Or\u0060). Peers: ConfigReader.getOrDefault (common/utils/src/main/scala/org/apache/spark/internal/config/ConfigReader.scala:111); ClosureCleaner.isAmmoniteCommandOrHelper (common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala:87); SparkClassUtils.getContextOrSparkClassLoader (common/utils/src/main/scala/org/apache/spark/util/SparkClassUtils.scala:29); SparkErrorUtils.tryOrIOException (common/utils/src/main/scala/org/apache/spark/util/SparkErrorUtils.scala:35); KafkaMicroBatchStream.getOrCreateInitialPartitionOffsets (connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:370). Rename to \u0060bitwiseOr\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Column.scala"},"region":{"startLine":1355}}}],"partialFingerprints":{"codehealthFindingId/v1":"d349663fde3d9a4c1af772b69a736f001f7efb3e643099f5a2daf7de5918480c"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060bitwiseAND\u0060 spells \u0060AND\u0060 where 559 names in the project spell it \u0060And\u0060: 559 of 560 names in project repository spell the token \u0060And\u0060 (559 of 560; unit: names in project repository containing \u0060And\u0060). Peers: ClosureCleaner.getOuterClassesAndObjects (common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala:104); ClosureCleaner.cloneAndSetFields (common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala:170); ClosureCleaner.setFieldAndIgnoreModifiers (common/utils/src/main/scala/org/apache/spark/util/ClosureCleaner.scala:620); SparkClassUtils.classIsLoadableAndAssignableFrom (common/utils/src/main/scala/org/apache/spark/util/SparkClassUtils.scala:65); KafkaExceptions.mismatchedTopicPartitionsBetweenEndOffsetAndPrefetched (connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaExceptions.scala:36). Rename to \u0060bitwiseAnd\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Column.scala"},"region":{"startLine":1366}}}],"partialFingerprints":{"codehealthFindingId/v1":"68d6e6457525096cfdee21e8056896df10c227dd131bcf2e8fe46965e89cac53"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060toJSON\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060toJson\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Dataset.scala"},"region":{"startLine":3449}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ca37b541ba009adc285aac90deefa5a2e54d6526532937a7fffd21a1d2f8ee6"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060parseTimestampLtzNanosPrecision\u0060 spells \u0060Ltz\u0060 where 37 names in the project spell it \u0060LTZ\u0060: 37 of 39 names in project repository spell the token \u0060LTZ\u0060 (37 of 39; unit: names in project repository containing \u0060LTZ\u0060). Peers: org.apache.spark.sql.catalyst.types.ops.TimestampLTZNanosTypeApiOps (sql/api/src/main/scala/org/apache/spark/sql/catalyst/types/ops/TimestampNanosTypeApiOps.scala:172); SparkDateTimeUtils.timestampLTZNanosToNTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:326); SparkDateTimeUtils.timestampNTZNanosToLTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:341); SparkDateTimeUtils.timestampLTZNanosToNanosOfDay (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:427); SparkDateTimeUtils.stringToTimestampLTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:1004). Rename to \u0060parseTimestampLTZNanosPrecision\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":535}}}],"partialFingerprints":{"codehealthFindingId/v1":"a68f132a7245c1c68a2063b6af882ce848b5c9ed2781fececc8286b01cad7c43"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060bitwiseNOT\u0060 spells \u0060NOT\u0060 where 531 names in the project spell it \u0060Not\u0060: 531 of 532 names in project repository spell the token \u0060Not\u0060 (531 of 532; unit: names in project repository containing \u0060Not\u0060). Peers: org.apache.spark.SparkClassNotFoundException (common/utils/src/main/scala/org/apache/spark/SparkException.scala:344); org.apache.spark.SparkFileNotFoundException (common/utils/src/main/scala/org/apache/spark/SparkException.scala:454); org.apache.spark.SparkSQLFeatureNotSupportedException (common/utils/src/main/scala/org/apache/spark/SparkException.scala:815); SparkCollectionUtils.isNotEmpty (common/utils/src/main/scala/org/apache/spark/util/SparkCollectionUtils.scala:43); SparkStringUtils.isNotEmpty (common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala:43). Rename to \u0060bitwiseNot\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":4898}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d69aaa3a40672a60563d9526c00ea870c0f4282e7cca270fb5ff3af6fb69403"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060isLtz\u0060 spells \u0060Ltz\u0060 where 37 names in the project spell it \u0060LTZ\u0060: 37 of 39 names in project repository spell the token \u0060LTZ\u0060 (37 of 39; unit: names in project repository containing \u0060LTZ\u0060). Peers: org.apache.spark.sql.catalyst.types.ops.TimestampLTZNanosTypeApiOps (sql/api/src/main/scala/org/apache/spark/sql/catalyst/types/ops/TimestampNanosTypeApiOps.scala:172); SparkDateTimeUtils.timestampLTZNanosToNTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:326); SparkDateTimeUtils.timestampNTZNanosToLTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:341); SparkDateTimeUtils.timestampLTZNanosToNanosOfDay (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:427); SparkDateTimeUtils.stringToTimestampLTZNanos (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:1004). Rename to \u0060isLTZ\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/TimestampFamily.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c8f60f0205efead4f8f09f125d79b4c92bddbe66dd8c32328e47addca2e9931"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060toJSON\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060toJson\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1282}}}],"partialFingerprints":{"codehealthFindingId/v1":"b69e5795d49f87eb1f535bfb0e591b69e4652b759cd2162cb356548192275981"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060CannotParseJSONFieldException\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060CannotParseJsonFieldException\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/BadRecordException.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"511f43cb2c4d1d6e1dab2b88d8ae86ad50c89f3a754e16913bd8dead8b7d1841"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060PaddingProviderBE\u0060 spells \u0060BE\u0060 where 41 names in the project spell it \u0060Be\u0060: 41 of 42 names in project repository spell the token \u0060Be\u0060 (41 of 42; unit: names in project repository containing \u0060Be\u0060). Peers: ShuffleDependency.canShuffleMergeBeEnabled (core/src/main/scala/org/apache/spark/Dependency.scala:209); ResourceProfileManager.canBeScheduled (core/src/main/scala/org/apache/spark/resource/ResourceProfileManager.scala:117); RollingPolicy.shouldRollover(bytesToBeWritten) (core/src/main/scala/org/apache/spark/util/logging/RollingPolicy.scala:33); TimeBasedRollingPolicy.shouldRollover(bytesToBeWritten) (core/src/main/scala/org/apache/spark/util/logging/RollingPolicy.scala:67); SizeBasedRollingPolicy.shouldRollover(bytesToBeWritten) (core/src/main/scala/org/apache/spark/util/logging/RollingPolicy.scala:118). Rename to \u0060PaddingProviderBe\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowUtils.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f1bcc0b6797430f583aaff38d852492da5dd3c77c1fe8849049c3abb60f5e67"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060cannotParseJSONFieldError\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060cannotParseJsonFieldError\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":1477}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b0b57fcf1bc5ff120c410b2900a36d8e9f0e426723f4d779750fe4c832850f8"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060cannotParseJSONFieldError\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060cannotParseJsonFieldError\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":1482}}}],"partialFingerprints":{"codehealthFindingId/v1":"d71d4b29bc0a883f8b9a85edee605b005ad73acd8c7dcfdde8edf2f1dd48de0b"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060malformedJSONError\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060malformedJsonError\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala"},"region":{"startLine":1686}}}],"partialFingerprints":{"codehealthFindingId/v1":"1905ba2467c75a8f5a68026d98a23a4663821d8ec496eda11cb42ce275bbfcdb"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060runSQLonFile\u0060 spells \u0060SQ\u0060 where 22 names in the project spell it \u0060Sq\u0060: 22 of 23 names in project repository spell the token \u0060Sq\u0060 (22 of 23; unit: names in project repository containing \u0060Sq\u0060). Peers: org.apache.spark.examples.ml.ChiSqSelectorExample (examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala:27); org.apache.spark.examples.mllib.ChiSqSelectorExample (examples/src/main/scala/org/apache/spark/examples/mllib/ChiSqSelectorExample.scala:30); org.apache.spark.ml.feature.ChiSqSelector (mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala:50); org.apache.spark.ml.feature.ChiSqSelector (mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala:124); org.apache.spark.ml.feature.ChiSqSelectorModel (mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala:134). Rename to \u0060runSqLonFile\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":10367}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ad9c1602775fcfd0be037f730f58c645be3a83292eb8b23090998488dc2b2ad"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060pysparkToJSONReturnDataFrame\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060pysparkToJsonReturnDataFrame\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala"},"region":{"startLine":10548}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2c95821c4b0df19d6616c235cbbfd000b77b28e4a8df388435210173630fd12"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060toJSON\u0060 spells \u0060JSON\u0060 where 292 names in the project spell it \u0060Json\u0060: 292 of 301 names in project repository spell the token \u0060Json\u0060 (292 of 301; unit: names in project repository containing \u0060Json\u0060). Peers: org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:34); org.apache.spark.ErrorClassesJsonReader (common/utils/src/main/scala/org/apache/spark/ErrorClassesJSONReader.scala:156); JsonUtils.toJsonString (common/utils/src/main/scala/org/apache/spark/util/JsonUtils.scala:34); ProtobufDeserializer.checkAnyJsonRecursion (connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala:113); TestUtils.createTempJsonFile (core/src/main/scala/org/apache/spark/TestUtils.scala:408). Rename to \u0060toJson\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/Dataset.scala"},"region":{"startLine":1360}}}],"partialFingerprints":{"codehealthFindingId/v1":"8de1c9f91f7a6a3228c848698516defc5e0928c9a06397b73703ece8cf5c2658"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060TimeStampMicroTZVectorReader\u0060 spells \u0060TZ\u0060 where 16 names in the project spell it \u0060Tz\u0060: 16 of 17 names in project repository spell the token \u0060Tz\u0060 (16 of 17; unit: names in project repository containing \u0060Tz\u0060). Peers: SparkDateTimeUtils.convertTz (sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:197); functions.convert_timezone(sourceTz) (sql/api/src/main/scala/org/apache/spark/sql/functions.scala:16726); functions.convert_timezone(targetTz) (sql/api/src/main/scala/org/apache/spark/sql/functions.scala:16726); functions.convert_timezone(targetTz) (sql/api/src/main/scala/org/apache/spark/sql/functions.scala:16746); ConvertTimezone.nullSafeEval(srcTz) (sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala:5179). Rename to \u0060TimeStampMicroTzVectorReader\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowVectorReader.scala"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"52cee851b784edf0e9588bf433e8dd86a2b2e9a14e0f1b29ca7cc068739b6535"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060afterInitialRPC\u0060 spells \u0060RPC\u0060 where 36 names in the project spell it \u0060Rpc\u0060: 36 of 38 names in project repository spell the token \u0060Rpc\u0060 (36 of 38; unit: names in project repository containing \u0060Rpc\u0060). Peers: SecurityManager.isSslRpcEnabled (core/src/main/scala/org/apache/spark/SecurityManager.scala:300); SecurityManager.getRpcSSLOptions (core/src/main/scala/org/apache/spark/SecurityManager.scala:306); SecurityManager.getEnvironmentForSslRpcPasswords (core/src/main/scala/org/apache/spark/SecurityManager.scala:434); SecurityManager.getEnvironmentForSslRpcPasswordsFromSparkConf (core/src/main/scala/org/apache/spark/SecurityManager.scala:455); SecurityManager.isRpcEncryptionEnabled (core/src/main/scala/org/apache/spark/SecurityManager.scala:500). Rename to \u0060afterInitialRpc\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteHolder.scala"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"81e63b6d4be2ebf34014af3568fa9229b1597d49e808effd15c40562ea977170"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060executorID\u0060 spells \u0060ID\u0060 where 23 names in the project spell it \u0060Id\u0060: 23 of 24 names in project spark-core_2.13 spell the token \u0060Id\u0060 (23 of 24; unit: names in project spark-core_2.13 containing \u0060Id\u0060). Peers: SparkJobInfo.jobId (core/src/main/java/org/apache/spark/SparkJobInfo.java:29); SparkStageInfo.stageId (core/src/main/java/org/apache/spark/SparkStageInfo.java:29); SparkStageInfo.currentAttemptId (core/src/main/java/org/apache/spark/SparkStageInfo.java:30); DriverPlugin.registerMetrics(appId) (core/src/main/java/org/apache/spark/api/plugin/DriverPlugin.java:73); ShuffleDriverComponents.registerShuffle(shuffleId) (core/src/main/java/org/apache/spark/shuffle/api/ShuffleDriverComponents.java:55). Rename to \u0060executorId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/api/plugin/PluginContext.java"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"75294798ea9b580d10e1df3d427c4e0c6bd6beaa0cd0634a8aad8ce1e483f4fd"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060getServerIPAddress\u0060 spells \u0060IP\u0060 where 12 names in the project spell it \u0060Ip\u0060: 12 of 13 names in project spark-hive-thriftserver_2.13 spell the token \u0060Ip\u0060 (12 of 13; unit: names in project spark-hive-thriftserver_2.13 containing \u0060Ip\u0060). Peers: HiveAuthFactory.getIpAddress (sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java:201); org.apache.hive.service.auth.TSetIpAddressProcessor (sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/TSetIpAddressProcessor.java:40); TSetIpAddressProcessor.setIpAddress (sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/TSetIpAddressProcessor.java:69); TSetIpAddressProcessor.getUserIpAddress (sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/TSetIpAddressProcessor.java:108); HiveSessionBase.getIpAddress (sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionBase.java:84). Rename to \u0060getServerIpAddress\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIService.java"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"c00500dca1b3d3c5932a99580555ba744135136e866ec44c61613387cd7c4aa0"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060DistributedSequenceID\u0060 spells \u0060ID\u0060 where 31 names in the project spell it \u0060Id\u0060: 31 of 33 names in project python spell the token \u0060Id\u0060 (31 of 33; unit: names in project python containing \u0060Id\u0060). Peers: SparkContext.setJobGroup(groupId) (python/pyspark/core/context.py:2147); SparkContext.cancelJobGroup(groupId) (python/pyspark/core/context.py:2454); RDD.collectWithJobGroup(groupId) (python/pyspark/core/rdd.py:1703); RDD.zipWithUniqueId (python/pyspark/core/rdd.py:4572); StatusTracker.getJobInfo(jobId) (python/pyspark/core/status.py:107). Rename to \u0060DistributedSequenceId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":1213}}}],"partialFingerprints":{"codehealthFindingId/v1":"f19f3fdcd3184062bfd2692d26ed68da8e61360e9c0bf96d49e6243f3ed5de1c"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060DirectShufflePartitionID\u0060 spells \u0060ID\u0060 where 31 names in the project spell it \u0060Id\u0060: 31 of 33 names in project python spell the token \u0060Id\u0060 (31 of 33; unit: names in project python containing \u0060Id\u0060). Peers: SparkContext.setJobGroup(groupId) (python/pyspark/core/context.py:2147); SparkContext.cancelJobGroup(groupId) (python/pyspark/core/context.py:2454); RDD.collectWithJobGroup(groupId) (python/pyspark/core/rdd.py:1703); RDD.zipWithUniqueId (python/pyspark/core/rdd.py:4572); StatusTracker.getJobInfo(jobId) (python/pyspark/core/status.py:107). Rename to \u0060DirectShufflePartitionId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/expressions.py"},"region":{"startLine":1343}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d39c58edb592bbaaeb02aee268279c429b76e7053169ea67e1981cf3b789cee"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060bitwiseNOT\u0060 spells \u0060NOT\u0060 where 18 names in the project spell it \u0060Not\u0060: 18 of 20 names in project python spell the token \u0060Not\u0060 (18 of 20; unit: names in project python containing \u0060Not\u0060). Peers: python.pyspark.errors.exceptions.base.SessionNotSameException (python/pyspark/errors/exceptions/base.py:210); python.pyspark.errors.exceptions.base.PySparkNotImplementedError (python/pyspark/errors/exceptions/base.py:358); python.pyspark.pandas.exceptions.SparkPandasNotImplementedError (python/pyspark/pandas/exceptions.py:39); python.pyspark.pandas.exceptions.PandasNotImplementedError (python/pyspark/pandas/exceptions.py:56); Catalog.createDatabase(ifNotExists) (python/pyspark/sql/catalog.py:223). Rename to \u0060bitwiseNot\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"68625c6c25f34e36fb0468de6ee7740284966c834722ab0ef5fafa5d12c2ee14"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060bitwiseNOT\u0060 spells \u0060NOT\u0060 where 18 names in the project spell it \u0060Not\u0060: 18 of 20 names in project python spell the token \u0060Not\u0060 (18 of 20; unit: names in project python containing \u0060Not\u0060). Peers: python.pyspark.errors.exceptions.base.SessionNotSameException (python/pyspark/errors/exceptions/base.py:210); python.pyspark.errors.exceptions.base.PySparkNotImplementedError (python/pyspark/errors/exceptions/base.py:358); python.pyspark.pandas.exceptions.SparkPandasNotImplementedError (python/pyspark/pandas/exceptions.py:39); python.pyspark.pandas.exceptions.PandasNotImplementedError (python/pyspark/pandas/exceptions.py:56); Catalog.createDatabase(ifNotExists) (python/pyspark/sql/catalog.py:223). Rename to \u0060bitwiseNot\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":3985}}}],"partialFingerprints":{"codehealthFindingId/v1":"2746227ad6399be2261c5c5159716d3fe348ab8d4e41d83b387cb9c00f0e8430"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060TransformWithStateInPandasUdfUtils\u0060 spells \u0060Udf\u0060 where 129 names in the project spell it \u0060UDF\u0060: 129 of 130 names in project python spell the token \u0060UDF\u0060 (129 of 130; unit: names in project python containing \u0060UDF\u0060). Peers: python.benchmarks.bench_eval_type.MockUDFFactory (python/benchmarks/bench_eval_type.py:439); python.benchmarks.bench_eval_type.ArrowBatchedUDFTimeBench (python/benchmarks/bench_eval_type.py:563); python.benchmarks.bench_eval_type.ArrowBatchedUDFPeakmemBench (python/benchmarks/bench_eval_type.py:567); python.benchmarks.bench_eval_type._ArrowTableUDFIdentity (python/benchmarks/bench_eval_type.py:681); python.benchmarks.bench_eval_type._ArrowTableUDFExplode (python/benchmarks/bench_eval_type.py:686). Rename to \u0060TransformWithStateInPandasUDFUtils\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor_util.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"f29b7bf0c8d388ba0245eab64ff48e7b5da0293a350ea309fb3b6b514f99e7fc"}},{"ruleId":"D24","level":"note","message":{"text":"redundant comment: \u0022Red if GC time over GCTimePercent of total time\u0022 repeats the code it sits on: 4 of its 5 words (gc, time, percent, total) are already in \u0060return (totalGCTime \u003E GCTimePercent * totalDuration) ?\u0060. Delete it, or replace it with what the code cannot say (why it is done here, a constraint, or a consequence)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e10e32effc29bdd5d58d63fadf6c3d9162c72cd66ade5594b9b1c72e32a2cf7"}},{"ruleId":"D24","level":"note","message":{"text":"redundant comment: \u0022Toggle the class of the arrow between open and closed\u0022 repeats the code it sits on: 5 of its 5 words (toggle, class, arrow, open, closed) are already in \u0060$(this).find(\u0027.expand-input-rate-arrow\u0027).toggleClass(\u0027arrow-open\u0027).toggleClass(\u0027arrow-closed\u0027);\u0060. Delete it, or replace it with what the code cannot say (why it is done here, a constraint, or a consequence)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/streaming-page.js"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"6faaae453979ff781a9162e78cb34c576614392f717ea0a95ccac1b3c5b2662c"}},{"ruleId":"D24","level":"note","message":{"text":"redundant comment: \u0022Toggle the class of the arrow between open and closed\u0022 repeats the code it sits on: 5 of its 5 words (toggle, class, arrow, open, closed) are already in \u0060$(this).find(\u0027.expand-input-rate-arrow\u0027).toggleClass(\u0027arrow-open\u0027).toggleClass(\u0027arrow-closed\u0027);\u0060. Delete it, or replace it with what the code cannot say (why it is done here, a constraint, or a consequence)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/streaming-page.js"},"region":{"startLine":357}}}],"partialFingerprints":{"codehealthFindingId/v1":"f39f89be6d3c14387c4592f183ba743b9d4d2223bcd0b70c22134bd553030389"}},{"ruleId":"D24","level":"note","message":{"text":"redundant comment: \u0022downloadThreadDump\u0022 repeats the code it sits on: 3 of its 3 words (download, thread, dump) are already in \u0060$(document).on(\u0022click\u0022, \u0022[data-action=downloadThreadDump]\u0022, function()\u0060. Delete it, or replace it with what the code cannot say (why it is done here, a constraint, or a consequence)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/table.js"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"cde8eb8a392b4efc4f4a3d8195fc544e97aaac1e8c6ded81d4a4354c765634ca"}},{"ruleId":"D24","level":"note","message":{"text":"redundant comment: \u0022end init\u0022 only labels the closing brace of the function init. Delete it, or replace it with what the code cannot say (why it is done here, a constraint, or a consequence)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"11adad03c77fdc672b428a4770aa6632bce1a9926114601f08becc94bce89dd3"}},{"ruleId":"D26","level":"note","message":{"text":"Projects may be oversized for their cohesion: 10 of 51 project(s) overshoot their size bounds, lowering Project Cohesion to 6.1/10. The most over is \u0060sql/catalyst\u0060 (268856 LoC, 3482 module-visible types across 80 directories). Review these for cohesion \u2014 draw the boundary inside the module first (group each responsibility into its own package or directory and keep the cross-boundary members non-public), since splitting a published package moves types between packages and breaks consumers."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"d5a94650dc74886a0f1f08eb9fb6775f1fc395279ef7e901c970c9d26f767a72"}},{"ruleId":"D28","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"69fad535bcc4eadda86243f7611b116a36427b905df3324ea6f1433bde4960ad"},"properties":{"commitSha":"642ab5c1e1ba98833265447447702c3c39fb2d40"}},{"ruleId":"D28","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b88989112bdffcbd70f9aa03966ed31ab0298ac7d18a38013f0baff72336d32e"},"properties":{"commitSha":"642ab5c1e1ba98833265447447702c3c39fb2d40"}},{"ruleId":"D28","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3cdfd7beb31b791ae18dcb425e21eb157c842e7bbcd522cc330573c1a6538db1"}},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6d5d456b042dc9603ec9c694feba3e2186a3828e37fc3913b10e8c0c20208e08"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"30d8b5dfa4423049d410ef984041506b6305d19a3375cccddf3183c58764bf4a"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7ae83b764d504c59207792767aaf3723c868b39e470c5fa88507f1c43f84917c"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8cd942f60fbb2b2acdccde1f24df152fec1504d9ad726936f3e4626004208bf1"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bebbf502a96c389564c91f367f05018184ffb3e5a862c56d038219de8c7b5846"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"62d2350315faeaf2beb5c43d31a401143b9515487a155b022e271a239553b62a"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"60d7461ddfa7f409bb8f90983f3325afa07d1d0584c0249efd5e437906ea2b5e"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9ec6412f13e2115ae59f92e20c90d6dff5cf6f0eb8dd7131717941cb48e1176d"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"47eeeda7c66b55e2208ada7422c7d2b5c14ba76168ad2f1f7f710f085f90d27b"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"07fdf79112ad9ae11595f5219ffeee1660c0464cc2bebb7991a345ab297fb3bd"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4c4842ff9be051b9b25a0abaa1a4b2b9a7eb8ec818b1ecbab278c1781e1e14d9"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1f10e654d08d1fd7c21b3ce42c265b753212e0dc40af028e6bf6b96907a68777"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8db73828b18903825023c7183806f6d2587d544da47d58ea62165d226a6034d4"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"03f78d887ab06a98f696e8fee4c05c6c4ef77035c491519a404c7819545e96e9"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"634c003445adc8685e9f2f293d9ab40f132187cb77f09c25dfc4e6d9bf24d1c8"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"73ff098774c4b8bec1115f0e0d73ad1a7f71d7343e3af2489df76baa1be37ec6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d1feb51a055779b1ed17f4292dda929683feee81d563f9fc326728486413815a"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"eb3b14fae3fe9acc4878012b5415394084c25e6273e4c4a6cb2fe794e3a275a8"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b647a53f3dcd8af1098bbc4576b39f79d499561b70354162d113217f80b332af"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"cff96b4a3fda2e1a1a9705195a200773a7016f71b4bcf47bfad09def31e7befc"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a50c8508bd1b52c66c6a809bac9237ac0ae0395d79bf00aced85211fb560cd80"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9adba04c34b4d2e43f6c69bb3ca028977d3059872a3d52b352e7560571d59ab5"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"956f958ea7004274e31c0d06fa9cc78e395b91afb8d816695e6dd694f134d6d8"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5727b4ed57e33dbc4cb5c8c746bcb999ea6f32fcb58d1396e9c62ebb11c0148a"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0c9b50e7637d91057ebb505e546deff87284fb68fcc315283d0f8f9204b0e4ee"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ab658b748bb56bab03e09fb91af07303b33782776860e4627ce32f11335034f5"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b46e206af060f2fd52edc04520a71915c9a3f79d1e7af9ef7884621b5f9304f1"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3757ddf2919f7f98030955af94d9aba551ef28f18f6888aaf20e2429e6c3a400"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c5af8f5de6ce795aa4bf3dda2d211523fe174bd3783f4c916a2dd4233f1f226a"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7fae0d0bd0159d78a98610db0aa9f71fb4cd1a9b259f91a78fc11eedcbffbc6f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0aaea1b0bfd8ba814f84f19c71d85a957e4435eff08cb4f794e4e71409e4d914"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d6a8f892b535d298281ddd1ea362db4b53557beedfc9e65aba29ef8550fcc684"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d73850df185956cfe45609229eb4a8960004bed843463b32db8b2ca76b6aaaa0"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bd8a7faa1478521adf521f0e55553422c95eb424f16bd5723dad68b57532edd6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"61eb85e9394c4d23d761e54fff03f62466477d4803932f43d8fdc92cae9bf074"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"083fc9b0956cb97fee8f1c6ccd112d9e63ded98d9a487fb82482c5c4f86794f0"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a4769653bc76ba29382fd9f9014ee16f377e52a7e12106b2fca779a53c6d9200"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2bba90fe90deb6b5e2783e893f73edae0275d71b6c93c6779e975cbe6e5d4bbb"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"90c3b54996765c7e9af8ffee2a9d9399570700198fcc49bd2b299363b074fe10"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d6108b50d869ef3455891321a029481ed873ce11c5f96972b60f74f802cb5696"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"22bf2b16e072bda19bcb083da901a8349a98af297f550d3acd789dbb82a514e9"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"92042a93ca79ba3cf581b3128ca47faca7f66b19b7cb2ae72db682ed0ebe1fcd"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"45f41e6b3798f703966e37011a92152da95a715d57f6d49dd0c98aebe451d0da"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5e036d5ec9ae99928c33dd0eb1c6b22932756299238e41099da8f1f1c5392ce6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e63917e9f987d29edffff4c7534b93f53faad21bc56a6590372db5f593c7e6d6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d8f488f305763c9e9746ef927f48f7d89fa1ff706e0d050a8c486aefa04bbf70"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ed65706fbf17c56febf95a961f894440c9d715cc9d20f5cbcc63e82086292006"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f38feacb1c6e7df688ade1210ce1cc8ed56ba9ffe48c363a24b40e24a521f280"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"52d8fbcf0694b49b06571fd01aca79f217c417d527ba06c3a3dd48e64051d091"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"07c420647f312ea71201a8d526c9f69a1a232b2daae54f3b143295d75eab9305"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bce019bb6364b9dc3d6d05af1fa5dc6c5b427a74dbc3a6d929ef360b9e582c23"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2bcd981d23e26a4bd4d536f9a896d94c74b91bc6aaacc5193a7a521db855ae0b"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9cc70491916792b52acc01ca3b28e31363dc073742ff05982799f40d8c3f9059"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e074044a20b1c9d14acb618b9b38c6f83f1a2c3e33b1d3d8e0d40506e58b30c3"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"19985e6259d52cc81ddda061294d6e8b6eb41b0810c23e877098519010a437b0"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0cba6ce10978f1dc12fbeb379fe5e67cb0bd9ec258ed3e15be15141fae84d4a1"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7fe5c8700eaedb9ac8774a55d42a82d6aad1f6b1f8b9a58bb1fcf6dc910ffb61"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d78aa6b77241dee4fc6228d52a59375d76f6c7e194ac276b991c32124bdeab4e"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"89232e364fb821f0700dd081c7b8fe5da234ce9760f17ad5c1f94d209c927ff6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"dbed3d3e937565cad585ab288e0d7ef358b72213a03ede5205376f745c379b80"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1a200872e83f236bcf670f4f810f8efb2e3d07d29b273eecf761705add93ebf0"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3060a491ad8c809122119f2f8a88b23c239c3dfa437f1576448bc6b9774f3e44"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e2732ec8929ec873539d0a2700ce2fbe6e0f0f9ee64315fc5139fbe88812ff2b"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4e848d4b2d8a4305ee1708b3a92ec4dc24d307a25f31bd3316105dc4ee1b50e4"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"afadb4deccc294e3a92fa1bed9adb4428c317dd274411b4702d682480ecc0cfa"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7537518d83d174b97ec7f1b6a37f8f68b7a803e6e421654199f5b38084c43b3f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"91e194840fd7d689868f25bab58417c6347f1306f27f10d6fb0e6edfa7be44ac"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1a8e6734c3abb8d22f23bfbefb1fe10943877c3815b7fb8794ba20eccc195ce4"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d1ae9df31187da84d960212450b749695d880ed9632627f0d2eeeb6453ac305f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e9bb81186c39830a9e4bc178de770134fbad90930031290c6702cb69b21f62b9"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4fc2de991b7a649b5df8d221772f2e4b15fef9e9712c9cdc72c87044f537f697"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2515fa169fbbbaa27c765e58427a55bb996c4b43b13a6165b7572e8afa141105"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1c7045c7ab1cb0e839ed27c0aefe7686376d41e7799c44b6320c5d684b12e8a3"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4d3cb10bfcaa7718144b65e85e5356097878160f5bc51a7622cd330ec2021480"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f32f4abf3a78c8bf97d175502d1790aeef840c859ba9b2bcadd3dd4b8e4ffa8f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5dd5b90b1a0f7d25a0c9b84fa5cea232c68dd7c23689fe4ea07d28aba4f9250c"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f3b397f3a086da2584ddf1ac623532a47a5b9241364e047f8ee4d743ccb1a3cf"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ef641cae8816c805f85eef50a32d3648e93ea372f3a5dfe8f4fed7ca69273de6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5917ebf1bfbd33cb26064bbcb9d51c2ca4e65dcae06ea76e883e0cad7c09e75f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4e72e3aee443eeb9f4abbe78b5d40a6243673ccf291b9fb333016f2748722ef9"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a1542fbdfe276521098bef7c5272e861114821ae08d9470649dc24bc9a5247c4"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7b31527ebb01406596bad3432c730dd0f2e0c248c89a771d6691ae0a518c9c08"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"972ebac9cb18ce32711a01c5a9dda9decd54dfbb963ab9a5d8e41d9c0f34eafc"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"051a44e751b51b9ccdf181f0a2bea02a82e09e2e6ea8623c15bf86db7e1ac350"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8f4e7e125ebd63c9616ff9565742216f9f06dece438980ee075d7ea55c8017df"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a3e71a85b30350b0e3fc279affb7ce784e84d5e6b1b73b45db97affc36bfa4c4"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8c505fa71f471384d34ca3fbfb24f364f06ed8f7a9d8b77e5fe4761e5c58a619"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f56aab94d895ebf299ef3ea7fb8e81d7289d2034ead3becb82483fccb631ed21"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e3c526bf16f9cdc38a5609524712a6851bc7e2b9749fa27d2163af59bcf68ae8"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ef9988ae6f2cceed7be3ac41f830afd514073df9d86b7aad694f2d352f61f79d"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"45e690340b50e1a88445c0393688c36b3d6df8679f678adb51bda471a9222b3c"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ac20e1f1fa48ce1688f153ef98a43166d1af29871c7f80d03d6cc271b8e436d7"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"529e64ac7f5513c136218a55722e1e8db40d46a92233167006311fa57553cae9"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8534d311141cc616347d3022da1d7ad2f288b0a00d68e3bd9b2d7776333a4743"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6073f4164582e29172989c9dcf492b69352a5b5cba8ee5bf004b31ff99fe4c6e"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4588f536fc92b2a2590ff449d5e0d9a251275e66f0c56ac66ef9e120bf8c1435"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4112b9a725caf05de218eb434140d35d2267521ef6cf15c0d21574d08a7af273"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2a716fc54d08bb7bc79455e84f9bc0eab447abd8a987dee1b94c83893471f2ab"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a2cedfe237813a75a296289449912d8c5feedd8b6adaecb4d788a052a4498c44"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"036bb31621c0d18251f49b01c1f5831c11308cf33b3b3b3cb640a6fcb9d0fd75"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"82fc058234d5ae18d5e2631e7062fa22668c164830e423214595547fc85c114d"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"34f998d59eaff18b05f62f3ffd53eb1d86ddd758e021a3b06f3dd141181d69a1"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d87564a0a6d5f9b5cf5188438287684b616fa712694832ba642f5b5c6eea901b"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b9c99348f9b8b4c8d7c46576b22112aeb8c239a234c92a6f3ee361e8202902db"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8ee68b88a74b78307a6d512ca7a30b157154c7cba01d1e47aeaf8e9dfc018256"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d47913b66f01d670c7517a2f898e390a474763a4aff6b50acc464a42d5db924f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"cd47a5336a9e1f18e360872db924c3e29543843c7f9fd5c56103ed50ff0c8b9f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3c91450ef5dc99a089ba5f8c586f10cd5fb31cb37651f95caf702397bfa86b9a"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b781832f9a9f2def96270ae19f922a273a41d825d6d59ccdfaf2566de41db327"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"10a55effb54f7ce824645ce7b15ac2a06b4f98a6110c01fabd4bc841a75a9e45"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3766951fbb5456ec7d56f49673c052092c132ccdf093f3b1b9558a87c44fe7f7"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a9eafaddf6df8779ecdc48b214eee515f35fd2553fc11b0edb1392b73eda1cbb"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9aa02c7e1451bc3312f5fb3e0b17801c33e7b10a118414cc43c933961657fec4"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1eacb6fb18824a04b20293b215239e54ad61d08ba78d9acefbd347c3870cfb4f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"31e15292ee7781495cff3025f3779e23aded0d07be93120b45c65e1d6518c389"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6819b36024d45f5f0e1d43e74427f1e72c7d8dae5d09101e0f966a51bf6829ab"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ae59d5e9dd2c30e110a21be3f2f3e4339df91ffb4154cfcf5f17bedb858ec684"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ab8d83539c5ebe567cb6deae98d392d6617f9ea4001a34a9a21fb3f393c0be8f"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2688137d7a5867b81521c20ab2ba174c854266637e1b2dc91c319aef1dbc5327"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6f9f9d1108bf98f0a8cf56f35edeecdff7c6e991dba52ff0c171794ebefd89bb"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d989e6072bda6c27f7e3419422d133e0673774a5014de5fb56bfc663a68fa834"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f54bf9b91766a0172a25dfb3e289b6b5e5c06652d9f30b2a9a8bb1ce120f54f7"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7074973246c5ea3829a9f68ed80e496a534e557a8f89a3685124518dd61c9e31"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"df2cc17b7e773181407eb95372432d8f092205e56282ffdf3372fdfe39dc1547"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9752abbd6b357c17b44016a31337a77c708d58257292da6df264205c5969eb31"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f22464bf5fdcb5711b90801cca0462405cb54631aeda150d5ec8d81329d55d9b"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"04d9db243faedd9ad568c4004515ab9bef2399a3cff22bff03b385d530e394b0"},"taxa":[{"id":"CWE-95","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"37dd08e30a468235e6043c053fd84ad6f49f670446b46f97ab847a6ab7f5c63a"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c6d73095c476c1a3e0a7e525827ad11b89235934070dcfd6ab11593998b74937"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"476e9c75566868a60961c22b7cf50afe138272a19ca3abe62ea2e927af65ab37"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f60b7eeceb8fa2216ade1ebe4160ae693672069c4a184347f36aca8e70982429"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"04c304fc7963c700a857713f5ab09c7ff626c2a577275f371afb945b6d2d3d8b"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5da00275e6ac893c03de878b2bc54c4d4d5130887be80ab6b452314e7c7415e9"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7a86efb555c5237dad27c34c9d65f10ed218b0179a8af6bd3aecb034ed9e9fa4"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1121d71acf33e957eea9295a95bc82c4d4736822d29205b761b2c8c4f2e85d65"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bbe9433125adb672400641e94ce6b7aa70957a7fca11945519dcee0065a324a6"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0a318c3255b21245cca079873e894bb0bb8fe1cad36493f1cb9fdf445b9533bc"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d5613510ee778cda4fb43111011a1044ee89d22e9cf34d8199ef5b6ba7c8c884"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9cfe094b4d95e25fd3c9a68b4e233436725008eb9ae1fec719532641b0bb0814"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8e595a7a5d29d2bdede757000746d356a002629305596a0491c11715d730900c"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"97d53b8b5903ab1268b485c0ba19df6956e198a841dc75e82edd728b814959aa"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9d7d137df8358d0226bf94eeb9ce6c58b3464eea9f88cb11db88dd4f81fce6d9"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"51f578ea5b7c0f0c969f5c7bf4c658c9f77a264798f886e7a7cbe2df663eced4"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f0d9aac5f64716ef1d6b39220d6004913862b6ec7cc192df019665f428392741"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5143a72f0833320eeacadb3f64d35c25063bc697ff6be3c313a018150f144971"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f2b08a216b77b73df4e591462dcf61c7ffa05fffc7d0b5b648791c4b766dd39d"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2942acfda6b03806122f045111aafb43aea74b458a01a9db5541a7616e006610"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1942417b8893ddd04dfe1d87b8fb19b59ed87e07a856e68d7d40e19d40d94272"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8378169a9f602e0721ff6ce65859b32ceb4969fb9a52891aa24e8cd4ee2c1020"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7b8ecdbb5e94d84179cfe0f2101c7a8cc4bd79be8eed5f5c8e62924b9590b808"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"acbdf6a856143c8da0875941727bf331c73c591d9feda441e0e0f40f2b09f02e"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"26b3c0505f47c40caeb9e7f6e75c0bf34f7dcbe4f6e73bbafb6e17a1358e8f04"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fd455c772d4e408d57f1b504e43e96396bb5565ba464ad2bda6b96f972feaa44"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"821126f9b556321eddef8585fad62dc0e04029f264e473666b5db14143f4c517"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e008283eecfe3bd86a7c4b61ae7a7cb714c7c129cd406f965ea743f0e4365768"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c3274a5ca41121d0269bd94fc4aa49a577e66130cfcd905bb2ab854ec9dbfe67"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8de524014935b00448c5304f66bfa5f5d4a3ddb462180fb8dd64af77fadbfd10"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"eeaa633e3a48539a8ac2c56de59406fee32d6cbcdc1c2cbeec4727867189a981"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b26d2789bfc0c4aa776993432543001bfedbd696d6d10a7680ef40416317d19a"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2454c69205a5f9c934c6426e29a50a99f0b55b72b7b8b3ace7ee56c44f5f9462"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b1e76c3a3db8b4a345f8d77a9bfbff387e095d82adc0c7352ef02440a5eb672a"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7f43341aab6d035444e4940cdf1d937624dc075ab261314d45063f3d04944aa7"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a07aaa448de54e29b3c16d1c000b7365c3c8d0f3e6debf9edd38ae8b92c8bb60"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"120b90120b4351cfe2426809bb249902ee63eafe5cd9b6df1e01690bc5af4d3b"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c85c495156b391e326e8e7c747c7bd3c7e5d830b1b8c73fe72483587c5cec805"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b0b3c057e34114556ae22dbab0935836edaa75baa00d3a880b4a97e96f459ab4"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8c3841254670ace2d576dbc33adbc7c4654c668f29126d6f56a5625b26c7735c"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"093e3f9d17cea1c00dbd68ee2eb6ac18552867b6ea0f002e7c8df35de45ea310"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"58424838eb8b5a7fea339dedbf8666db9de10791c990d7170c6a47c71ed2c141"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"cfeecc87ca198a1f5a2ababafb563b64ee7b12b7ad94bb1bae56e9824febb321"},"taxa":[{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"724ca86e2a64d910f651ee39016c9bbce6338a1b0c4b40841a991220cdd27d32"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"210d92aeb73ea2a273160b1cd06143d101af8a87f6bee93292de9e8afb780b19"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d018fed922d1cf5d334c8f7f91d1019b83edce5d6378ebeaa4ce822fd8c89ec6"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a11ad892bca43d3fc0276d4647f5dc594ed01cd4033c3c4f4c91eeefcc70e467"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ca22805c3825a66c46bd0fa2c7799ee89bc5733e1f8822d6545bbf40f1638dce"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"68aa004d19ff2f9c96d41f66c6e209d59feef67dfe71f763662d7b07ca1e3db3"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9bb2ef5ba4eb57f8f897d9628d0a8d3dcba0c3b779dffdead330061892875ff2"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bda671bce286791469f795c4686986923b450e43c20e224702bd5aad882ce3d1"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e7fea577bbf8f40fb125a899384f4fd88855e02169f9292375048d692c85d67c"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"118b928010606596ee7a0474e1044bc83387081cce4f28459ca53153a85d8255"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"38b90d3846e2830c19ebf70b5a379e1ecee2fc3325290476fd007e3945ce4745"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b1e7d396114b11338b86c1125873d63e405f63d2e374d8efee461768c105325d"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"8e643b687f29cbd683a9245d67b59e3cb187274d19c8ccdc88b05204a7a736ca"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"65a275b5c85c4df8788ba94cf42a8399a82b1bcc79f5a363e718516c8e52ca7b"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"28e6a2b1e721ffbc792eb70741e6b9c09839bd80c37b61dcc39ed1fc78e28c27"},"taxa":[{"id":"CWE-319","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A04:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7b592ba05cdb57c0d9bc85534c47cbec2ae39546475252d01122d9325a83394f"},"taxa":[{"id":"CWE-319","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A04:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c5eef9f38200142861a9c90cc6ce6d699aa3a404a0d160de4372e3cf4cb3ae14"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f686a6122d46df92f0fdc375fb60edd11f2e755ac2b9974b0ffa4b45d6a64373"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9589f8b12615024b4af05859f9c2f4f6e148b9dc02692dcdc738b2359e792273"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9b11b797c004a259666638134c1adb4bdb7f10b7763c7040dfae529319c310ec"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"132dea5b140b17bb698f9cbb6932c55539d4906e7e8399cb5597817470471065"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"dc09114bb5bc6d5b7df9047bd7e169c1da158f234aaca2eb89041f0c737c20ee"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ef31900bb2b7ae915c5a28ea8312c5a938504f96434ef5fab71c4941f3f0f023"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e3b7e043bec9ea236101cba954df876b797d12cd9aabe06bd41ddd7564eb71b3"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1053634cd7011d2821e2d6c1148c1ffca97dab554534791596013ae4806821fb"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f9218cce45f7ff520e795e2bc19b276365b09393c50c3fa4c59f5264395e7bfc"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"51f08b020bcf3758dedc7b7f09cfb59a26c21a48ea551f2fa2cc945035c39894"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b5450fd5c313def527b9c0106c84a3612c27137e5eb6fce31e02c2f284413d9a"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"af1d2c1c0c422b53e046232ce281c921d73f8294d29418a95756bd77007c12b4"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c953003270cca3aab6a3397ea24fcbc2e91f367e562f90a0a05546fd77b9f0d0"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"865e4aa2d21fe114356ac6b7fe63bda0461517998880dabbdb49713258608862"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0fa7795b0e9e0a8285fea67642ee163e608eee7cad27e68663967718f580913a"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"856c59b21b7c9c6d476de82d7d0d04b5e41570832affc00c7548efdd8f29cffc"},"taxa":[{"id":"CWE-502","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6898d295bbffeedb7671ba1306ef181b82bba88c14cd1412bb0cff9f86d6373e"},"taxa":[{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c016cdac3a2aa4379d8303649a4c3c4d859ccb4883ae991b057259f41ee66d76"},"taxa":[{"id":"CWE-200","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A01:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7fdb9da168b1449f280a3d0cb7bf3753e1419aebc2c53acb498da8ab563a5043"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3d19d259c9101f74ff1adf0871efbeab37c9993bb8b7693dd8fae132f93780ee"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c1769adaabb89a1dc28726243c758dca3d76df35ea773e291c90b272934cc494"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"27c37a045c0a3b319492f06126b0d635aa819867c638c71af2459a7707f344c2"},"taxa":[{"id":"CWE-125","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A06:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"990716626a6c4493cf50447ba41e6fb68c2d3bd60d5b4b8bf4a85a1e1f26cbbe"},"taxa":[{"id":"CWE-295","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c20a9d483b12dfd1fa45f3cb6350760520b5e56eba33e9ec1303b9bd5a55ffb9"},"taxa":[{"id":"CWE-295","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7911ba4702a9509874bdc809a44e8b2fd7dc146c1e785dbf17581ddc24949dbf"},"taxa":[{"id":"CWE-295","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"66e24ff8fdbf71c4bafc3d08c6bbbdcafbb0cceeb88f2db9a44049ca2126cadf"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ccf62fae89043470628f92db57188e82cd8978b95a63553669c71a56a13b0138"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"271ce9625c685d43e8056266869f1932a1834cf19ff4c37d9a51c1d63d194a2a"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ad93c7f056a594db79d2d5d7b67438e71548e006f496150d876b410d4fdfa572"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"43f13dc88fb3032fe2bc6012beced002a6178124245ae123674bd25a433ac1c6"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"565ea704139f45d31dc03b8e58a938a35dd84c7972d184fe51a05e5bb561a88b"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0f65eed18a85db10b5318c3853728a1b8a31f339ee724b5f13a7b0e21d84d6c6"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e79309614491415a0f613dce0359143cadd1d4d96aa76bd1580bcf109b7a031b"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ecc9f008c8add9c6a3046be3a04da055a1faf51daba122a482a94040ffa4c918"},"taxa":[{"id":"CWE-939","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"916e3556683310e2cea293b4c4be457cb8075f5897569372fc41f0d8deeacf91"},"taxa":[{"id":"CWE-1004","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e2900c68efcb0490dcefb751f7e02eb087b86f3eb236b2b69743a15566916091"},"taxa":[{"id":"CWE-614","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D30","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"db0a83abf65da4b3836473bd0ef541296cc842edef0be2de24456b60812ba47f"},"properties":{"dependency":{"package":"mlflow","version":"2.3.1","advisory":"[GHSA redacted]","aliases":["BIT-mlflow-2024-1560","BIT-mlflow-2024-1593","BIT-mlflow-2024-1594","BIT-mlflow-2024-37052","BIT-mlflow-2024-37053","BIT-mlflow-2024-37054","BIT-mlflow-2024-37055","BIT-mlflow-2024-37056","BIT-mlflow-2024-37057","BIT-mlflow-2024-37059","BIT-mlflow-2024-37060","BIT-mlflow-2024-37061","BIT-mlflow-2024-6838","BIT-mlflow-2025-0453","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[CVE redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","[GHSA redacted]","PYSEC-2026-1636","PYSEC-2026-1637","PYSEC-2026-1641","PYSEC-2026-1643","PYSEC-2026-1644","PYSEC-2026-1647","PYSEC-2026-1649","PYSEC-2026-1651","PYSEC-2026-1654","PYSEC-2026-1655","PYSEC-2026-1657","PYSEC-2026-1658","PYSEC-2026-1660","PYSEC-2026-1663","PYSEC-2026-2657","PYSEC-2026-419"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"eca51ecc6c9a6f97ff889400e5f11163c7c17b77e8a8ca082d1187259ea4a7bd"},"properties":{"dependency":{"package":"org.apache.thrift:libthrift","version":"0.16.0","advisory":"[GHSA redacted]","aliases":["BIT-thrift-2026-41603","BIT-thrift-2026-43869","BIT-thrift-2026-43871","[CVE redacted]","[CVE redacted]","[CVE redacted]","[GHSA redacted]","[GHSA redacted]","PYSEC-2026-3926"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3b84a0691a2c5680c0ab9042e23e91d18d49be424276dc17a3c8b3d02bbae2b6"},"properties":{"dependency":{"package":"io.opentelemetry:opentelemetry-api","version":"1.49.0","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"09e7a885ee9f42dd4be9cb539bfa706ebc37b75f49810684f316e2b7c38399d6"},"properties":{"dependency":{"package":"commons-lang:commons-lang","version":"2.6","advisory":"[GHSA redacted]","aliases":["[CVE redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"884bafedd1ae0a0637d7c319675d5c35a568fdd8331f3e6e75d0f21cba43833f"},"properties":{"dependency":{"package":"commons-lang:commons-lang","version":"2.6","advisory":"[GHSA redacted]","aliases":["[CVE redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fa9351fe7849e8d0687cb3b267c0e90f1bce78671fb161e939bd58f45ed3fed6"},"properties":{"dependency":{"package":"io.opentelemetry:opentelemetry-api","version":"1.49.0","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2d22bc6ec520e58c22069294b61c2186e89dac99ca00a53268c7f60a58b995f4"},"properties":{"dependency":{"package":"io.opentelemetry:opentelemetry-api","version":"1.49.0","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3b2272e7ef5dbd7c5e3def4f0df0845e49a087ea16d6e83ae8735eea4a1bb713"},"properties":{"dependency":{"package":"commons-lang:commons-lang","version":"2.6","advisory":"[GHSA redacted]","aliases":["[CVE redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"29c282102d044f91286c5c4eb1b6e2d5bb67454bf8fc5ba4305f07ab9193b9fc"},"properties":{"dependency":{"package":"io.opentelemetry:opentelemetry-api","version":"1.49.0","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D31","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"79ed3a6a864f8d5b4e961227a8be0545ef1825ab9e3351b72a63ee598517d26f"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"da2d32fd3715075ff3ca5b33d454b62383f7ee612002cd4b1fcd32baf339507c"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2bd8ec915678142a7672452dc8d1b99a6620d4efeee429ecbc18b401c8953872"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},{"id":"CICD-SEC-3","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"aa36e583393b2622b81851979e466370f03a5c12559ecbaa89f974960d0bc85e"},"taxa":[{"id":"CWE-527","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-538","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A01:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c5b17e62c659d25bc09d0f505bdde32db977e7a1b4cff8f28b1eaac7ac9ba80e"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"295515da4ce5621073e535e0ab006f2b12f08772842297b280c37f35175463f4"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"94d4715a3f9d074e7c4eb030662e1e5e1cc6623301b05d1b9f78371130d7c198"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fde889d25c01b2c0e14001648737f7704f8b023a5083b54af6988a06155aebb8"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0607330e226389761b0dd48b7a29f6e9f8087c1a1c185b913b546fb8fc97dd6e"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1b7d66a9064772add5d9f12137b76d0a3f2508192039427d2807fa49bb72b653"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1d6d9b561626d4082a72f98dd9e28ee69913723ddcb3bda9d099cf6aa7423c1a"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"319365ffa3b57bc90d585049e634b72ae0038eb18249b005df8c0c8235691410"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"af94b9775671df5fa8f7a5dea44a14e3a45741701ce957c819b524a5f70e4ccc"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/linalg/distributed.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"46448619dcabd07ba1f6f206877245fe31f9cd459e54b1d66c2dabee1e589c16"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"643b7680b2889f95d82ca6dd00d5e71493d8b3eff34404ea3fea29d8506feca3"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fc36e5431413d9d5094817b4596b68c85347861846cd1dc060b7a5ab1c47ed0"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/spark/accessors.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae572092635f59932e50d8cdd5e9c539cc13aeb081c6ca7155fd2f71612563f4"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d7b17a33dfb2e14d74406c498ad7834fffb37c60e57168338e5541140ff675c"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/functions.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"06b68fe763490f1033d0e9363333a3ea5e027da293e41df1bce7cec89f960377"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/regression.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dd0b6d4ebcd18df7626890bb68a8e3a7c0e76cb55c9994239ce5a36b0afa453"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/StageDataWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b22d41726eb3fb754cc49c5f4e73b159a763712687258b3e4ab4f3d36cc039fd"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/UDFRegistration.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d87efb1ae30e5be5682d8b895331e77eebf0ebcbaa3febb0fe5f7afa7abba90"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/dstream.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"973680993ef94c11d846416887c62130cbaa24f9e12769716d276fa4c7571fae"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf17a3cd79d3b93ee0fc19ba3fb5bcb66be42f0dc89ba019f0fc5a1be6c4605e"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/KeyValueGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bca00dccac80f8a3aa381baccb2cccd09d76fc36161e2dcaaf6ead366474ae0"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/feature.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c372aad110b7777b787c7cc6953fe8586fbcb87acb389f19206d48cbd3b97e8"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dc2f39f07425120fe01ad34e675d1f17d5a6dde589e2aad7211810f55f47bb8"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDs.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a143ab39a2f6c755d148fafc150fc8df897f1f52f01e3c02a211de905faa27bb"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/tree.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ed24dbbaaccf65e86f235812cb623e7bb5e057fe3a8e1af9ff97f4abbe4ba53"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away, so if it breaks, no one currently understands it. It does carry its own tests, so the behaviour is pinned even though the understanding is gone: schedule a read-through, using those tests as the specification, before the next change lands here."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/tws_tester.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee0671c02cfc7cb77aa06bf18f9b930bbbeb098887899ade6845ea624ac46d92"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/RebaseDateTime.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"02ccefae7a1c3541c59d62e6f5ede27f976d29205b457267a40ae45fc84f1eeb"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"80e6184160a6f8ba64c3152ea5783f2c87110dc5a9f0c81e04a39cdda34f1b3f"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/category.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aafcabe20e0b58dd9b3bd197d7e9a96eeed76d8883e24cc4270305dd52ceac93"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkIntervalUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"04e8a5b97644b8372c439c23fefbf73268544cfaafe8d4036c8be788bc621b4c"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1366e6d5a97eb26bca8163142fa3c514d2525da944167e38bfc597e79900de14"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameReader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3486664013c3c89e8568211add4b004c87aad3a32229c890d550900ca8eeb56a"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/storeTypes.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b541f6ca5313dbf487ff96dd1d54bb1222136875c397165a0b4b46f83ff30511"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleUnion.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"893f48b06e1c75f6c270021b12a74047ae56299ab14211a390d038c088085306"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/XXH3.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa0ef334841a3b12b5dca7c068366b2b881f68e6f530d12971c30b23d0b8dc53"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreRowChecksum.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"36bd23b0ad32ee474e57e1752cfe65187a1405e89eeef28c3cf9cec05c8b9c39"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/evaluation.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"076ae77e2accce012a8f5ebbcad72024036f5527f643e99248d540cd6e1509b7"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/random.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"651f03d4da02c1e1f21deb30f2d1009b4cf1fa0ae7834ce7a8fce4cafe052fe9"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8410029ec2319821e169c3fceefa7b259969716fa1be591ab77d899e756f8073"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"77f2f45d59f72192931d1e214137a48a3af95b125479fc7a48c8224e0d17f8c4"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"86c73fc6bb825130253f080e2ca70d67a94be4e8cdb93e87f134e6d672d9df4a"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/ConsumerStrategy.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b24e5a9a617acfeff2ed7db4b1107dbd8d40b574820234c8cea1101ca9c6f84c"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/ToScalaUDF.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"48f7b057b3f8b6ddf6f28cb3211c71683a155ca0f977df5238026296282043d0"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"049b7bb44c3ed06f4233829b0aa1eafe2fc3a57b4f6161d3747d221842dca309"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9ca97489b2dacea00caf94300f87b0ea9878e32f7bdace6ecb02075e0edf6c9"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/param/__init__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f06f23beb51f28a4f6b5b91276f7b879e975c6fc7f435b03556cf4702b1df98b"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/ExecuteEventsManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb8501a68f35d06eeb54c91741eb1a8cdbf5a96026cbd25eabf08c94fd1630c7"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/ThriftCLIServiceClient.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd9c9f9e48789423cd14f25c074ab221c08a0e296edad600f426fb547d626233"}},{"ruleId":"D34","level":"note","message":{"text":"Further orphaned files (smaller): 505 smaller file(s) also have no living knowledge \u2014 folded into the freshness score and metrics rather than raised one row each \u2014 most significant first: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/linearRegression.scala, core/src/main/scala/org/apache/spark/storage/PushBasedFetchHelper.scala, core/src/main/scala/org/apache/spark/scheduler/SparkListener.scala, mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/AnalysisHelper.scala, python/pyspark/streaming/context.py, python/pyspark/ml/fpm.py, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala (and 497 more) (544 orphaned of 2912 analysed files in total, counted over production source files of roughly 2,400 bytes or more, excluding vendored, generated, example/demo and scaffolding-template trees and test files identified by path convention, largest first; 2912 of the 4700 production source files in this repository met that bar). Attach the read to the next change that touches one of them: have a second person review that change, and leave behind a short comment or test recording what the file is for, so the knowledge comes back at the cost of a change you were making anyway."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"ce861fd78f6935114d3a342cb90ad25870f984e1042954fcbbe27c0e23be3658"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/PushBasedFetchHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffe3dd487ab3584047a6cb54e73404a21c30140fb71dcc5807abab4c4875decd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/SparkListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"427bec5751fc6bd6acb52b4bb6e282479637580a5e264c5ad8b62eb34a9be1fe"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"39a901b7d08e626b308795a12b7d81f76879d2700a17f3863176625d4da1b803"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/AnalysisHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3559a1a82f08d1c2199b89c14241120c6d3ce56296961854a80873a3be2a1c0a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/context.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fa9664c54d861ccb1ddca42cc74b1381481cd55aeb7080b196cf0aff1f20038"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/fpm.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e4235fe6968c794266991f3f2192c7b5fbed6c56d2a447872cb7d65cc89925f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fca8dc6ff0446f936e8ac03de08e915ed0a1ea1a4abc79b19d66f85d8d46510b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/columnar/CachedBatchSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"613ff906b9a120029726983fd8d6524d2f8b773447ba025b58c34ce4470f2425"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/linearRegression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8270cd90c324bef1edf3a970d82ee224f7c1b63b2e29ae665311efded087eed"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/stateful_processor.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f1c2ab630e6fa436b354842980c6c9388c7c30ca7b5b3f8aea752267d5d97f0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/gen-sql-api-docs.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1caa711eebe168c835d8181f0bfaf90f29888cb8db2967ed906a25fb44e19b5f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5ab204171e84117e2991f7f8e25558f56bfe7792aeab17cf84243f89907fbd2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SSLOptions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"349b01f29ec616d4e2b1e52a19d3de4058e7ef94a7fe8bb77c9b493a5628c48b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b930211358708c877177d5d85f44df67f8c1a0d9918635af216a3fe1a1feca9a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f9729d7dea229446aeae247281c01c085a6590dd37650a1d1bc1894ba657994"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e73209f09ebd08e67ef5ef7766e6f8238688eaa520f3b0442eec97d3c8c44bfa"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e97b70794ceab20c25cdb8a7085b051babf3f8b4321fff3508ce0115db40d67"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/GroupState.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8231fdbb774098760818d8c67a2bfa5bde72b764be49121b3a1e6ecd8590c3a9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b33ae6e96332354accc664a6a5853818f8373bba500bda1b12824868add72203"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/ssl/SSLFactory.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"44c7bccc57e029683babb6af9846d0c1552c381d600449ee186c7fa03ed9278f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"31d86d5c94b83fe44f2b102eacb2cc98b59cf3c3141ceddab11de66e02bb1c65"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"87b04f695087da52554bd48eb2f3f83af6aa4b128df55571255284cd055592cb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeFormatterHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c36b159531e7cbf365508c81f5748a8935b38e19e4a8442e48bbe4f58095199"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4de0486725e8e45c1c4c132c6548845ae53291359e6729a707a8f70afe1ae8fc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb3556fd363c4aa4b40f3862d38fb798a8db17444b10aeca58b35e45ea21b5f2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2ab7b8ba9c514ee2231b59138fa3f93d63c20738bc1aaee878eff82012d99f8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/pipeline.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff6669216cda48d13eb47e1a8b818bc2a9de60f4b5fe8508e1e43ef7cd777f98"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/stat/_statistics.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b34d8d0137457cd5be8b1a7a59f1b50ec4765bbbf216f4facee768236b825e11"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/map_state_client.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"34544e332ff6c5216d9bb1b79257c9a0e8f2c06e0262e50c332f71fbad220813"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e68e005e2e0c475f96d755ed64818e4fe3c34a2c2539e313be7dff43758045b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"74b8e033f9eaf3ed28066080f10621df0511741934977b8e3dd5e110f9dfa9b1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"44a413f340f00a9838bc5310b28f1c4c8393ff111e1a7c184b1e9cd51af6b40a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SQLContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"804e7c1b0b194351337c875930492812c3999c679b293e1510f883f8497fbbad"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaDataConsumer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c557f36c4f42313e33014999a1d77b3bd0c44252e2bd7c5afc66636f2ff56d93"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"129c459bc06de315b1d6a2df4f2074d7b9634ecd36bec728c337bea89624dce5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/common/UdfUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaff3db2d2948ca813996837b14ad36109c9bb580fa000a04aa31955179d66c0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/protobuf/functions.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab8696b8683f4645b8e8f2c1b6aa1cdd29f88937a8485710564e7d34976eeb88"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"326b18d8c442176b4b7de59557ed9648357ae44e1fa18ef2c0b49fd0a3944f94"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/columnNodeSupport.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ab00bd195400c72019fe6ea41a91226f1b89f6afaed927c5a69923770825bc2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ShuffleReadMetrics.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"457673b9d815c198591a273648d5863666505352dc12acd4aa5f3599e0371040"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/GeneralScalarExpression.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4dec703845a3cb640c2376f7f0ee1ac131fa445f8e41672c0e9e4391d0ee9b8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/RandomForest.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e15b136e139dca16bf71b0bae0f8ef7b04fe56a8d3974078c22fec356d632d4e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockStoreClient.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a7685de0e2bc278ae277150992f739504c579258b30311863af3c5aa5975036"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d58de2e777e6445412c2be624e24698d8475e97b5435e0537008ca6470b5b1c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a0b18e07ba271a94b66a608430301c055532b2d3c45ffb0c677fae04340e354"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a2508969f47a3553ef849fddac1cde95d91857242f8852c8690a484e6f295c5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cbf1e644a94430da932774c7e81c16df1dc5a56662aae32abbbe4e64889d737"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/FileBasedWriteAheadLog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b0ca380ae777119802dcfa35c4f18c3a3a46c720a04c6d2d8445dc4d561bdcd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/recommendation.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6241a2798684e25a06ac6bdfa7c6aa3eff2c8e15360e7e2d255e1d6a41b85fe3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleIntersection.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"76f2f22931dfc83a5a42e696e165a2a3864d83f6773002cf78da6ae3a0d5d00a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/python/PythonDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a2805ccb79d2b1adc3d92fe0bf02f3a1966cf4f3f06c71843bba6a134140e6d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/RequestDecompressionInterceptor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2591e915c325e0e3a24f46ff5e3e88b6c2eebbce0bd379920588122f4d5ac763"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8afdb210cd2b30138b5f34af58bce35d66d17dfbbf1e1b8c34d83100e02fbd32"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7a4ffb2c45fb57fbaa8fc217ef6929e2dd71e7cfd56d6db68e2eabe6b960b90"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/api/v1/StagesResource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2092d27bae17756b8ee1b7d3200d6ae8a604067ae420109501f10b037abe6e83"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/broadcast.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0c97c998570f4ad00a9dc4f7227aa9c85995f0a3eb5979c64bc7961cff3e3c6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/TupleSketchUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8ee80591539cc90ca3dc25cf884bebdbbedecabece5cc04ca92dcf372f57978"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4d89d01a8ca169b2f2a00568b0c9a202eeec2a3a5b247bdea538fce46bf5cd3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/examples/streaming/KinesisWordCountASL.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d66fbfe618ab717be392eba2aa43b44f1213e82be5255de5eccb68d65004127"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce19be205c6f2a518ad35f0c09fefc0b3bdd15231e1ba273b3dcf4ea1e5e11f6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/testing/InMemoryStatefulProcessorHandle.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0390a439ee7b7217dca328d7e3f78c55c97ee7a642ef1e896fe3024e9dc296b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c216001162e26a9a115ed0b0bf37e5b87224fba0b1360aa0937f58a281774bb5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxMinByK.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"750ed5f891e205a7f0356a66101b8aa19054fba1826cf38e30e87afbcc57d29a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1a4a292e9e06060c35358801e1537eb43c7a70c012f488719838d16ed2552ff"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"18dda19e03a17dade314009ee84950978fe745970e48d1e0b5dc80ad04cab391"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceivedBlockTracker.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc926eb834269e8dd51c51ac7b48137a90023d6785ed0a3ad7244a39ecd04fa7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/MergeIntoWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae9f9b9dbee6fba16f96bb0101b20a2e64e9be4771b1655a2554410bc0be9ba5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f0b68f35f5b53f9c691f8fb4a7ba31aefe14c63670c2d96ec916ab2a097367d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/base.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4f5d6742630279ee6e0df797d216df8f2a1a139b12b535397b5d64de72d2ea1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"639912c66f976f135a5fcff86313b6d74b6af7730993570c2f0e57d174647693"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/BarrierCoordinator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"57e7f9d067280eadeeaaebd7d30aaf23302a6ccd62686ba06ed650bd5d58e942"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c10d0ce201f5ae6a758e16807e5b48a7b5edf54645b5ae800c559e9bca91b462"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/Operation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d48c9c4eaf37fa9f7f5b4fc5c737c90fbb26a91cd38abc034e61a3085ae7238"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"16ee6f62809a375144edd5b8db7a6085c181053bfe23842b5ebc8deaa7643d5a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExecBase.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a39f34f7310cdba80db4565419bcfd07895bc9700bf29095bf232fb1299e5a6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/CtrTransportCipher.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"908f334699518f9103f03578ebe78a73a24779a6403459b0117edbb72ac5b305"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/testing.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cecc92533cede20274f33bc80f9888a373a9ccb0e8e30c5528e5f9c8eba277b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/tblib.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bdd6e1f4cfe7521cc537cd4c03a6dd6449a832a6c43cfd594a1727ecdf466c7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/RewritesAliasesInTopLcaProject.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5c5cec26a7dbd1946993486053db3806db722ea0ef318f3df5221ddc4f0af80"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/FeatureHasher.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9691606ae77db5ea13a8067a7764bea5de3b724c9fd24775d38dbba7b941694f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"622bd030e66bd431318fc78990ec50bec8527e02f02727c6fedfb74f1df82cb7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a48313b732439d4e5f01e41ca4ebc64502d289c9bba3319ce7084158f3f79c0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TaskEndReason.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2b3a89afd040e86a39f3d1d982430beb52c70050934feb183fdd20b9974631e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/OperationManager.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a633b8b3484c4535ffa482ddb576ba7694e70cafdf390402848fa90223eaec3d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/logging/FlowProgressEventLogger.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"78be95854aa5d789040e8068e99d5a4845095eb63f7070eb0d3ee3361da8ebff"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobScheduler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6163366838b7512b0de10dbc9ae2eb078a6dc506f46954725cfc3be2a12381dc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetColumnsOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2bcdc400452100ad7f19bf169e0582c92d732cc31beabdf6a164b4bc1934e98"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SchemaPruning.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"21fe418482787ac6a6b24f12e16b5716d27cd2a6ab35ca5dec407e3f1a1dbbe2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/BlockStoreClient.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"871bb7e649bc19f2782ec71ffdbc9ec0e56f8d5e4534a629a8f18504d172f87c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/UDFRegistration.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf4f4624e5d360e78aad02448d9190c715c4ab0c11f7a582060e46cc322e6bf7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/EmbeddedArrayJsonDataSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c3fefe4ec4102a4d5cb4682db6c48bb3df7b6f2d24cb0604dc7baa96b479443"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a92858420585d207013887edab55dc2150914942123803f6a562937016cba56b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/StructuredStreamingIdAwareSchedulerLogging.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4c5f3f8416c67c1f3984b2841f1525a075d889b2f2b017dc0cb6054e3fdee59"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"31d841c353608e5877aeb8c994773737d2842dc7f79ddea408c17026ee3653c3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaContinuousStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae71ef7c4179e8024962ffcb855507c282866feabef085a6bd6c96233484bcf8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/submit/KubernetesClientApplication.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6468bc8350a8f4622ae5ff730ac52a588f2928d9d911a2288086f5f8bfa38d8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/io/FileCommitProtocol.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a18a1b5b9029ae14973343dc35776bfac50fd23e7630ff83e2849c2cccd97f7d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ArrayOfDecimalsSerDe.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e27c77eb258ac3ecfff632bf18f0ff262dad22345c640360ac322721d328c01"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdb2835cc779d172fc2864548c3381a971d80191266551ea9bd1d1737a4af491"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLShuffleMetricsReporter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"999f09edb62e5f279944a934fde254d36ddd0b7cffe11a0a9337d792911dd3c0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/urlExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcdac112e654293581a398da40a19ca04ab43d0e52d5af946c2018cb04bef47e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/FutureAction.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5255a23947874679c5f862e34196923515706bbdbe4a948d9c1e29e1b5caff7e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/SQLImplicits.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"afab0157535b9f163882aff779c09bbf18cb400ef587fdd01443c1d994ac7469"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0264f0d588dfd5ccf21a93008e385ab53aed9f57e8ceed16ab6b5a1de7b9ac51"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/Task.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea7608b0f51a7758b4c89d188aa45af5be985e761daeb90c10e1bec9f4af3a0f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"080ec8b21ab67ff55e91820daf7c0b0d7791ae3bea41ffcfb2fc852c3ac48509"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a93787463628a56f8b39a2523b4abcfefb71de938066f06a443923cfd81de1a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/AutoSnapshotLoader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3b91d41cab4ab8275a949a9b53cbc50b692f9abd02e0e92ce45037ab812ba86"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/receiver/ReceivedBlockHandler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1203054a8fe76d605e187f4521c0ea7429ccdaf07ac30994d78739958d49b078"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7af0db67eaf0128af53f95936cc3c4154faffc5b4a69cd6dce811fd560f3317e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/BloomFilterAggregate.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4129398b90481c8147f858a2500d52be85fc1ee6815e517490af666917d916e5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/plot/plotly.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"187b2632c5f42ea4a1a32c62c8724a65551ad51a6fd1bc00492c427e4e753108"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/server/HiveServer2.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f455460f30b8d3461d233f04c1809e2a17ff4727f0fad4f7b4979bd3a0ef99b3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"242c5018d646a73ae83d06c08ef575a553d8ee286e441fc7776eefed13982a46"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c68ab17b6e1b241e435b620030ca951eb8896252365b2fbc719e0a8c0a2f2e82"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/util/NumericHistogram.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d90e6407c4a211f88e433e1924a3aadf73d355bf6beabde0073e51a08ce5b0da"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/ExecutorAllocationManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"88fdbd7f3e709a369ab6ee68f92d713349a7416298c0c72f49931f17600778fc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/DependencyUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"145f4260efa3f578ffc1b0913ec73beffc212bfdec3c8ca529af462de4fa5e67"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f83e983b2e444de98674362eb174ecd369892f714d3e3f0d0ab468dfceb25d98"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/evaluation.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f523756a0f8b2c844f557b15348c68c752ed02d8b2ff9c0f462df5aeb696c9b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3da420c68034aeecc6b11740d9e824ab15dbe83cfd9ce16cc082707a845570fd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/rdd/WriteAheadLogBackedBlockRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a61fa6faeb97d411c34c86f7ffa05124587c10582b049cda3e1860d60ddaeaa0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StatefulProcessorHandle.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"78e82607a2d70c2efaa63219b951fa3e3f1298958cb0ffac4fb422499dbf6af7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/errors/SqlScriptingErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"766486f5ff33e120e179e4a4b137c85cc268043e8834e4081c9bfda756dd90b5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ExecutorResourcesAmounts.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2769acd8ccb66f15be037e1bd5ebe992b1a891c4aba5328ba863024bd835fb3a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/OfflineStateRepartitionErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b3cc5c166f3eaa7f214006993e87a3b2ee40a724e8238e88c595530ca90d227"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/BatchedWriteAheadLog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b00e74f88cae4f2658650d13729a7cacd3be9e4d584e5b6346214597b7a31b1d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveTranspose.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ec23d7fa174874abd2247377aa5e5e08529c7d90041f971c0191a99498bfa82"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/thetasketchesExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e9efb6a00ba2d2487f80a564d740c4c90ce1f28b27ced39d535edc65e500403"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2230ad886e61f2e8db26644390e9a1b4ca8669b944798a0cd45dfeb6d8a8f7c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/DataFrameWriterV2.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ddf9df38ef77305d1e5cc065ed6cc8075b0ab9502cc64a7795974ffde172cb4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/Instrumentation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"21db746704c815abe56d7e8e4133a6eb5b972606cd648fb5ae417bf07dbd8fb0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/java/org/apache/spark/examples/streaming/JavaKinesisWordCountASL.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe82888986f540a14dfdca097bca9ebe23aa2ade46ee866986fcb1e598490cf2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleDifference.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"28e0acee18df7fd66aae787bef1ac99cc9b3bb898d07077e2d7c68238dcb9260"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/expressions/Window.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b62c9b6763181b42b7aad212698259b8798775d4358ce8bdfd2b3dcc575f278f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d358ab4a8c8e8ce453d914b84e9f84689e8cf7ff2aef124d07567daaef2207c9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskSetExcludeList.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf46173c25b2f4786e59b09ec1b239251380a65581809c655608cdd8abc0c993"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveUnion.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f40fbf55938736f5d64acd98d10936a9e77fc3069e1d6c94980e72fd1a91ba0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/missing/indexes.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a2383c7f7e97b51adaa678f5361568ee7279177a3d8d685533ed8edcc98d8e0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/SchemaHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f17cd6a9487ab36dd89e75ebcaf03cdaf49c01935c101e3155a81cce959adc55"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/python/MLSerDe.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcd45833788212023529c54bb2e7df762bee55dd7b12497a33f2af2f817aaa5a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/analysis/DetectAmbiguousSelfJoin.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d77c173f12c378bb6aea6cbcf05bb2f279f4ff8bed47298dd2ee9b5c66efef88"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectListenerBusListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fa6021d77d66acc0f79588f46f89c9559fa1bb3fb8f5c544bc2bc0548bd3b32"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/receiver/ReceiverSupervisor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fde320f98c35127a7b039c8690a8266b56c77faa82a5b7e23c4646944ff81c5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/ShreddingUtils.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f80d09f05e281b90045644aad787905e574626a5fd189c579e9cf6982f7cd434"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/plugin/SparkConnectPluginRegistry.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"581373eeccdabf919403b0cacbba4cfc2720b02e98c034072f2c6c35d4700cea"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/create-release/generate-llms-txt.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"38ebe11d4615f4f4daeb999a167a78306fb795994b15ad22e35845c117356f7e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/LogicalPlanDifference.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3ea65dc9580a1f44be62a974ad0e0cd0913bf7da74d453c3169d0b04c3f8009"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/ssl/ReloadingX509TrustManager.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"94f32e49e62f9459fb378a9f409a3dfc2413cf61d9d0e555f19787bdbf8bbbd0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/AllBatchesTable.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c12908f1018bb501f9a30a614ee0b9579708b996ea075e172830a1f611d9a47"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ExecutorMetricsPoller.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cc6a0a295e110ebff1e97d3e42b66925b30f39cf5ca1ae12fb81ae8ed730df7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowGroupLimitExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dec6606eaf7dd871f08f91f10caadff70b3959d6040e37a6ff859107cb8b36af"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"04866b282e15657a9f94af3bac272c701b7ccc438276289df6099f6f594268d9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/encoders/OuterScopes.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f45c6901b73c6471334f7ce111cb14953292aad979d8191449fb790d759a84fe"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"957bc192a93e8ea4764278343859801f94cadf949bd3de4f79cadd9533e58081"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameReader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb3573246acfcc2d56a969ef02b9225178a228ee2eaf2949dc5269c13215d9cf"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/ShutdownHookManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e99d2c2f27d43f7c7131146987e2631704ea8beb33d16861b643a321e90fc79"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/DateFormatter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"38b016a9b4a578126ccc80de792c24664e37eb793c82fca289fc2c698e988af9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a9ca8069044f5dea50f5025209dbb1387fddbf57ce7ceb4dabaa5a68338175b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameNaFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"371384f97c9178721a5dcacedebbeefc7be8bfbe7ab0d97e3b576126c58561b0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/kinesis.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"901ad2824f7db36d9b1282e9b356a91c7226b0c2e3d02c3f59a77fe6c939e84d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5aa5e890ff761d99bd123736c007b44d6313d376c1493fca6af41b4275df306"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/shell/progress.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa33a265e9bcc2d223b21edad82ad01bbe217adb1d6c25365b5c4febfb15769d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/storage/StorageLevel.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a0e6746b64992172b455193f023eb1ca78f8cf9cb76964d9e680af63ba73fa9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"927890b552bae658964a715cbfcfa97186eccd3903a27f4e626609bbd9d3a087"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/status/api/v1/streaming/ApiStreamingRootResource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"88098bbb9205bd78a052a328f911338c8e48f97c247fd091dcc3e52af8595f57"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/ExecutorSummaryWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1bd26e3f1a98c760697af15104326d9788b9b2517c293a4eb877283b21dfb9b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/events.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9595bd0f83f5780c215b8d409c1214013a20b2519465a6bdb9a62007e3d505ff"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/util/collection/unsafe/sort/PrefixComparators.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e14255b54ed831cc00b289fe02fb987f6dce955edf5ad80f78893627e9a4f25"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/r/ArrowRRunner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"471a3cacd29d13fd21c68c5c9dd18e4afcf935c16630180582d30afb4466f5a7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/metrics/sink/StatsdReporter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9158b913258f9d65ed74f31fc02ff686b42120cefd0dfae51aa7ec67ef15023b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ShuffleTransportContext.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd32de32374f51701a31806c227b7339e5be05d6adca96690484c05fafb069a8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe4195e30b45d5a6d99defd9a5953b4904d72e0813f2f28b7eb5e7b5e4635d33"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcSQLQueryBuilder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"03b44ffdc76e4c868057015c4059581e17966119dfe80d27cd5d4b890baf5ae1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetRangeCalculator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d73bcb0c6eb044f975073f75022922652d1009b47d2a30d91ce7ae8a38ea1e5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/mllib/fpm.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"11be4ab9e1d5e72671713781f553ec5077c7d16509f529e326ed49d59983dafb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/ElementTrackingStore.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"16825a9f94e685c9a9eb8c05fedd186f06d097b3f41ae7bc1c06933425e04845"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1f323f1be2261244b8ca5c2e85e9f6901aca349b8b21a64ffc911180be1228c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/producer/InternalKafkaProducerPool.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc62000dadf21055f00cf143308aca3230f3b245a521aa50db07c07506bc38ad"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/SparkAWSCredentials.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"909bf760c3100a94d0dde0abab35cc99845989375605c533f22c16f442710a8b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/codegen/UnsafeArrayWriter.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"236960d5a75e36a1c4d33e99306847df6d2500cba59fda6e23bfc8f498537893"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/plugin/PluginContainer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9138f3c9b5d5c40213481aa044ef2199e51c49b25214e2c3d35b45a2818bbb4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e74e6be94535a87cf0a5eb11370ebedf17b509f72d1e48ec22f59a51fc535380"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/EventTimeWatermarkExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f90925893d18c8246f3388d1cc644290ba9d4f52522904e35758a1b7579e221"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/checksum/ShuffleChecksumHelper.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"68b007228b2ec1625d37fb554826a7de471172964279294a276f899f662da324"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/DStreamCheckpointData.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"08dd333bb219a2f889594ae07da6b092be33a30da91cfceff1de4e1eca6a0e8b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/DStreamGraph.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"af1465233c511fd6fdc543f5c11550740b5a9c0f088bf118c697c8f18c66c7f8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/api/v1/ApiRootResource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a23c5721aeb0f1b4518a806b29d3f5d17c44fe6ec02583dbc8510b20932055cb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/RelationalGroupedDataset.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"35a45622605b5dd6302a30019b98d27035eae51358877eb248534e270fb49595"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dfee77759ed8721f25cca4e264ce9233e538887e1906c0c78c1801b3e001424"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/FileStreamOptions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4ec58768fa3f55dd1bcfa023e4d411cba7db9b2be2b11f9276a35de225dce6e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3248b612408554b6d8f8cbb2760e14b45eb5c4996682958f451ecf417d72452d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfe42c2f9297f3d4206847a89468491e66d49bcf8f5106b069075bff275bb622"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/execution/ConnectProgressExecutionListener.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"571493236fefe6ebd0017f01d4bb52ef91ba172ff7350f5e3a3db5f7ecde8f13"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PullOutNestedDataOuterRefExpressions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"92a5e3b6cc755517864a1ae011d70f34969de540f14fc85584af2392c7695768"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/Main.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e86c560e198fddf8f42227d82f8f841b1d28dd395d03b422864201fe95924c6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/rate/PIDRateEstimator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5c3c26a51fa3004099540e583172e782f4ab3251947c364f776dd0d49beb082"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/NameParameterizedQueryResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b3a72fa9682a0a97218eeb70d8f851252b4edd6727d2c345731fe56b48aa3c2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd3f6e716d7b61df334befc8f816190655b1cfeb4c6e919c5a776b551e3cd567"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/messages/zero_copy_byte_stream.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"341f56ae101edf929b48e9c140851f4c76a92cba677aed247e5954d70a157d12"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/ForeachWriterTable.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d508b80c84d244b25031d5fbfcee8f01628a2204eadd40a63d2f3c7e46027f1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b750f5b72c995f8a15d53078b941c3db70d3016aa2aa48a223bf686d3f3653fd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/consumer/FetchedDataPool.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"624d29252412d26836e61748fe8132c8b9a8ee686c05b0611f1fd2506a78182b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleSketchEstimate.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab488ac4b58e89965ee0f72a31092dc810a13894732ac5984ae6d2357a7c171f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsNamespaces.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2211780f2088919f540d7ebcf5d17ab049b73be0b45e4116e9b6a3d090017908"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/SparkParserErrorStrategy.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3a7aab0c1a35fd82c735fb00b2b9362172891b8f867595aa576e117f0ec2238"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerLogCapture.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc0395e79bbb0617f6473b56b86277a74196c7fa10596889fdb5c9a2ec53790a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/streamingLimits.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c30ef0f41d3625f8d2a0cac4b87ee7329a786d1f05d17ad1beb3cba253c8a36"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/check_pyspark_custom_errors.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b7cf6adc1997a265dc2d32fb0e064a32c3b3539e28ba6337a8f5b149b53396c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/analysis/alreadyExistException.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"11a0cd1959e7dd7f29babf6b938e51dd1326989d077f77189998b1e04a989842"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/SparkFirehoseListener.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4210618f4273232bd837fd4c446461537c8f798a4de971c2d447219f18dc6eab"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/EigenValueDecomposition.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"95f4f3cfbff77b91f609ff6e1ef8e07006e1bcab860a795da0ef2cfe9ca1303e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"94cdbc15a8ea2ed30e8d1ebe24380acb1a99b718b15c7e03d4f1b296608eb7a1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/GraphUIData.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e62b93602679d8fbafae4e19c61d84b381c44a49754f1d5ca415cdd5594c6464"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a6b45d869a34880ecf7f8f383c79f6796bbc9d412768a0b60d11177707ae028"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7bfa004fe5041a3ee30b203be522b702faef6003ab489eddf1437d6a38510fa4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/V1WritesHiveUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea69caa9a70ccc9260e47c3b5aa78ce27988b95d61bf93e4e61133ed0df302bd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/Expressions.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d8338d77cb3812e55cab86bc86f9af246da3fa10f1ea4c7c37e556d32d93e9f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/instrumentation_utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2851a548e5ace6693bd8a07d9dd9892bf09d94c494e2f6a74fa3251b4cce1ff"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/PivotResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0a2974fe0e481a7d5a83b7c8d9e213d90e15d57c51a60c69476f09234275581"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/deepspeed/deepspeed_distributor.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"86aa8f983163b1caddafd0b90aade86cc3a78fd0c4d02c8e20b669d79da96133"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/UninterruptibleThread.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc6416a837a37fd6e9a5fe843e39c24e538b050aa6ff9851a4244024e0881219"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/util/ConcatenatingArrowStreamReader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"be33da1b9846ceef104b48d5c194e1e9a6c576a321f6f9dad482141600f2068b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/streamingutils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0c903673f486d6cafaa5413dcb36f5a61b3f9deab949d27f46039e0ea4d03be"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/resource/ResourceAllocator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3543fe90397bc3143ac7e13d0c1895767d05b67c795dd9f88002b967fbe23a6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/tupleSketchSummary.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a06303d3cda6c77d580f3ed54a4103094fc7cc566e949f4a49369d663105c4fe"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/ApplicationHistoryProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b507b9ce304b8751fb222fba9be87e6c52c14f33448653d2b0b629fa9edf60ba"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/metrics/sink/PrometheusServlet.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"03f846de376ff0cc2b71488be7d63b672d99dd769c3336efc236cd1edb01b91c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/types/numerics.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f677272c7eeea7f9bddc8e643e1164d6f21afe08ceb853f7be1ac2af3bf2ba92"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/security/HiveDelegationTokenProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b0c0d57f930313d5cafbec8b9b40b6fde50081f12f43905f9b7bb66f580beb8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/NormalEquationSolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"83dab99172757cc4f5070efe18839aa1f78e2aa60c979ab76d07984d3f4e3a27"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetFunctionsOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"030d35dcde3c79143acd1ce11279b249f09e679a3ff413af6df6be8b464d416b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/conf.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"332757863917dcfd31fd1b1c21d7f714a0a1e7a2ce793ec954f2ffe7b81030af"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d2a3d7f9775ed14b6862c32540205e7d27bce72d52e0d40ed82bf490c00ca48"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StreamingQuery.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e472251445935d3e077901364a0e478f3f69676d28158bdb012d97cdaea27bf"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectStreamingQueryListenerHandler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a52f37d27febb57dd2197e5b9d874f9bafc83eaf5608f7c4ae58a0d1249cab1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SubqueryBroadcastExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9e6a507ac0ebb0d9297ada1c4d5ba8662fd95b2f61cea36aae181b2984bddb6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StatefulProcessor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1f0dc34327037861311b000a187c82801115bb946e28cb90277af498df43995"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ProcfsMetricsGetter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5262f6bad47e1f908f4cd8fc0bbe5477634d24d9550ed1c0850268327d5f213"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTablesOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a675f9321a3148a840f75d93b74ad6800d0badee270ed4fccf368e2519f83168"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c835c974207c62808fc4569efd82b7339694b06ece230f47d00a356557b8c4f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisCheckpointer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0337fa353dd008e219998e43a011fff3c5596dc76efea64aec5b0ed432ee3e53"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterBase.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c24afc74cd1da3e942759245c152650d578117957c24f1e91a410e9994c492b1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"814237ad9b6ac60e44568a8a35f461d8d185857f0c46eda28057071e60f4176d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/RDDOperationGraphWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd8e8e6b19b6c028ee76dde1f74b21dd0ccd07048c79f9f5d15c852b67373a3b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8bea1f415ad57e188c8b6bf2779050c25d01452261e3ee51d1d13a9adfbb41e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/EvalPythonUDTFExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c51a62795d88fe1493aa47a7b4a158cc19299e562920ea5f9f5231e6ae975c09"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/master/WorkerInfo.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2634445690e672abece0ff78e1c4af17011f992b11fdcfd37f9d8c0d6c570a13"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSession.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a665654976c9798c755a959f3180c0366d0bb2437bc58fe02b2043b4d277e53"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"df4ad443685d12873bdb94db447bc561e53c4f3a99de876099e1bea579d7de1f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/VariableManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8af41a54b41846bd199bf1758a948ad1726b7f8d094cf3989b2679293b6b659c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/IllegalStateErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc39a6ae1942cabcb52fdcf0e368422640e4559b02901f413111a63f846804f1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/PipelineExecution.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"806f6d1a269616d7b37e9e9783f9429eb500e2d4cc4a43e6ad4a421d715e1ff6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTypeInfoOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5d260c8cd4061c45ecd89a5cd26222a0f89c8574917170d1632e4d5c12973de"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f179d529cb49489b6ae1e3baae870be22636b18fc1b6407417c62bc8cfcdee82"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/MapStateImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc77ab0170d12739cff5896dc63212bd20164bc3d447a1e611b1379907b73b57"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/ddl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cf070431c22c35dcafac7760acfbc7f28d7d7d7766622e7b5321c721021af24"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rpc/RpcEndpoint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c065b9b0fd1e4afe1a66093ba71d1ff2c4b99e54ad59cf69b8a8dadae8096ff6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClientParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"655021aea12845eb3c4c1b2981b0743e0a6bdd2c46a4c25eed22273a1fc1ecce"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/streaming/util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dfd701146c3b479aa28887c410d08f40d6551cacc9a510f241e87b80926fe3b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e882b4abacff08fbc84a39b8f146ba9bf97383dfec512372321543210378c6d0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/RDDStorageInfoWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e258cb0bb362acf2db0a2109e175dc7e65c2816901bd3ba0dc80ec9616d7ff4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/dl_util.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"37beb3e3cb89e53f5bd4018386e9726b0b15b0118d71c4afc8f6913504eaf7c9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/BaggedPoint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc3a17a5a2ef18768bb23cc576f078bcb19941e5e206cf90954d937fc42e4358"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/optimization/NNLS.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f864744a587a96ea05ae3023de1604d13da1c285c58e9177893258f427dde82"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BloomFilterMightContain.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0834d0895ded8d55875e105d09feeb83be89d2a73dfd42ea0799a96d6f7e9918"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/categorical_ops.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e744f33f15635961b0a2d65446a433901278bfc2e21b9d19b66d28bc8f4b5f9c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionImplwithUGI.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6ba925dc0b443f57a29c26a76e8f9415acf4c178fdd8eeb9acea20beff82118"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc9301e957a0542d502834833ad61c87c565abda91ec32a6bb149cdc784d35e4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/broadcast/Broadcast.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"973e4e4be802fba8d6373e5a9d99bf55ebf48ae7bd27c9c1d43ffd1739e2dc4e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/status/protobuf/sql/SparkPlanGraphWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8b69ff961944627a80800b46616f964c1fecce8500444e8a8ae4077b9b544e5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/ResponseValidator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7cd4e03ba4f72568b6df8a3d45cac98c096af91b298a56064f78b257d32d2c57"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ExtractValueResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddf096472ddaa57260106cdc6c8cdd31bbf15cb7e59a9d0b49cc44fa19d1d2f4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/streaming/value_state_client.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2faf379d27310aecb97170eab43ceb36ab954ee86080da25d4d6b4a4a4f8a40"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"23d768146959ff1a4c368f638dfa5c83821edf1df0229d89791d38dd200d971b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/protobuf/functions.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd0448d7a62df801d907964a0ed5ef2bdacb89d1714db9b2956bb2fd506dbd72"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/StreamingQuery.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab14a28b0b139ae2dbe2065521f8a88f1c7cf2bc587be6ff7cc5be4f57d30455"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/HistoryPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2acf1f7eb3f9bf86e38ca1ce18dc31b5c7058c99de100907c6346f2654f28597"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxMinByKHeap.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dca11510d944d5982ce1fd45c72235b3228d388a11da4ddd53c6a33cc778e98"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/pathFilters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"86728a7e30b96909baf89a8031851c03cb9ce38e56de9b4226bf538310ebef34"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/shuffle/ShufflePartitionPairsWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac6bb1259e3eabc6c5772ed4ffc7e65bc5a41e987ac6f8901fa4e9fe159248ec"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/TreePoint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a837adcf4f2b598e6f18616f4d8e6c3ea7919c06a0a44decde55ab41b79507f9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/variant/src/main/java/org/apache/spark/types/variant/VariantSchema.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b331f8f1d3cb2c7b4e0e014c581dbd5eb3917baa0e3ca8e0ddecf5b79d2c9f34"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/OffsetRange.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7203f7eda31d7c2392fb094439345097c46d917c1726d3348e75999272d3d88b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/IndentingXMLStreamWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3a630f196ecc2b948618d8d6cdfa02f647d38a987e958ca212512a4060130c9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/RuntimeConfig.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6029c352496eaa87f926ecd6500b7d6395f2c2c94cbf89ea4b47f5c63fab0a4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/core/status.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"89dd492f40bcddad9aa7b03d1d745733315bb2f0d17a5d8ab2dbc742f76c111e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/gen-sql-config-docs.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"88d9d6fe745aac8298b1c302a53b8dcdcdcab06efad5859278f111e772a13722"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/LambdaFunctionResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff44db184264da749106a6860303ea1488adafc37f491bf73cdea1e825dba3a2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/events.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0021ae86cc7c14ae5b83d01b0e469a50c4a762948523d1f7fc22dfb6dc4d368e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1139bed192ac00a467a91f6f8b0e96c73968a5726d4601fa7e9a5ade9e1646c4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/date_ops.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"38200c526334778730dd381f9d94f6ce52c98e7d96d6ef2ae90ffee82c62bdbb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/expressions/udaf.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c03d62202802e1c3e7dbe6e2bdb9c863ba304c523001c9f6762cfef50b1b3574"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/usage_logging/__init__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c888a66b89d56fcc5e68cbaab57807a26b7869b0b7f3647532fd07baab45ad88"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/EncryptedMessageWithHeader.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"86f1042f6d14d822e383ff25a352d082329fd54bfeeb71439a1ea9bff551782b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/streaming/StreamingWrite.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e38a521d22ce223655220c0504a9cb803a5411ebbcaaf7a04b230b4097290a0b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/SystemMetadata.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d984811508cda154bf0174b561444449363f7fbfd712dcdd58f46d576fc58e70"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/TeradataDialect.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"89a08d8b2f78e57b93924a9c0ad4a5c48fe59005814bb2067d9b012edd6f6823"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsSnapshot.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9d38a51d40ed422dd958c2a44b4160fc272230e4f22b7955f1e2c6253102e61"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4410efd5b4888fd7a2c36eab4b4ca9421bf5d4c40eab78b7a060d57a82bebe04"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/SparkUncaughtExceptionHandler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"622add4458b8db9f89eb5607a57f1fa194c6e4b7cdef11daf98146c83a94076f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroPartitionReaderFactory.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f7590b1b9574764d5c39a9a438e7d071a4dbca4644bcaefdb4752d1c1c7cf45"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/ForeachWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff82da5a06d827d8b101b7dbf6b92171185fd7c1924de010e1283198db72fe97"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/AbstractService.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d9fbe8ef003d9254f30b93e4fa037094ebc7353377d0aa9e47e700c4abfecfe"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csv/CsvExpressionEvalUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc45756cf5057e556797672ec7198ddae8346b128e5a3e82ce3a4d369597ea1e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/VariantVal.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbd19749c9b4c48f351a3bc1befd0823025c2e4d5e0f15fdc7ba0f7cdd5b3d95"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1925396bb8337f217af6b46daddd09121625290265d1171587f5c9000433b786"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImplV2.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d68cc1c64c9cfc34a374b1a618809e5d62b3e98de020ec6230396f0374aa736e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/UdfToProtoUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"609e6b2eea3c506b8b9cc5e70b19625eca95721061a1d73c6710a8371ae27b8c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/package-info.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e207609cb34baf88a38dac7fe85c74f125112eee2b79ffa8946ec7ece84627a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a40f2aa61eaceed545f85bd143c212af6122295a4b28b444f81485af6ef2dac5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fc8de2492c1760e845647b6551261f7421e4d90d8174b8de3b3ef3dd5c7be01"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/java/org/apache/hadoop/hive/ql/io/DelegateSymlinkTextInputFormat.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1573ce3b595eb5a5c33f2d800b3909858e76bc59875c0e441404517c929e1bac"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/RRunner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3262c4e323ed14d67f05eabcc4687cb45b55b1e37cb49f8d511d2bf27e97245f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetOutputWriterWithVariantShredding.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"817ee913b9195f51549af8879c3b5b5aa2575db315490349d15cadc42f6d0f8f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/NearestByJoin.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"29d00e2b0e4f88c856afef98dec44539e049020493ca022622eb2fd666a3988b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/url/UrlExpressionEvalUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5dab17906d51b52bc06b814f37aedae763f5cc6f2cbd7b75a2205899ed5f92f9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/sql/ml/InternalFunctionRegistration.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"88ddc437bcca258614f2fcb56505f694e388647c129f9546b313b55e6b5f6c35"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/MergeStatus.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ee8f88ce582572967ad0ee03776b986b8449cff2e9520e6699289c943d5aa87"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/connector/catalog/TransactionAwareCatalogManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"532175484920b9855903e87e3fcb0bcafccfc02c3dd436bed47d542b3efbabdc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/expressions/filter/Predicate.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"48583474b6c18cacfe03f5218a59ab695e0d4e5ec458c07a4827962c0ce02aa4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/json/JsonExpressionUtils.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f750f36dc35a0b4a2d76570f539f49a41ce95e7debdd5515c8326aa2194c646"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"29734050500d84314ea6bde8113bd658f5f47e5f274a33ef4964df94142718f1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/InternalAccumulator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"697f9e3d366dd3b91e5c8759cd4ecdf1658cdaab25c276031ac11c5ab36f91a4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/ICLIService.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d08d8fe6f3cfa21ed2da8a5e7f9e2710abcd6e999b52c44a4529d205037aff28"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sinks/FileStreamSinkLog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c41f96634a4785cc28ca7b0a49cfe67e3592146e22a39ab5053b3a02d25ca34"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/InputDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5cd63f637edfad5d465ad0bbba95b7cde8bc1f4e194eab132fab79a7b9611e1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/UserDefinedFunctionErrors.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"921297550917416bc380f96cec94d1b1ee4eace4a46109c2e755b5688e164d68"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/modelSaveLoad.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"32dd9f74e3ce9a2da0c76657c02383d728851b5e9de4af9fe88d3cdb0ca91ea7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"54ab9f240555272d20e7ff47df4ac6e1f32a335fd0393345ace63401f659e431"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDeleteV2.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5763f67eac7bf93ade120820d7ac5236e30bbf619d02fc727906df200b533b98"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/protobuf/ApplicationInfoWrapperSerializer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7310538673a66c2bbeb17fe518c930b25e2c785b420e3dcfcf909990f8e5789c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskScheduler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfd6d7ba6d40df3d3cdd4d91d8c215628b0ab5ae4e669cb47412dd7d376fbad6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ordering.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e1b90f00bfab22362d96a93912333b3d6a8976c7c2272d2abc80373ab10e973"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/rdd/RandomRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5fee8015fceb7efa6c8b130b1f944f986c37b7cf662a361a80faf7440bc65622"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/OrderedFilters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"633126f6c601020d09a7bd763d37a4bb51f196fcb5293ce51c05de47c2a65ce0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/LocalDirValidator.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c7ac4714d5d9d75551558bf339cbaa1ef466ff12aa5cc7c17803ff5cc172520"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatePartitionKeyExtractorFactory.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb0274bcf75226499722e19038cb323106068afc1e45fa5c1bd6e5ccee2c98fb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/MergeIntoWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a7c72447815983854c49c918f4d74c87a1fdc970ea02dd5c84c0ebae088b06f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/lib/TriangleCount.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"57ad92d96c7fecfbdecc434fbf9c8f584ddede0438913b10cccd141816bba6a7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/block_session_mutations.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d248b0f1e58bc43c937ccded9b4da3e918f66b8dc0b86204ca5b331dcd3a3a4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/externalUDF/PythonUDFWorkerSpecification.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ca676bcdfd64dc6a03ed34b56242007e68e60764f971a78a8b17c4ae00fcf6f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/summarizer.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f07c1ac4db0a3a0122358a074160461562621f2baff77a31ef45dc316f27ba6c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/DriverCommandFeatureStep.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"54313ecadc59eced128ee800c52f1171f979b8c2c66e8cf56eb5ee74f0f55730"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/SslMessageEncoder.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e8d0c1ae2fd89b5c448f41b12a0a28a91fb8bc8e66f150a8c3b8c73da7157c5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/MergeIntoWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1bf2e33dee5d23197e723e56dd93edac9cc562342d02444854eb07782ecf858"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/EventTimeWatermark.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb2508a59df53a0c94e44eae5bac93763f02447f6382188c6e96c248c693c341"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/CatalogFileIndex.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b31287d32793ba8072649cfdcb639d01cf9838af9d0e4200e9324d8023bf97be"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/rdd/SlidingRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"77481a82bd094861544b0b42defa8d78800621a6a239f972876884002a0d4aa1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkStreamUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bee2ad88215ffcd0cf4d24dbe6cf83fa5af7552e23b76b18e0b228fc157a710c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/mapred/SparkHadoopMapRedUtil.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbb99f5f3e28f82255c0d8424f0fe53d82c9e25398894de3088b29c58523ccab"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/thrift/TServlet.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"837b21f6e07fd998c653abb8c83be00d3b481c2b6c959359681f11f427762ca3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/UTF8StringBuilder.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e702dd3374d364d63e18dafa2559c3c010854078b84cbb574193dd248a063438"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ResultTask.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"614dba6b4442ccb6f8ed2543a6fe71ad53361bdb47d14c6f2a3ec967bbad07a3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/InProcessLauncher.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d0672be7e7a70c73bb51f73531e644d46e6b99094722cfc6b0815fb8e5853f7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/GraphFilter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"85e042081c9012268c76c78fa271efa139e0384e83141914374cbbbbcbfd60e3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/interchange.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b96b546f40532e3bee3de58a720e110fff448b65dfa0eca1fd57189c06a2894"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"hadoop-cloud/src/main/scala/org/apache/spark/internal/io/cloud/BindingParquetOutputCommitter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"60c23ff9a7fc26181dc79928769ad11d4bab89f8f4a3b66d1113342a48cff3db"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/Pool.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"82e0daa522d958d1320ef3c576b58f24d09705aed7940bd737e37f0fc490ea9a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/MapType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a94a1eb75ce80137b983c89a2a4b6c12741ce0eca26a77a9cc6cbe783469ab87"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/Transformer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7883d77dcfd23b30a2ed2fb6fec64c0f4724d86fe83e8545e3323340aa21e9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"975d081050cda559ca31b9dbaa9ba850546f9ccf082e9d810740abc1ab2d7d06"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/internal/io/SparkHadoopWriterUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f64578286a016e4858ec0d000bc49876478680232ed391949b0b9e458c577042"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingLocalVariableManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"029f5f03bd3c00ef916f91bf68ab8efc28cf45108f6be6b4afc3d6c8f0a7765a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/LocalSparkCluster.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e92ab5166fb500e6718ea1550aa28a41934f876709f7b9325bcdcecddb2c2f7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/ToolTips.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7234d1a9f9dd3612e0ed5b2683b07182d533b600381b382a85fa0683fbf756a6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/table_arg.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a56d532b96b7ce923ee49899e7db9628c441d524eed15ea3cb90b61b4858715"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/PartitionTransforms.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa49304947c91d7b9275176462e7d9c56e91ef1251f0f16e09eae4e6375eac2f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/RecurringTimer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3e0d893165fffb497abb3ee097f41ec05d7c8ac30199760e21cc92f4fb375e2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/FlatMapCoGroupsInBatchExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ba3485639ac792f3b100a8e0f389e1878ed863d467a5101e3070e65e22f5c66"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StatePartitionKeyExtractor.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"456642a7cc051b269da603423b499bdd169660c396232ad7fe55e74bebe81081"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/EliminateResolvedHint.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2baa77ebd522a4918a6b48e1ca2d3e6385c545138019e8d84f6e167eaf2a618d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/image/HadoopUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dba1bd98d11818cd736af059b82c7d47a9da4eadeb8ca68c36c3917a63d2e19a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8acfc1dfafdac107324d83480deec7574581f7344fbbdd8249e3281099f3f7ab"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ThetaSketchUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2c7ced4510585346c4b9a13c223061bfb1bf44044f4f59b041ecad4e015406b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameStatFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"334146a30e3456e3f39c53a13a110674d3a121c173009bcd50690b88d54f27c6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/sasl/SaslClientBootstrap.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"55f5d40bc26706043069da2b3e83ba7272060b3279d5baf4ea5f8f70e923878e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"launcher/src/main/java/org/apache/spark/launcher/SparkAppHandle.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee8693d2af6496590bed1d567439be729146f63d2847f7f0b8540805f65fd30b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4218e17e292bf0373a36afa8f2433b3e9a655efb8a14fa0654630b2a38b62d33"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/stopwatches.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"67f0ccd57ce1e9452fe92f1855cb45e54911c841a9e971cac16eb9bfc91ea08f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilterImpl.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c8430ef0eb20670946d1d397ad7450e027d7017f7e1a92e9419e18e44225582"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/package.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"00e6d79188ead2f200a9e187c27baf27983708f3080ccfe1f6746e91e51c0ebd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtilsPythonHelper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"266b9612b6d3d57ea30b66cf233eddb784d10c9c6a96e028024f2b0d511d9330"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/ann/LossFunction.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e800ff4f3e05f0e80ad43154f823c6e13145f5b6860a3869dd03ba870c1a5bd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"92ea5f9ccad23b4fe271fb48506e4e98186901181094a50137abe946b9347b99"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/internal/typedaggregators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e457dbeb1581a9f20e43f4f08de14bc025f50635c39cbb0a1b8fd18a4a1256b4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/SchedulerBackend.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d357e3d586d5d964f6093f6bfa829b6f7f1f0171f52a8ac2948273bdb5a327da"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/StringPromotionTypeCoercion.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"faf41c7bd25d3a775146a2b8cceec2184f3e6e1d7f765434d49e4dd95f275425"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/CompressibleColumnBuilder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f96a74cf7a10d0d63da5c0c66b0801e591981e8ce50a5be7a7c7705154bedd4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/impl/Utils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca457966e51c44b892186ef4e0e2d15b6a91e3c297c444813c3f66aba1f1cd6a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ExecutorLogUrlHandler.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e21051203123037e563357a6074ae0d13a67eeee040e723e2a7eea3a57e667f1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/ArrayType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6db8ca98a7dcaa0f5b0ecb20ba99a5d217a09bdbfb1403923fca7fc3edec4108"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/observation.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"66e9ecd01a193695d8dc7d8b97f2881d153708328685d421eb64921dd4d4835d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsDelete.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5d8e30610bf89e424aaeb0505883bc9c736c57eeadaed125ce3873e7fb41485"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/AvailableNowDataStreamWrapper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f60de2cf4992a6922251b794cfbab9ed53ba4ac7efde748444a4a5cf631e03f4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/InputFileBlockHolder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"167f91bf1b441fe75a10bcc60a6061f3d77f1b7ab6e10f7b6a4e67c64d136047"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaRelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4530e9094e66f24f071287a49849cabfaf3edba2fcd5b9c99654ec2491444832"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/UIUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccfba63dd518a275b37304a5e7c84d6c99b8019484a17ffc873dafa756393f92"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/CompositeService.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b27412c6d5ca5f8a685ecfaf13d9691c9e83f8b1a02e801ca9fe805117c21aa5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a744867e09f9e6f2d61cb8b69b8b223927157239d4d2bd8c55fa646b52cef259"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/FlatMapGroupsInBatchExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d86c887f00a58834d3948b73e92cde539fcb85e99a65cb7dfe16116ecb553191"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/SQLFunctionExpression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"22edf4c408c6c7443b3bac6b05e4dd352176317a1811f118af5ba725d91b9c1e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/UDTRegistration.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cac65dbb20417d336943093e02c5af43b16ba48daf04c06b57112b14138ef23"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b81a389e73edd9046fb88fa7a3a7c324dbd8e10e4484bca815f06c2ae07a9b4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/join.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"388e9ca2b4c6dc8aa85a6174a43f4a2981e7b7d06f1a103f6404c017ca967707"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/SocketInputDStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"85eb18a11ce2404927df182f3c20f30d0f7f4c7e096eeebd8ad43b19d8d08b27"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/messages/spark_message_receiver.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0942c22c4a4e998e3b8488d7df65eb6ddd9e5b85ab354b285980923e024685bd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/service/SessionEventsManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a305c1469b94b9461d56587425cbb013685bb8bdd1dc8639ecff78551fdb4edd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ToJavaArray.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7964caa74a9324217423c05b1bdc5ccecf054b502ab29e2ffccdbb089732ea41"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"graphx/src/main/scala/org/apache/spark/graphx/GraphLoader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bca5c549e27994b03ceb941a34586b5ca956b47e2d006de5f1b896dd447a7dd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/ExecutorMetrics.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"658519cb58a1a085ae9aa029b034f2e43c9132b04bb50329e31b9ebb0b76ed97"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/MapState.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f30dff9029498edeeaa691607a8fced8ab6aa5e9c0d6fe093a8b5e93ae67f28"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/buffer/ManagedBuffer.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"746cdf30812402d8bd004958918cc709cf9d500217edd9498e651013638b6b34"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/StreamingQueryCheckpointMetadata.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b975f3f468dd56ac8c30bb0e790b8d595ca4873a6d2d07026d97522038c7758a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonWorkerHandle.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"54dbbe1f16a0471a7c94aaa2a15efcd0969885b7f580a71e2144f2823fb574cd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/StreamingQueryManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8c5b3bda2861f96e304ed1a23002a2b841d7090e667a3481e48bf0e96dca97a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/fpm/FPTree.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdfe38faf157f07d5b5d1a615f785ea4932e27ee54d07578562a5e5869822906"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-token-provider/src/main/scala/org/apache/spark/kafka010/KafkaConfigUpdater.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa38ac08207b5d90294f18cc202f436f0b638c0c25b5f9192b826ad56dca4a27"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/TaskThreadDumpPage.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e55f36e26d8b5821997ffd4892bc128b15ccedeac9dd42a9a4efb1dccea90d8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/ShowPartitionsJsonCommand.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"514ed071452c20b738642564749361f412bdb22f13a71de7cc86720737430a11"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe2ac4f8c2239a8617663d469600ff7f3fc39ae395a6f7461afe36ac6ff4df75"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/storagelevel.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c449ac1fbd9d0616bc087ec2242214f8c74f959e27df645723e327b5208e184"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/data.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c569d1fb89b15133490ac45bdb94a2fa461545a970dee8499c1bf3d7e83216fb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/binary_ops.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf3f3b3253b6118767bbb5dd4f2e82e052cba36186d35e8f55a920768d428c55"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a99e8eee3cf9f1f98524a066f4cac58757c7a49e32e339e3ffd2f87afcdf623d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/errors/DataTypeErrorsBase.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf3243df41192be2040a518a6d01c02b20484cffc72be634129c717cc8c06fbf"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/DayTimeIntervalType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"09a7518252b33acdf8a1931bf3bee5d62c859c3e6cf8a20bb231e0866944a628"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/transactions/Transaction.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a9c3f5b29fd53e457cc08e916b2a19d4434a39a5eedd6bf3cce107541363fee"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/DataFrameWriterV2.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"20aec6bcda547b4162cb7e851465e3aba1e0da1456e50de1480a5148057af382"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/HdfsUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"659550ab20f39f9449d1b4f6c966631570a7912c604cdb378b5b8a0697211146"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/PartitionedFileUtil.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5645a2972a4640e4a3fed5419d3c36564193cc3e375b5911988215064707c52e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/package.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4daeb7865787e9094254a712fb10eb43e5221c0ebcad996b9faacfa1bec3ff74"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/loss/DifferentiableRegularization.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f23d70a2fd1bf23e1516f38e20a1bb0fbe5e763d9ae476414d6cfb53a436df20"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatch.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"29d511af69956adecfd56da940dd745758d7ee7d4f3d886b1801a90079469ad3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/KernelDensity.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3893aca663588c119a91ea65ef15d4749ad0ce9df63d2507ded979dd770b0471"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ToJavaArrayUtils.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dff9db9bbdb1b4f78947b32d21bc2127ef92f0698c646398dd404e0730471e4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetSchemasOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"14020a5c7c58202049b8fd0d358e2bfef7e947dad1be5dcd6c277c2256bd6efa"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DescribeColumnExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"42187e4cf7c9c5d23d00bea7a06efa0b5516cd16a0c8ded8d9ae139d100adab4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/MultiClassSummarizer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"289bfe11931fc510207c58c6f893f0db50b20a1ce5ee2258b2bf05b881a80352"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/classification/StreamingLogisticRegressionWithSGD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1125bac48bab0ca224a17a9813b898ac279345b61d6086a5fc88addf9114a205"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLEnv.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5ec3d16230a6f69076c77483909c61c4e8b2fcd01364fff7b87544919fa6b50"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/scheduler/InputInfoTracker.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffa7920b469a5dfe6ccc9e034833e8b64323560c493ba4582e0211de2008aec9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/SpecializedGettersReader.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2fdc822150daebc29ce36bf43a7c9d62eba508ce6871b606c2cbdd0bb0b5380"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ValueStateImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1990c910f369943e402bacbd413ccae52ac6be377379c5383f90619ff8c51a74"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c6070f5bef99dc5cfb0735c24b4f686517d32b6f7b35c6f52a2f1c68ba2d52a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/statevariables/ListStateMetricsImpl.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b4cf69ae50c153e72d9f9807d7afddea4f1f649c617cb097def434a2f9de7de"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/RpcDeadlines.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3a096daa9f20cc1beed7aad11fc378258aa67418af1b9747b0233f4d6f6ab37"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4e82e33616abb601dc18542fc97de836a08febda5a9f9b1501820036c395c70"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcScanBuilder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c71ce84e0f527b7e4213d83ab6957b7340679ce7f7dffa9f7cfbe585cd2fede7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingWrite.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"351f9994d4ded10816a8f1c0ab0d4d9e68445fcfe0b1a5c1bf7205609bf25b8d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/test_support/pytorch_training_test_file.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f7cd3b89a7520e49e018d4db1dbc59f1e1070799573e9096347a049cdb904a3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/metrics/sink/GraphiteSink.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"53e6dcbe3c44379eb6612c223dc9dbea4930a57c96c5288800ddaf8da92ccaa8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/UserDefinedAggregateFunctionWrapper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa50721b7eb5ae5f4ced5f6b1cbd4d9d2c19cfd604f6d85f33f259a0b688693e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/GetTableTypesOperation.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef2aabe8f67d55736e43b83213d5bb7fceccbd057db71de10eb02e9acfb228a8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingSinkCommitRunner.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"61d53209996dfc58b896747ff4e2f91b14011036bb251cd5593caedea4ba553f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkThreadUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"644dfb63cd700b19649cb834ca28a863a4938c674200551e9bc02c913278ce76"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcConnectionProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e477e78c02c4c637921e4e4e5c2a08ccc63d30aa1c608b903e594fb62f114a81"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/BooleanEqualityTypeCoercion.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2007b4953214f6581bd9d052ab7afa53fc51772c327939c84226d5a4896a030"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ScanFileListing.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e391e76fdf6cba58ce914a20b9beeb202413ebe6856cda2f249800718f667ff0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/DataSourceRegistration.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"513812a869e90041d44fb89b7c023e3f738b2beed30e545f614ff309b8f80740"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-token-provider/src/main/scala/org/apache/spark/kafka010/KafkaDelegationTokenProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"50b765ffe5dba175f4e8f499144efa2750703a0ced99d048ad3e75185a70f04a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/input/FixedLengthBinaryInputFormat.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"143aec523c206a16690722c81fcc338aff99774951e868f54172776c51f100c4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/BaseStreamingArrowWriter.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8c5ab666861d0cf08aee3a567e1625b2f53add81ab5d4c7224e8ec8901b2f37"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/types/YearMonthIntervalType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3a3b07b29392bdf4df555c81e5810a7f56728472cbd81fa75f51b19555127b1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonStreamingPartitionReaderFactory.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbd1c4acae87b571358e170b25cdad0e64765793c37e75e086b70184af76b717"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/SpearmanCorrelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f974220b6111cf44e2a5a02e54497b1ac7cbd0fc32cd6696cb6af8b16ea42c26"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/SemiStructuredExtractResolver.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aee441593474db192ae3b2904092a87517eb357a375cf851884c9f9bf2815703"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/java/org/apache/spark/streaming/kinesis/KinesisInitialPositions.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"63ae0757978179da451f269fa3ff279865e149db641575ff67f77129e6dfb0c3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"68da6a0b93ae78a2e3d5fa61605f5bad67a332faea180b637125f227c2eac59f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/ReliableRDDCheckpointData.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a3d29c9a15b096ae4cc000be6b2b20842a1f0974b63ddecf4cc792012468520"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/PearsonCorrelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f9ef644e98f4c392b7803fde1b6ee7e8d43ad5edb80ba1ebba53b16b1a169af"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/java/org/apache/spark/sql/connect/plugin/GetStatusPlugin.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"799d06c07d02a78be174f5faee07d34653f73954383db61f303f88f4a6944d94"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/spark-ganglia-lgpl/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c15a3ab6e0333a084b382c7851763ba45bc335f8041b6ec9365f8074b035312"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ed04a5f228ebe48ad5cf0519337abe00b1d2b9f084b6462263a24673ea762c7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/Correlation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"115fe78294394b99b2a8bb893f4c4993b5aab869067c8bad863e9b3e9de03589"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/HadoopFsRelation.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0aba54a8f15ad313c82c7dbebd3577676f43b5b5702389e4a894a20b2fd8d91"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/DirectByteBufferOutputStream.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1e31bf2ff5bc0ec72dd80729548d4bbb0509d5d7466c2c89abc87104ead777f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/taskListeners.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"07edcc44d9ea442d6884a71b6829f0cecd483268017e6e3f0da8d26ba89b67cb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaSparkStatusTracker.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b61c459c9123c5eb5c87b7e890084aada2ea9c75b8a919dd89e503d8316e4411"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/SupportsCustomDriverMetrics.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ecf6093c0415379b1069445227a2ebbbb834feb5b574dfbe7be6a07dc8a751f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/output.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"11a7e7aecd0a2f187038027611302271e515071db0ac80a478ce98795a1fbfcf"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/utils/PipelineAnalysisContextUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cb9c3b3af0b9efdf4da2df8bac9c54b4ba5777f9b20568dbba6041b1e039e3c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/connection/SecureConnectionProvider.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"006c9acda40818dcad0d6c97dee36cc2eed3a6502a7fdd589eb92c508d9b1f14"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/StubClassLoader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"894059699b32de83c745eb5240ed541436756cef2844e3b821efa126009f93bc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c1cb6e53727daede53aa5576e66b8fbb2e061154c82d8c11fa63ca9794cab31"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/SupportsPushDownJoin.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"69c0de78b0e7f2698cfc3bd791dd91e25327bd0c0cc35b241957da5b3ee102f9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V1FallbackWriters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b4949121d8879777d5795eff83b95a7b86a9e7b7e1ba6bb20fc80cb3ccd5231"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/NoOpMergedShuffleFileManager.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7599c2deb551a3643cdbf4f341c3dc31c16c6fc22af385ec48a5665c6ffae561"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SQLHadoopMapReduceCommitProtocol.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"748cba532128d220386212b129da1839c5233662897478e0c9adcd14128b9023"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/ExecutorLossReason.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a4a1693edc910b4aef0d18f023c360db08dd0f3a1f9e7fb18a9c857f6da084b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/CartesianRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d90240577507f0c08abd448f8acef69266ebfe079e19928501ce1f2c38bad17"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/network/netty/SparkTransportConf.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"660b820cb7ed92e46a7b664f41dbf3db9e1c27e0991971c958846f4f454c7998"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/RWrapperUtils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4db8a255765b919f71c5607266de0de0e39ba3960ffdec867d928ce104b441e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/null_ops.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cec1c97593bf92c5ebfbb7afdb29822ca3003028c054f0521475a4e3bbd3e19"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/ConnectConversions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7a85059ce364dd23d4d22471a8144fec9a0c066c54fb9adb404a0291c2ee731"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatch.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca8c700ddd03fde8b41e725c1041ae6134e7857f42fc56bb5ce9c62e87ad7bf7"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateV2MetricViewExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7b7dfe2e8faa864f83c7668746e29a0031eeaff336507b02d6ee98595880f95"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/LimitPushDownThroughWindow.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc2f83d1dd114abd569e5e57844cd2d161b1d2cc926807c89e05dd9c70094279"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVPartitionReaderFactory.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bc1091e12cd6661cb319e96cf145b5547da89655dca01361c458d6c5214b6c9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"da74ab6a913e0850db363f5ff7db9558f22595c78a57d3e88d7149349a3b9a67"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"421164e6b09a114c0017a159fa7c323129adde519089bb1849127688c3c72396"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tuning/ParamGridBuilder.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c43d993445712cd3aabeaf47a1534684876b820c7b996fe368628f6f377df9d2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/text/TextPartitionReaderFactory.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f51d1752941f28d6b23990b52dea0e5ceb7ec3a3cca355075441fe681270897d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/io/LocalDiskShuffleExecutorComponents.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e445f849b1004b51399d873442bc3490d0b57ff7ccd20ccfd819feac7f87c210"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/SupportsMetadataColumns.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0b61dfe9a4113c541ffc287cf54dd73a0847fd4783d9c3ff8e30b69fce51b22"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: __init__.py \u2194 VariantExpressionEvalUtils.scala: \u0060python/pyspark/sql/functions/__init__.py\u0060 (context python) and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/VariantExpressionEvalUtils.scala\u0060 (context sql) sit in DIFFERENT parts of the tree yet change together 61% of the time (11 of the 18 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well, and counted over this repository\u0027s 10,000 most recent commits rather than its whole history \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) \u2014 the bounded-context boundary may be in the wrong place, or one context is leaking into the other. This is the behavioural boundary violation a static scan can\u0027t see. You can check this without leaving the row: of the 11 shared commits counted here, the most recent 3 are \u0060ba4441f3\u0060 [SPARK-59130][SQL] Add \u0060variant_pick\u0060 expression; \u006027404938\u0060 [SPARK-58062][SQL] Add \u0060variant_strip_nulls\u0060 expression; \u00605d23405f\u0060 [SPARK-51975][SQL] Add variant_from_arrays and variant_from_entries \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/__init__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"decf0a33741b371fce18b61a8270a35294e477fecae9480110cd9a4fff50132b"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: RewriteMergeIntoTable.scala \u2194 RewriteUpdateTable.scala: \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteUpdateTable.scala\u0060 change together 90% of the time (9 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well, and counted over this repository\u0027s 10,000 most recent commits rather than its whole history \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets). They sit in the same directory, and in this ecosystem sibling files there normally share one namespace/package \u2014 so a direct reference between them needs no import and this pass cannot see whether one exists. Read the pair before acting: if one file only DECLARES what the other consumes (a constants/types file beside its user), the co-change is definitional and the question is whether the split earns its keep; if they duplicate structure, extract the common part into a shared function or type they both call; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 9 shared commits counted here, the most recent 3 are \u0060ded9b617\u0060 [SPARK-60673][SQL] Read all referenced metadata columns in DSv2 DELET\u2026; \u0060deeadfea\u0060 [SPARK-58082][SQL] Add DSv2 relation and row-level command tree patterns; \u00604553429c\u0060 [SPARK-57644][SQL] Support generated column values on V2 table writes \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteMergeIntoTable.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c266a79f6a38a574f88aabd461f496cd43d9c339afd257c052fa2aa5a2d15254"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling clique: CSVFileFormat.scala, JsonFileFormat.scala, XmlFileFormat.scala: 3 files \u2014 \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala\u0060, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala\u0060, \u0060sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala\u0060 \u2014 all change together with no explicit dependency: a fully-connected co-change clique, not 3 separate couplings. They share one concern (thin parallel siblings over a common abstraction), so extract the shared part into ONE unit and the whole clique\u0027s coupling clears at once \u2014 you do not need to break each pair individually."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d5bc1ed58559a1b64b4df583ede357a7eb5e5a7c45e5fbca91c65bdb880b182"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: RuleIdCollection.scala \u2194 TreePatterns.scala: \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/rules/RuleIdCollection.scala\u0060 and \u0060sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreePatterns.scala\u0060 change together 59% of the time (17 of the 29 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well, and counted over this repository\u0027s 10,000 most recent commits rather than its whole history \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency \u2014 the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE \u2014 the registration is the link, and it is meant not to be an import \u2014 and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 17 shared commits counted here, the most recent 3 are \u0060bd3c05bd\u0060 [SPARK-60691][SS][SQL] Add the EXTERNAL_LOOKUP join hint for external\u2026; \u00603bc29d9d\u0060 [SPARK-58933][SQL] Resolve expressions in INSERT target IDENTIFIER cl\u2026; \u006016801417\u0060 [SPARK-55206][PYTHON][SQL] Transpilation minimal functional implement\u2026 \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/rules/RuleIdCollection.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ca95707ef973ff0fc203bb46f7a0860e451e471b3e9d29840127e9ccf4591bf"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: api.py \u2194 spark_connect_graph_element_registry.py: \u0060python/pyspark/pipelines/api.py\u0060 and \u0060python/pyspark/pipelines/spark_connect_graph_element_registry.py\u0060 change together 50% of the time (6 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well, and counted over this repository\u0027s 10,000 most recent commits rather than its whole history \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module \u2014 a sibling reference still needs an import \u2014 so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 6 shared commits counted here, the most recent 3 are \u0060324dfbe4\u0060 [SPARK-59447][CONNECT][PYTHON] Add ignore-null updates to the Auto CD\u2026; \u00603c28a9c0\u0060 [SPARK-57594][SDP] Add spark_confs support to create_auto_cdc_flow; \u00603d593617\u0060 [SPARK-58247][CONNECT][SDP] Support SCD Type 2 in the Auto CDC Python\u2026 \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4df0c5a023336880f322cf60bad1cd4a51bcb322011bc36bec4f1f814d035079"}},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1b213f6eedd4b140d0bc37bdf1496f72811a643f34064f12518b32e9e83bcfc7"},"taxa":[{"id":"CICD-SEC-9","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"90f83b4fa27db32740afe9540c905f3c0499caed87f61049a8a903ecc95b41c3"},"taxa":[{"id":"CICD-SEC-8","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"bbc4c2e61a61bac062368cd5dea8bc2cd49d055e76afd100c5521cdbabe118f5"}},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d7607849a591d455f8eb1d4d300dc563fc51dcba849902cf3b2366907898100f"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b7c8fb5b3e2fdae8487c15b4543ff5a2d21a353f5c3609d39c7cdca11d9af4b1"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"7ad4701c91f7eaa24aa7b7536975da3068c18dd1ab098025ae5c285286432c8e"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"09702f6cfd4f5ef119bc34d8e669aa4b4d5ec48634288cd2f1c69784084a5677"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"a49408a47a9cf16df008d13ec044d6e5d096580abcba37532160566a3f8a84ff"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"5dd08499d5c17c1c658545040f2931f4dd1487db08e735374d0c5b23124779aa"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e022e7222072a7763e2ffa60e9776ff3c4fc90cd148eea11093dd48e4d9be0ab"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"40edc7937677f15660aa81a0436b9b4e1ebcc910954226741fc6c8afdf9d4ac8"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ebd8509a593bb0f0301c22ace20df94643958c297aee974645a13afd91474f32"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4178f38ac61407c50c76bd37b4608d868e1cc4779af90c439c04b33491656aac"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9b8ecf649b4ec5806b3e6377f80f396d8ca7bc7865a152ce8ac7f69677208a2c"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fe73b651f089b321545129b06064c2d4eed3555f858a9fbef3abbcf85f8cd5b5"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fc5445989f2ed1a6cdd8ba1d81af8788542d376cfec71d00d96fee7fbe6ee193"},"taxa":[{"id":"CICD-SEC-5","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d657599f6f99da1927d3377533dfc0888b34c4d84aa7d5579841fd72d0e39bce"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"4f1e7684f8281bd255ddef97105c7055c2ebae06964c8745716b83e174debe83"}},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ace515990e7ee0f17b5c17e44dd168a5bdecf90804a3a3dd845cf05540978013"},"taxa":[{"id":"CICD-SEC-3","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"AC2","level":"error","message":{"text":"\u003Cbutton\u003E with no accessible text: A button with no text and no aria-label has no accessible name. Add visible text or an aria-label (an icon-only button still needs one)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/environmentpage.js"},"region":{"startLine":206}}}],"partialFingerprints":{"codehealthFindingId/v1":"8985d2dba494aca75718e2dd7a7b2a03fa0d1e3431f2d1180103626cd8ef0997"}},{"ruleId":"AC2","level":"error","message":{"text":"\u003Cselect\u003E without a programmatic label: This control has no associated label. Add a \u003Clabel for\u003E / wrapping \u003Clabel\u003E / aria-label / aria-labelledby so assistive tech can name it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"3efc98772c99bbbbfaf73f0ae5ada25887b6601454d5b36155992136b97cd2ca"}},{"ruleId":"AC2","level":"error","message":{"text":"\u003Cinput\u003E without a programmatic label: This control has only a placeholder \u2014 a placeholder is not a label (it vanishes on input and many AT ignore it). Add a \u003Clabel for\u003E, a wrapping \u003Clabel\u003E, or aria-label."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":468}}}],"partialFingerprints":{"codehealthFindingId/v1":"765a65b9ebeb583f0dbeada79a2b7a476fdb93b8f9a3ff4f198c967d15327098"}},{"ruleId":"AC3","level":"error","message":{"text":"\u003Chtml\u003E without a lang: The page declares no language, so assistive tech can\u0027t pick the right pronunciation. Add lang (e.g. lang=\u0022en\u0022)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"licenses-binary/LICENSE-javassist.html"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"942116949931b8fde5de0c9d2eb53e7d0478eb208a2fb03b3c66787b60c6a492"}},{"ruleId":"AC3","level":"warning","message":{"text":"Page without a main landmark: No \u003Cmain\u003E (or role=\u0022main\u0022) means no \u0022skip to content\u0022 target and a weaker landmark map. Wrap the primary content in \u003Cmain\u003E."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"licenses-binary/LICENSE-javassist.html"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e8ebc66d41fa91a09d12d8f48942394c5205a121da182132e67c77d8db3d942"}},{"ruleId":"AC4","level":"warning","message":{"text":"Anchor without href: An \u003Ca\u003E with no href, role or tabindex isn\u0027t focusable or keyboard-activatable. Give it a real href, or use a \u003Cbutton\u003E for an action."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":899}}}],"partialFingerprints":{"codehealthFindingId/v1":"36893a0bc6186079808d4ed625bd5a4155b602252214c4bd8f0d5fd794a6f02a"}},{"ruleId":"AC6","level":"warning","message":{"text":"Low contrast colour pair in CSS (2.8:1): \u0060.badge\u0060 sets color: #ffffff on background-color: #999999 \u2014 2.8:1, below the 4.5:1 WCAG AA minimum for normal text. Darken or lighten one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/css/api-javadocs.css"},"region":{"startLine":20}}}],"partialFingerprints":{"codehealthFindingId/v1":"566b39c6beb089ff7194ee1f78c31b2c4df3c9d0d19548db1224a194e79decb8"}},{"ruleId":"AC6","level":"warning","message":{"text":"Animation without a prefers-reduced-motion guard: \u0060.nav-trigger\u002Blabel\u0060 moves (\u0060transition: left 0.4s\u0060) and nothing reads prefers-reduced-motion for it \u2014 no @media (prefers-reduced-motion) rule for this element, no reset this project loads \u2014 so a motion-sensitive user cannot turn it off (WCAG 2.3.3). Declare it under @media (prefers-reduced-motion: no-preference), or neutralise it under reduce."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/css/custom.css"},"region":{"startLine":907}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5760da0ee841b80b4f4a5baf043981b3811d28243a1bcd6d36ce4ee03601d61"}},{"ruleId":"AC6","level":"warning","message":{"text":"Animation without a prefers-reduced-motion guard: \u0060.stage-details\u0060 moves (\u0060transition: max-height 0.25s ease-out, padding 0.25s ease-out\u0060) and nothing reads prefers-reduced-motion for it \u2014 no @media (prefers-reduced-motion) rule for this element, no reset this project loads \u2014 so a motion-sensitive user cannot turn it off (WCAG 2.3.3). Declare it under @media (prefers-reduced-motion: no-preference), or neutralise it under reduce."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/webui.css"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee85a1511c8f59a7fc56f7dce37988a7e141aa6a5b91b480cb831eafa7743446"}},{"ruleId":"AC6","level":"warning","message":{"text":"Animation without a prefers-reduced-motion guard: \u0060.stacktrace-details\u0060 moves (\u0060transition: max-height 0.25s ease-out, padding 0.25s ease-out\u0060) and nothing reads prefers-reduced-motion for it \u2014 no @media (prefers-reduced-motion) rule for this element, no reset this project loads \u2014 so a motion-sensitive user cannot turn it off (WCAG 2.3.3). Declare it under @media (prefers-reduced-motion: no-preference), or neutralise it under reduce."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/webui.css"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"6458624190196594f71fbcbe1b94877e7b47998f661aaa33675e4297277f1172"}},{"ruleId":"AC6","level":"warning","message":{"text":"Animation without a prefers-reduced-motion guard: \u0060.arrow-open\u0060 moves (\u0060transition: transform 0.2s ease\u0060) and nothing reads prefers-reduced-motion for it \u2014 no @media (prefers-reduced-motion) rule for this element, no reset this project loads \u2014 so a motion-sensitive user cannot turn it off (WCAG 2.3.3). Declare it under @media (prefers-reduced-motion: no-preference), or neutralise it under reduce."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/webui.css"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"38748ff82b7a739dcf718676db4549db50837bbe0485fa51e23a25de21b81fe4"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: SpecializedGetters (20 abstract methods): \u0060SpecializedGetters\u0060 declares 20 abstract methods: \u0060get\u0060, \u0060getArray\u0060, \u0060getBinary\u0060, \u0060getBinaryView\u0060, \u0060getBoolean\u0060, \u0060getByte\u0060, \u0060getDecimal\u0060, \u0060getDouble\u0060, \u0060getFloat\u0060, \u0060getInt\u0060, \u0060getInterval\u0060, \u0060getLong\u0060, \u0060getMap\u0060, \u0060getShort\u0060, \u0060getStruct\u0060, \u0060getTimestampLTZNanos\u0060, \u0060getTimestampNTZNanos\u0060, \u0060getUTF8String\u0060, \u0060getVariant\u0060, \u0060isNullAt\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/SpecializedGetters.java"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"f71ffa913880b039e8028c8891e017c6898fcbe80d2676481550de88c1dc59dc"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: VectorizedValuesReader (31 abstract methods): \u0060VectorizedValuesReader\u0060 declares 31 abstract methods: \u0060readBinary\u0060, \u0060readBinary\u0060, \u0060readBoolean\u0060, \u0060readBooleans\u0060, \u0060readByte\u0060, \u0060readBytes\u0060, \u0060readDouble\u0060, \u0060readDoubles\u0060, \u0060readFloat\u0060, \u0060readFloats\u0060, \u0060readGeography\u0060, \u0060readGeometry\u0060, \u0060readInteger\u0060, \u0060readIntegers\u0060, \u0060readIntegersWithRebase\u0060, \u0060readLong\u0060, \u0060readLongs\u0060, \u0060readLongsWithRebase\u0060, \u0060readShort\u0060, \u0060readShorts\u0060, \u0060readUnsignedIntegers\u0060, \u0060readUnsignedLongs\u0060, \u0060skipBinary\u0060, \u0060skipBooleans\u0060, \u0060skipBytes\u0060, \u0060skipDoubles\u0060, \u0060skipFixedLenByteArray\u0060, \u0060skipFloats\u0060, \u0060skipIntegers\u0060, \u0060skipLongs\u0060, \u0060skipShorts\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. Those 31 declarations carry 30 distinct name(s), so part of the width is overloading rather than separate responsibilities \u2014 but 30 operations clears the \u003E15 bar on its own, so the row is about responsibilities, not signatures. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedValuesReader.java"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae92b26a5bb83a8587fd5ef1e335868933df22590606752127c810c5d8c0c337"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: HiveSession (26 abstract methods): \u0060HiveSession\u0060 declares 26 abstract methods: \u0060cancelDelegationToken\u0060, \u0060cancelOperation\u0060, \u0060close\u0060, \u0060closeExpiredOperations\u0060, \u0060closeOperation\u0060, \u0060executeStatement\u0060, \u0060executeStatement\u0060, \u0060executeStatementAsync\u0060, \u0060executeStatementAsync\u0060, \u0060fetchResults\u0060, \u0060getCatalogs\u0060, \u0060getColumns\u0060, \u0060getCrossReference\u0060, \u0060getDelegationToken\u0060, \u0060getFunctions\u0060, \u0060getInfo\u0060, \u0060getMetaStoreClient\u0060, \u0060getNoOperationTime\u0060, \u0060getPrimaryKeys\u0060, \u0060getResultSetMetadata\u0060, \u0060getSchemas\u0060, \u0060getTableTypes\u0060, \u0060getTables\u0060, \u0060getTypeInfo\u0060, \u0060open\u0060, \u0060renewDelegationToken\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. Those 26 declarations carry 24 distinct name(s), so part of the width is overloading rather than separate responsibilities \u2014 but 24 operations clears the \u003E15 bar on its own, so the row is about responsibilities, not signatures. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSession.java"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc68b3e85257addbcf0955a4d3814b3c54415a6670cb58e8fdc384c0b2a1a4d7"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: HiveSessionBase (17 abstract methods): \u0060HiveSessionBase\u0060 declares 17 abstract methods: \u0060getHiveConf\u0060, \u0060getIpAddress\u0060, \u0060getLastAccessTime\u0060, \u0060getOperationLogSessionDir\u0060, \u0060getPassword\u0060, \u0060getProtocolVersion\u0060, \u0060getSessionHandle\u0060, \u0060getSessionManager\u0060, \u0060getSessionState\u0060, \u0060getUserName\u0060, \u0060getUsername\u0060, \u0060isOperationLogEnabled\u0060, \u0060setIpAddress\u0060, \u0060setOperationLogSessionDir\u0060, \u0060setOperationManager\u0060, \u0060setSessionManager\u0060, \u0060setUserName\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/session/HiveSessionBase.java"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"06184c7f18e66d99499fb03f564d2357df9bfea73bc3dbef46ec5df88d9b2ded"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: ICLIService (27 abstract methods): \u0060ICLIService\u0060 declares 27 abstract methods: \u0060cancelDelegationToken\u0060, \u0060cancelOperation\u0060, \u0060closeOperation\u0060, \u0060closeSession\u0060, \u0060executeStatement\u0060, \u0060executeStatement\u0060, \u0060executeStatementAsync\u0060, \u0060executeStatementAsync\u0060, \u0060fetchResults\u0060, \u0060fetchResults\u0060, \u0060getCatalogs\u0060, \u0060getColumns\u0060, \u0060getCrossReference\u0060, \u0060getDelegationToken\u0060, \u0060getFunctions\u0060, \u0060getInfo\u0060, \u0060getOperationStatus\u0060, \u0060getPrimaryKeys\u0060, \u0060getQueryId\u0060, \u0060getResultSetMetadata\u0060, \u0060getSchemas\u0060, \u0060getTableTypes\u0060, \u0060getTables\u0060, \u0060getTypeInfo\u0060, \u0060openSession\u0060, \u0060openSessionWithImpersonation\u0060, \u0060renewDelegationToken\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. Those 27 declarations carry 24 distinct name(s), so part of the width is overloading rather than separate responsibilities \u2014 but 24 operations clears the \u003E15 bar on its own, so the row is about responsibilities, not signatures. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/ICLIService.java"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf4500d6eeb13231c5b6dcb04ed6244de29967b0c21ded365ad2c2dade04f93b"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: ExternalCatalog (40 abstract members): \u0060ExternalCatalog\u0060 declares 40 abstract members: \u0060createDatabase\u0060, \u0060dropDatabase\u0060, \u0060alterDatabase\u0060, \u0060getDatabase\u0060, \u0060databaseExists\u0060, \u0060listDatabases\u0060, \u0060listDatabases\u0060, \u0060setCurrentDatabase\u0060, \u0060createTable\u0060, \u0060dropTable\u0060, \u0060renameTable\u0060, \u0060alterTable\u0060, \u0060alterTableDataSchema\u0060, \u0060alterTableSchema\u0060, \u0060alterTableStats\u0060, \u0060getTable\u0060, \u0060getTablesByName\u0060, \u0060tableExists\u0060, \u0060listTables\u0060, \u0060listTables\u0060, \u0060listViews\u0060, \u0060loadTable\u0060, \u0060loadPartition\u0060, \u0060loadDynamicPartitions\u0060, \u0060createPartitions\u0060, \u0060dropPartitions\u0060, \u0060renamePartitions\u0060, \u0060alterPartitions\u0060, \u0060getPartition\u0060, \u0060getPartitionOption\u0060, \u0060listPartitionNames\u0060, \u0060listPartitions\u0060, \u0060listPartitionsByFilter\u0060, \u0060createFunction\u0060, \u0060dropFunction\u0060, \u0060alterFunction\u0060, \u0060renameFunction\u0060, \u0060getFunction\u0060, \u0060functionExists\u0060, \u0060listFunctions\u0060. Counted over its ABSTRACT members \u2014 a \u0060def\u0060 with no body or a \u0060val\u0060/\u0060var\u0060 with no initializer, once per signature; concrete members, private and protected members, and members of a companion \u0060object\u0060 are not counted, because no implementer is forced to write them. Those 40 declarations carry 38 distinct name(s), so part of the width is overloading rather than separate responsibilities \u2014 but 38 operations clears the \u003E15 bar on its own, so the row is about responsibilities, not signatures. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalog.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"d04f8b8daf3d63bc3ff194766a87f3ff970015c51ea02ae9dc5ae05c73bba37b"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: LogicalPlanVisitor[T] (24 abstract members): \u0060LogicalPlanVisitor[T]\u0060 declares 24 abstract members: \u0060default\u0060, \u0060visitAggregate\u0060, \u0060visitDistinct\u0060, \u0060visitExcept\u0060, \u0060visitExpand\u0060, \u0060visitFilter\u0060, \u0060visitGenerate\u0060, \u0060visitGlobalLimit\u0060, \u0060visitOffset\u0060, \u0060visitIntersect\u0060, \u0060visitJoin\u0060, \u0060visitLocalLimit\u0060, \u0060visitPivot\u0060, \u0060visitProject\u0060, \u0060visitRepartition\u0060, \u0060visitRepartitionByExpr\u0060, \u0060visitRebalancePartitions\u0060, \u0060visitSample\u0060, \u0060visitScriptTransform\u0060, \u0060visitUnion\u0060, \u0060visitWindow\u0060, \u0060visitTail\u0060, \u0060visitSort\u0060, \u0060visitWithCTE\u0060. Counted over its ABSTRACT members \u2014 a \u0060def\u0060 with no body or a \u0060val\u0060/\u0060var\u0060 with no initializer, once per signature; concrete members, private and protected members, and members of a companion \u0060object\u0060 are not counted, because no implementer is forced to write them. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"332ff992f5db2d0bf27abfd1a1cf0e081d287b07ccf7c971bf871036c21aeafb"}},{"ruleId":"GD1","level":"warning","message":{"text":"Unfinished stub \u2014 body is a \u0022not implemented\u0022 error: \u0060invokeAll\u0060 is a shipped member whose whole body is still a \u0022not implemented\u0022 error, and nothing in the repository overrides it \u2014 generated scaffolding that was never completed. Implement it or remove the dead surface."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1d3939c188b876c61d4f30812dfb2639911062994eb2f3023addf16428ae401"}},{"ruleId":"GD1","level":"warning","message":{"text":"Unfinished stub \u2014 body is a \u0022not implemented\u0022 error: \u0060invokeAll\u0060 is a shipped member whose whole body is still a \u0022not implemented\u0022 error, and nothing in the repository overrides it \u2014 generated scaffolding that was never completed. Implement it or remove the dead surface."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"13c69a2680ffd710063531f8ceff12eab99761250dc889c088ce4843049c7b19"}},{"ruleId":"GD1","level":"warning","message":{"text":"Unfinished stub \u2014 body is a \u0022not implemented\u0022 error: \u0060invokeAny\u0060 is a shipped member whose whole body is still a \u0022not implemented\u0022 error, and nothing in the repository overrides it \u2014 generated scaffolding that was never completed. Implement it or remove the dead surface."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"602e79843345be186e210651753b118dd87d6e0959d574bd145e5d517173dffe"}},{"ruleId":"GD1","level":"warning","message":{"text":"Unfinished stub \u2014 body is a \u0022not implemented\u0022 error: \u0060invokeAny\u0060 is a shipped member whose whole body is still a \u0022not implemented\u0022 error, and nothing in the repository overrides it \u2014 generated scaffolding that was never completed. Implement it or remove the dead surface."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ac81bce9debc9f53f1157c42dc7888497b9bac7a345f52c967330816667b614"}},{"ruleId":"IC1","level":"warning","message":{"text":"Unfinished stub \u2014 throws a \u0022not implemented\u0022 exception: \u0060invokeAll\u0060 throws an exception whose message says it isn\u0027t finished \u2014 a not-implemented stub wearing an ordinary exception. Implement it or remove it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6167b02134cf442522be95c7ff66e59746b2ba13a68fd81a644212077835428"}},{"ruleId":"IC1","level":"warning","message":{"text":"Unfinished stub \u2014 throws a \u0022not implemented\u0022 exception: \u0060invokeAll\u0060 throws an exception whose message says it isn\u0027t finished \u2014 a not-implemented stub wearing an ordinary exception. Implement it or remove it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ac1168522b572b4a417231142ef292a4c07f7b69bea8fd3e5e166da414419d1"}},{"ruleId":"IC1","level":"warning","message":{"text":"Unfinished stub \u2014 throws a \u0022not implemented\u0022 exception: \u0060invokeAny\u0060 throws an exception whose message says it isn\u0027t finished \u2014 a not-implemented stub wearing an ordinary exception. Implement it or remove it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"37a26a6d45f8ff8201e6f85f794ce50a6f47ee25c4ed15bacbb1965dfeea119b"}},{"ruleId":"IC1","level":"warning","message":{"text":"Unfinished stub \u2014 throws a \u0022not implemented\u0022 exception: \u0060invokeAny\u0060 throws an exception whose message says it isn\u0027t finished \u2014 a not-implemented stub wearing an ordinary exception. Implement it or remove it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9eff636a4b91056227be7f1f544496fd9248b6fea377004fda1a5000627ddef"}},{"ruleId":"IC1","level":"warning","message":{"text":"Empty method body \u2014 does nothing with its inputs: \u0060validateLiteral\u0060 takes parameters but its body is empty \u2014 it accepts inputs and does nothing. Either implement it or remove it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/ExpressionResolutionValidator.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8357df8325aa56f2ec1146949f5ea7e022f4d5583b1352e612736bdcc4b97e7"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/test/scala/org/apache/spark/unsafe/types/UTF8StringPropertyCheckSuite.scala"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"814de077b4528d27d23c108ee6437b8fa78e37e5cb252bee2ac02498b5297527"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala"},"region":{"startLine":2910}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fb925c0aac7a086a80cdbe123a08d61adb22b0d1c728da9d18369dceaa66081"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtilsPythonHelper.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"80ff9a7e00610a85d7112771f3a79256430e2a82a7460f5eacc05da541bf0b4b"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/SparkAWSCredentials.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1f6246f30394b3992d7f87fd65850583f939a86543fda5c0aa62a4da390f152"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/InternalAccumulator.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"3153ec3d6455e484a9ba83763db9c9ec4e3b6b929cd8560ac2f877442fcf6d6f"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":206}}}],"partialFingerprints":{"codehealthFindingId/v1":"9caff9fe898cf7cd847e74cde7e2b36d6276991f73dd55132a9560702f8468f8"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIUtils.scala"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"0583bbda2ec6b4174df4229a6d25d7996ba6d1c3447f6d116fe692cf42f0bc92"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"1746fd10a35a349b3bfd85c72ba86a764b9254875c91230500fb9621c8f2865f"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/exec/ExecutorThreadDumpPage.scala"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"c55c18bbf4a6e135aa12e3f3b4b4bb4a0f524d59575df04fbed0da6f61a1bd27"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e615a70360b2a4d52b2d0c43643291c3d8226c62313d7a6dcf8f351f6ced462"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/BlockingThreadPoolExecutorService.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ad1b02f8d3a4e397728557b9ac62cbbe3238d080c3ff84cabac4790829de1f3"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/DriverSuite.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dde448049dbf8fc92c2282c36c50bd77c852f740a05960ec59a367ef440f033"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala"},"region":{"startLine":814}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e38272602722b8bc7b317e70edb1ddefffd51e4b9711b6895b4c558584635c9"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala"},"region":{"startLine":905}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2150d8d785bf77012128a13099cd96c456634962b4e06f6a3964f72ee9f9789"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala"},"region":{"startLine":2037}}}],"partialFingerprints":{"codehealthFindingId/v1":"add9a5492cd0616389cd52d2bef05d16c70031a1d356e98a7ced8ee5a7845bf9"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/scheduler/OutputCommitCoordinatorSuite.scala"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"40b3adb24a7fb98dc96a338c2c24de9d9aa5405f6dca99dd0066a523ceb5ea89"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/ui/UISuite.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c92789a1165e7517d9776cb30ce06753843b32bedb507b8a17e0200cd90e90e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/ui/UISuite.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c177b7c2825d39886de9f2ea758d48d2c94ee7877d9cd0ff267e1e8e0e58cc5"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"8499d9dd976090dabf1f03e1167ba47c48fe156d583f21fe51c2bc88cd463bbf"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/functions.scala"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d90750965823a2a3b13d8fe96dc627b3a0f57dede9dc80b65d957c56d4bfa88"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/params.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"40e88693d213216b7308777d161a68170e5e6b07e9f5828c31a6ded6f437d44b"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"42a3d91c0ab83eb6cad800ac1aab4a2df3926ef158511eaff571faa93aa715f8"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"23cc5dbaf13ab93689a7de327309453603b947655af1df3fc6a92da45824476b"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"d79c74c82236ed77a4a33f028704202fc618feda608550a780ec91550d43b260"}},{"ruleId":"IC1","level":"note","message":{"text":"Empty method body: \u0060apply\u0060 has an empty body \u2014 confirm it\u0027s an intentional no-op and not an unfinished method."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/sql/ml/InternalFunctionRegistration.scala"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a2d9918f77e9371bc761e0303e91a26c019ed8796cc2dd19c4e9e0398736970"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/classification/LinearSVCSuite.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1e1c8e0b8a75e397c0cf4ff7a182073d41be0db1711b212a86dff207c2ab9f0"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"34f7dbb41f5de5a5eb4cd76c3812d8fab5626955f48487561af4c23bf35fd31e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/regression/AFTSurvivalRegressionSuite.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"16dcd1392e50f669558b3022fae5e1341762066be5f1edfe6226a721e7c0168e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/regression/GeneralizedLinearRegressionSuite.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"16ab675b2977095a53e9ee6a32c4863d3e8aaad40ec0ea12e22461c8b95d637b"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1599a1b904d9a6bf66d83915b0f6dcd2a6a0cc584da6221142727bb58fc945e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca406d83a98350dd7e3903813f25c15499db87b272c703584ca7879d43b7f390"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"b56426092bc09583127633ed5c78f3b14d3d19f8910eba85559568b6da0bc4b3"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"306fcd58139140eda68a60bae7aba4625274b1c15ac375df304c2a031e77511d"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/ml/stat/SummarizerSuite.scala"},"region":{"startLine":599}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac140d439ac96b2774412aff92df9c34ab78d95c2802f8d7dbddfaaa8e5582b6"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/test/scala/org/apache/spark/mllib/stat/CorrelationSuite.scala"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"873e7169f4d258bafb464e6e47dd4c733e8d39919f7a3d23d3282b87ac132779"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/PVTestsSuite.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"45f49dc9b85b392984bf2a4d38ddae0c79e103eb7f8b979395b03363ed0b5225"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/PythonTestsSuite.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa0d1a78cf90019519faa11f9598fb6aba780fe317d96186de233a5e3d53a4b3"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/expressions/scalalang/typed.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"28c57c1fee6fdbc6b2b47f4b8b44ae765c3a8534ec9a60fbe1605e21209584bc"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/functions.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea9336d01f0e1de6be1cb357668f9f832be6cdf1d9f7cfe6da509c9592f00d27"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/StatefulProcessor.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"e26edb1d5127d8defdb7a794ea1654d3438f21e84d4ed9511342ec03c7c914b3"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala"},"region":{"startLine":22}}}],"partialFingerprints":{"codehealthFindingId/v1":"2860c04eccb65e334a8d81b81c9c2898ad9703ae9a4e72e650368d39cadf2e3f"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf18296cea57c2240b19cafbd4e53391984e206bdb5e12e88658bc7e3de35fe7"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"b93db8dc755348ceaba357c1c5e0b4751ebef107b526ad840f979d11e183ad57"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala"},"region":{"startLine":827}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fb36f102571bfbe678283f00c02622243f02225fa40a04346dd3864179881ce"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b4a3191ac00cf9495b64877003d912f697f96d06967cba6b0d61a2fe9e526af"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ca085ec7a022187e138cb2cef2603f557dc8f6b162fcf256cbe1db242551946"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/HyperLogLogPlusPlusHelper.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"01d5f48dcf3cba561878e788ee016eedb4fedb5fff2c325d69e91e414abc621e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala"},"region":{"startLine":2149}}}],"partialFingerprints":{"codehealthFindingId/v1":"acaf72199c0cbf7b66d0f88e7b09755e63e171fb4b84468a593a48d23d2041cf"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/util/RebaseDateTimeSuite.scala"},"region":{"startLine":309}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3b7ff169ba922143d4ec1080dba8e9c81837c652d5ab2426ff1805c70c14ac0"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/util/RebaseDateTimeSuite.scala"},"region":{"startLine":317}}}],"partialFingerprints":{"codehealthFindingId/v1":"520408ab474d56f26c1a9ef84cdee1f396ab288e15f82959f7c4d45fe556c5a4"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/test/scala/org/apache/spark/sql/types/DataTypeWriteCompatibilitySuite.scala"},"region":{"startLine":631}}}],"partialFingerprints":{"codehealthFindingId/v1":"29ab029137eed181292fc2f72151a5ccc95d546e8e8aeef47b9ba3185b0f404d"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala"},"region":{"startLine":3779}}}],"partialFingerprints":{"codehealthFindingId/v1":"0eec3bba30e04f3aac216990d7d02db4ceb9db00dcc628ffca4fa3468095c0f4"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/PlanGenerationTestSuite.scala"},"region":{"startLine":3785}}}],"partialFingerprints":{"codehealthFindingId/v1":"c87e4178f6e374172c3fcb6edc776568970858129f588fe1d7795c9fdf954b68"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/CheckpointSuite.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"d24920d5645771d426b9c559f271a00636e4e12601654d003c3e57044f4cc9e1"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/KeyValueGroupedDatasetE2ETestSuite.scala"},"region":{"startLine":509}}}],"partialFingerprints":{"codehealthFindingId/v1":"155b7e08596ea7e621c099ea8e6a97f1d40c4abe5eff9c7f3b858cae8c503a01"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/UserDefinedFunctionE2ETestSuite.scala"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"67ce50de71d0bf667674e5b197f3b11921aedf1696463b025d9b01b826da29d9"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SQLContext.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3a58ba6315e37644a217cc084f555c3a732fd480c9b7c2b98ee2067baf2b92d"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/SparkSession.scala"},"region":{"startLine":409}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5e5c5f2222141d700cc5c333e5b5769982d6f45e0768121c20c884694737977"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SQLContext.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"874f0fc0da39568679813f1d363cc56027a73c57a5bb379bbb9e5182829fe0d8"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/SparkSession.scala"},"region":{"startLine":853}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3715085a070307d16948a5a07bd54b8d8ac60dc3d5451211a92ac731c28f5d0"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/QueryExecution.scala"},"region":{"startLine":710}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b4a1685312c865f43a65a7bbfc7f4bd6b7c418efdf319fffbfd64be19f3b659"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala"},"region":{"startLine":493}}}],"partialFingerprints":{"codehealthFindingId/v1":"d688170f4bea83f002dde6bf11e8d7cdfbeb51b337863a15412d61e5e3029570"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanRelationPushDown.scala"},"region":{"startLine":668}}}],"partialFingerprints":{"codehealthFindingId/v1":"aebbecfa99fcc74f49c50911a6740a090e978fe1770878a6aef803c367e2ca84"}},{"ruleId":"IC1","level":"note","message":{"text":"Empty method body: \u0060release\u0060 has an empty body \u2014 confirm it\u0027s an intentional no-op and not an unfinished method."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDB.scala"},"region":{"startLine":1875}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8a9935ac62070c1a8c1bfeff3cc3164874af68f82aa69952543126bca481675"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala"},"region":{"startLine":1561}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf65ac904b169394a19bd54858928f460b99500965c10dd1ff86cd0102698924"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/package.scala"},"region":{"startLine":54}}}],"partialFingerprints":{"codehealthFindingId/v1":"5abad32e1953ff5442dd5af9731573d985ed16547689ebb2728fd69d972806d2"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"fda69d309da1f66985aaa0443fc0957b935924e194af4f056927e84867fc54c6"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryPage.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a957cdca4602312739f822b1d96b2f16662d97e832e49891904febf9b932329"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1d30eee45aedd1c0a977c3a6f18a89a3a5c18775aedcd494c4c8e3bdc6471b1"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"9832e5c57e21269e9a4fd328c0b52be9fa2dcf3075f6d6b65e2b9962d3964ba3"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala"},"region":{"startLine":341}}}],"partialFingerprints":{"codehealthFindingId/v1":"82cb0a3c4bdd8e1a7af38e9f2cdc19f6c43a40eba4d3be2f2f8e26e297e0fe22"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala"},"region":{"startLine":659}}}],"partialFingerprints":{"codehealthFindingId/v1":"73159094fb95a76a2062e8773a3d5eb7e35709d84fa016159b4a9fd4eca3e0c3"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala"},"region":{"startLine":1924}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3e57b0fafa75f3dd1466681e016aeefa7ab6060a00e237d954cf739a865eb30"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala"},"region":{"startLine":3212}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3f7200ce20d6ff23014a232308a796de8245444efd6b171d148447a37c5b88f"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala"},"region":{"startLine":1433}}}],"partialFingerprints":{"codehealthFindingId/v1":"b05f6ae9e866d61a6ca7d43d29eb02adf93534094fe5b8ea92f1188bb4a17b15"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2MetadataTableSuite.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1e64eaaed14928f06dd4088e99e209e08c8f3e10ee00789db6bc3ac23d1b4fc"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2SQLSuite.scala"},"region":{"startLine":1200}}}],"partialFingerprints":{"codehealthFindingId/v1":"3328d2456a820cc7a87eff2e3937c7a21241e501297363c1ab6d908d594c527b"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/SQLWindowFunctionSuite.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"04cddfce4f8e90f004aced7e82f20e55135ffcd5e83c141ebcb453b6fd10f423"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala"},"region":{"startLine":996}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f5a05282154a842461e0ba95661615022aa4e629c2f096c672422e8350e73b8"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala"},"region":{"startLine":1005}}}],"partialFingerprints":{"codehealthFindingId/v1":"28d03ef7aeb0f1d002f6af0435d8acc90e809b1fac8f40149182a716b6387b83"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala"},"region":{"startLine":1097}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d350be4ded89fb65839a98915a7d61d77b86c3056f543a4edbdcd5c5987c408"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcQuerySuite.scala"},"region":{"startLine":1226}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ee661bcc9252ca4b3683194c4dfbb1be81424ff42f61bc8cbd5590e2857fcb2"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcSourceSuite.scala"},"region":{"startLine":364}}}],"partialFingerprints":{"codehealthFindingId/v1":"473c4bf63b581e0c1f26262f7de34a4697f52fac3e8b4457ec77f9d3782abd08"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetAvroCompatibilitySuite.scala"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e7059b073ce54b7154c95894ebac7089d1015b4ca55250e3603594ce02cebdf"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala"},"region":{"startLine":459}}}],"partialFingerprints":{"codehealthFindingId/v1":"37a51537fb3f8c99fb112beaf1caca671a544bdaeab13a97fe77ef3b360eaae4"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala"},"region":{"startLine":602}}}],"partialFingerprints":{"codehealthFindingId/v1":"16efa2b1f6473f10d95aa30a415bdf0693cd1661e128cfaed8e673c344ff9c46"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRebaseDatetimeSuite.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"defe4ed1756ab1c64c6eb4044947af876576ccf4dc927e2bfeef56542b423b13"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/joins/HashedRelationSuite.scala"},"region":{"startLine":586}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f8ca5edc288d7dff0782dea74388203f02eacfec00f8be72613295e4891d34e"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/joins/HashedRelationSuite.scala"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"585d36c2ebbb954c22b16927a668e82bc239fe2f8116329fb59c82722f2763d4"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/MemorySinkSuite.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"0077a308ae70ba22a9ca0ac042a202d41557df15df1741da603a7aacc9e93e5c"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala"},"region":{"startLine":579}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed07a4442e696170cc4580db636f9ad9d88e803a31bd4cf72bd08ff8c2b2c4e0"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala"},"region":{"startLine":510}}}],"partialFingerprints":{"codehealthFindingId/v1":"de54ee4f9a866f96d8e09a52f5f8457bfa08b2f5639269812ff3cf0ac8e081b2"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala"},"region":{"startLine":854}}}],"partialFingerprints":{"codehealthFindingId/v1":"05cf6b105afcf88460ae95fd5c5e2454912bc8b671e18621a228aa086f46ee68"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2259}}}],"partialFingerprints":{"codehealthFindingId/v1":"29191e16f5f35b58b097e420e160588f1abb6783b67adb2c5ed8d500574548eb"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2351}}}],"partialFingerprints":{"codehealthFindingId/v1":"1309f8dc8f5aeaf620e4234849add1d2d052d275d5f77e755b4fd1be68c62a9c"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2570}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb7c8a66c489dafbe44cfca8e3233fb41b606fa23e7ddb070b309ceacacbe07c"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateSuite.scala"},"region":{"startLine":2646}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc1bde29e5d17b14c50e3fda69c323dd468ea0fcfc59f495dfe49142aaeb8765"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/test/scala/org/apache/spark/sql/util/DataFrameCallbackSuite.scala"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d197911b6a0518984837a911e5f30b37ce1bd986ef5923144dcf6b75c781029"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala"},"region":{"startLine":460}}}],"partialFingerprints":{"codehealthFindingId/v1":"483e0d5aeea1595ab3bc18725354caea7c1b021a87fefa10f6e22123989b8647"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/package.scala"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f49abcf018de7201ae7c4d64fb80317733a370a2855fe6319f4572c5eceb737"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"10b54df6a5aaf66858e8d70fbea05e160947daa503a6134d940b31ae13c90a9f"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/ErrorPositionSuite.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c6e86b7b04c6682770cf9d2f07eabe8e696fbbfce67c092efd55421a75bc6fc"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/ParquetHiveCompatibilitySuite.scala"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"21220453d9ba2fb9d47eaad84c58d9eb3a7d2235c909256070779d558229f01a"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuites.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6dbb358b72da79022510d2096de740aef7cda3e2d43c189c2d1a7227bcb25f6"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/ConcurrentHiveSuite.scala"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b6cf60cbb3a9713f595d9a3edb11b5c6744080346832d2fe10e197c5c5585f3"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveResolutionSuite.scala"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d5cb72c9aff2c2090e1bd6b3f3bb1e08d510df87bf6c775dbf7086051c98db7"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala"},"region":{"startLine":1292}}}],"partialFingerprints":{"codehealthFindingId/v1":"efbb2942707b0c5c4b5d60afb0ce78233abe385c7af7e76256892a24e5b62963"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala"},"region":{"startLine":1314}}}],"partialFingerprints":{"codehealthFindingId/v1":"faf7e1b89b62017f0a16996969312f27b010eb705936f43024da669e1ce21291"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala"},"region":{"startLine":1579}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ea3c605d5a4d858f3ec051b45c62dc3b21ea9e233c8080677af8ce61d198b5b"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/python/PythonDStream.scala"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"92b8bdce5cf88d5072acb6277f592229392e19a41c76bf412a0bf78b29740630"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/BatchPage.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"63d05676d314fd96da66662daac9cfa2cdb76d9b34ef5170506bbbd19aa7f2f7"}},{"ruleId":"IC1","level":"note","message":{"text":"Blanket warning suppression: A bare \u0060// scalastyle:off\u0060, \u0060// scalafix:off\u0060 or \u0060@nowarn\u0060 (or Wartremover\u0027s \u0060warts.All\u0060) switches every rule or warning off \u2014 hidden debt. Suppress the specific rule on the specific line, with a justification, instead."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e25bf99247259dc7c7730f25afb656fea59a371ec2d8963c72931b124878dee"}},{"ruleId":"IC1","level":"note","message":{"text":"Disabled test: A test is skipped/ignored \u2014 coverage that looks present but never runs. Re-enable it or delete it so the green run means something."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/test/scala/org/apache/spark/streaming/ReceiverSuite.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c7cca2d2213fd4961dfb9d269f78659bd18f3b54f032bdc214c558248ad9f7d"}},{"ruleId":"M2","level":"note","message":{"text":"No ADRs: No Architecture Decision Records found \u2014 no conventional ADR directory, no numbered \u0060NNNN-title\u0060 documents in any markup this check reads, and nothing ADR-shaped by content. Design rationale recorded elsewhere (a design-notes tree, a mailing list, pull-request discussion) is not visible to this check and is not re-findable per decision, so a future maintainer cannot ask why one choice was made and get an answer."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"670b3d6e36a756d63097d0dfbf90afd5fc761308800b9354894a07c3f4e4aa14"}},{"ruleId":"P2","level":"note","message":{"text":"Logging is not universal: Only 23/29 runnable modules use logging (modules with no entry point or server are excluded \u2014 they are libraries a runnable module hosts). Silent: \u0060connector/credential-aws-integration-tests\u0060, \u0060dev\u0060, \u0060repl\u0060, \u0060sql/connect/client/jvm\u0060, \u0060sql/connect/server\u0060 and 1 more."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"91a94e21d6d4d0e6a2003f94505b0b02b157176f0b24c4820f3f82b4447a97fe"}},{"ruleId":"P3","level":"note","message":{"text":"No dependency-update automation: \u0060dev/package.json\u0060 declares packages, and nothing in the repository keeps them current: no Dependabot or Renovate configuration that schedules updates, and no dependency-review gate on pull requests. A pinned dependency stays at the version it was added at until someone notices \u2014 including after an advisory is published against it. Add a \u0060.github/dependabot.yml\u0060 with one \u0060package-ecosystem\u0060 entry per ecosystem the tree uses (or an enabled \u0060renovate.json\u0060), and gate pull requests with \u0060actions/dependency-review-action\u0060."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/package.json"},"region":{"startLine":2}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ca528629f035a26b2d6016bb326ade0ea06f3fac43d21fe9390fcdc7a6b09be"}},{"ruleId":"P4","level":"note","message":{"text":"No rollback/health safety: Deployment automation exists and the service already exposes health probe endpoints (healthz/livez/readyz or a container healthcheck), but no manifest in this repository wires them into readiness/liveness probes, a rolling-update strategy, lifecycle hooks or a migration job \u2014 a bad release is harder to detect and reverse. If that wiring lives in a separate ops/Helm repository, document the pointer here so release safety is evidenced."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"db6bab8a28a2145f47e5a4e6683cda39d2ba0296c723238e8057da979ae1c706"}},{"ruleId":"P6","level":"note","message":{"text":"No changelog: No CHANGELOG/HISTORY/RELEASES file \u2014 what shipped when isn\u0027t easy to reconstruct for support or audit. (Versioning/tagging makes releases traceable, but a changelog records the what.)"},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"dda5aa5aed8cbb292c3ef2b733bc138f614293ae6426c85e98bf31ef330d9415"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/TestUtils.scala"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"f42058fd0bc46cc4c6d7a083c103ea050ce0cfa6ee063cd6ed5089fa475df1b6"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":283}}}],"partialFingerprints":{"codehealthFindingId/v1":"6030f98255a34e6d721c74e8c7f4ae6e6e0cc811c9333eea87a3691a8085876e"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb28f16592c0f104e252af79d097b7fad1f113741f2c341e68c81fe02a5f4c6e"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/rest/RestSubmissionClient.scala"},"region":{"startLine":299}}}],"partialFingerprints":{"codehealthFindingId/v1":"80411bba79df02db5e5418d925a6af2c7041945a306bc3cbbd77a893d16e219e"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060HttpClient(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/JettyUtils.scala"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"8487bdb173331d5bb641a71740140da470a225d25c8e4ec2d0645dd7e44fcfd9"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060urlopen(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":633}}}],"partialFingerprints":{"codehealthFindingId/v1":"41b3de0940c22e35a0d38c786ed5478feec16c666cdf97bc1952442afb505be6"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060urlopen(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":897}}}],"partialFingerprints":{"codehealthFindingId/v1":"3df7723381ed7467ea18a23bf9771d019c7e2a918d3e7594558de9d6b030c73a"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060urlopen(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":914}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba7d059828428139838711dcb34aff338652600f470d5a96bdc596ed7a2543c0"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060urlopen(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/merge_spark_pr.py"},"region":{"startLine":3290}}}],"partialFingerprints":{"codehealthFindingId/v1":"65f3ba70cc071c83ad8cbf0f8ed731292cc3d717857fdfa4c2340bfc04bf11dd"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/java/org/apache/spark/deploy/yarn/AmIpFilter.java"},"region":{"startLine":218}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f9e84494c717246e662ae0d791662ef56446e25b997ae1cc3f445397e193c53"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060.openConnection(\u0060 makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service\u0027s request, thread or connection until the call gives up on its own \u2014 or never, for a client with no default timeout."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1763}}}],"partialFingerprints":{"codehealthFindingId/v1":"18cd7c07f06dc3e778c5e329160a7f0c474b40ca60b76405e16a725851f0714e"}},{"ruleId":"R1","level":"warning","message":{"text":"Type Safety: 0 typed \u00B7 34 plain JS \u2014 the untyped files are core/src/main/resources/org/apache/spark/ui/static/dataTables.rowsGroup.js, core/src/main/resources/org/apache/spark/ui/static/environmentpage.js, core/src/main/resources/org/apache/spark/ui/static/executorspage.js, core/src/main/resources/org/apache/spark/ui/static/flamegraph.js, core/src/main/resources/org/apache/spark/ui/static/historypage-common.js, core/src/main/resources/org/apache/spark/ui/static/historypage.js (\u002B28 more)."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"d00ee7953f55325a823d27e5db9657c80ca9b9861c0c0abf8fe487cd3fa586d3"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block with local edits (37 matched lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js:411 \u00B7 sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js:192 \u2014 the two spans are one implementation copied and then locally edited \u2014 296 tokens are still identical, in the same order in both files, with only local edits between them. The copies have already begun to drift, which is this row\u0027s finding: an edit made to one and not the other changes behaviour silently. Diff the two spans first to learn what genuinely differs, then extract the shared core into one module both sites use, passing the differences in as parameters \u2014 or, if one copy exists only because the other could not be imported from its context, make one of them the single source the other is generated or re-exported from. If one copy is no longer reachable, delete it rather than letting it shadow the live one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js"},"region":{"startLine":411}}}],"partialFingerprints":{"codehealthFindingId/v1":"d642adeb5747577425bed0a52fd742118a1a894aa85ccc12f0edaf57ed91fde4"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (33 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:696 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:851 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":696}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dd07bcad63fec15b04e32b1925ee3aa7d561ea0290f3867385fa9567aef1d85"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/timeline-view.js:108 \u00B7 core/src/main/resources/org/apache/spark/ui/static/timeline-view.js:209 \u00B7 core/src/main/resources/org/apache/spark/ui/static/timeline-view.js:289 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/timeline-view.js"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"b516dc19584eb30bba7d71e2369fc38fbae0561280284dbae15807a225380ecf"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (22 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/utils.js:205 \u00B7 core/src/main/resources/org/apache/spark/ui/static/utils.js:228 \u00B7 sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/sql-table-utils.js:153 \u2014 the 2 copies are spread across 2 directories, so the shared home is a decision rather than an obvious spot: check first whether one of them already owns this behaviour, and otherwise put the extracted module somewhere all of the sites already reach rather than making one of them depend on another."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/utils.js"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a7319e094b71a6a5fac9d71d3b1edbe81a409814c5a70450c464982286c902d"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:871 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:921 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":871}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7e213a40eadd12dfd7fda873913c09b720f427ddda9d3f5cdd8dc8b755c2ae8"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 4 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:621 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:639 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:657 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:675 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":621}}}],"partialFingerprints":{"codehealthFindingId/v1":"af0ffac32eef2f3d6662c6624ebc9b5a465d89af586a80ae81f3311cbcd099db"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:524 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:543 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:561 \u2014 all 3 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":524}}}],"partialFingerprints":{"codehealthFindingId/v1":"92d665b3c248ef21968a1faa09b872c11f518e18d0fc9c70c6b7799f8487cda3"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:590 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:819 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":590}}}],"partialFingerprints":{"codehealthFindingId/v1":"31be68f0bea443505dac819e77ba3600f59e11121f742c4ad3c8a5bfdf8d8263"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/sorttable.js:286 \u00B7 core/src/main/resources/org/apache/spark/ui/static/sorttable.js:301 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"921e2203f5e804f6b900b7cfd4216af051b0bafc8ae08ea05902344c6f6a2c41"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:964 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:978 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:1002 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":964}}}],"partialFingerprints":{"codehealthFindingId/v1":"9717cc795ec50165e7877d477b9213479002eb9b011358be23122b32b0b6442c"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:60 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:77 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"60f264363b1a5da4442769ab8d5e1967afba5faafbfd0685ad9e060f1a3f4f1e"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:940 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:1032 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":940}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca7c486108cd399ea285767689c09bb7f7dd56db874ac15742e639d3b04c6715"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:982 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:1022 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":982}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c62b5b97257e24130b0a718ce1e349e882ad462da100d73d7c8a27b2d7f1f38"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:234 \u00B7 core/src/main/resources/org/apache/spark/ui/static/historypage.js:66 \u00B7 core/src/main/resources/org/apache/spark/ui/static/historypage.js:81 \u2014 the 3 copies are spread across 2 files, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"be942c90726c15635da7cf43375a3299cf48385a70b4568f2b486202c756c1a8"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:892 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:902 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":892}}}],"partialFingerprints":{"codehealthFindingId/v1":"ebe871fac40dbed6379a00eec99cd6dca8d01bf0b7a260c863a94ddb200469a3"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:1024 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:1034 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":1024}}}],"partialFingerprints":{"codehealthFindingId/v1":"882b03aa602a8d48b35346280e5e4c349aae288b6c1c08d9fb4356ac8bbafb44"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2 locations): sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js:57 \u00B7 sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js:719 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"5de3ffbdb0737edee7443c979a6da82e834af95a743e2488bfffed9b49c25f80"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/utils.js:114 \u00B7 core/src/main/resources/org/apache/spark/ui/static/utils.js:224 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/utils.js"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"93527ce2874421fff35a7dea0abbb3f312969b449ae7a473cb78830e3ab577af"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block with local edits (9 matched lines \u00D7 2 locations): sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js:885 \u00B7 sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js:1100 \u2014 the two spans are one implementation copied and then locally edited \u2014 101 tokens are still identical, in the same order in both spans, with only local edits between them. The copies have already begun to drift, which is this row\u0027s finding: an edit made to one and not the other changes behaviour silently. Diff the two spans first to learn what genuinely differs, then extract the shared core into one module both sites use, passing the differences in as parameters \u2014 or, if one copy exists only because the other could not be imported from its context, make one of them the single source the other is generated or re-exported from. If one copy is no longer reachable, delete it rather than letting it shadow the live one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":885}}}],"partialFingerprints":{"codehealthFindingId/v1":"a618fa08690717c8d24945233d3e09406a448c58f8c1fef9c04a120c62b7a950"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:291 \u00B7 core/src/main/resources/org/apache/spark/ui/static/executorspage.js:301 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"d57a226924fe9ccca68e5bc1650c560341dfadbbf96892b23819e684e36492db"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/executorspage.js:916 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:384 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:392 \u2014 the 3 copies are spread across 2 files, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":916}}}],"partialFingerprints":{"codehealthFindingId/v1":"26fd268c513cc13cca5c8503a75128d91420bc61dc426208f9a1927c3302cb88"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js:172 \u00B7 core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js:184 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf5e8647115b449304160b10c23fef219e1d408978fc18d6f65d51a5b89e41bd"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3 locations): core/src/main/resources/org/apache/spark/ui/static/streaming-page.js:176 \u00B7 core/src/main/resources/org/apache/spark/ui/static/streaming-page.js:281 \u00B7 core/src/main/resources/org/apache/spark/ui/static/structured-streaming-page.js:35 \u2014 the 2 copies sit in sibling files in one directory, so check first whether one of them (or an existing module there) already owns this behaviour and the others should call it; otherwise extract it into one module in that directory and have each site call it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/streaming-page.js"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7c2195ad219c87ce238d54d985ad78160fb4e76de5790dc3a8e73841ad07ae3"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/stagepage.js:294 \u00B7 core/src/main/resources/org/apache/spark/ui/static/stagepage.js:308 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"b306abfed351760cd4a369913907a3a5a60314582791a522b0556895f3cccc3a"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/streaming-page.js:150 \u00B7 core/src/main/resources/org/apache/spark/ui/static/streaming-page.js:259 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/streaming-page.js"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbab6f019533b2b8754180bb5917cd9ba87422f74160931cead841474611c1ff"}},{"ruleId":"R10","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2 locations): core/src/main/resources/org/apache/spark/ui/static/timeline-view.js:191 \u00B7 core/src/main/resources/org/apache/spark/ui/static/timeline-view.js:198 \u2014 all 2 copies are in the same file, and the CITED SPAN is not a self-contained block \u2014 it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead \u2014 the whole function, component or branch these lines sit in \u2014 and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/timeline-view.js"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f4dc3ae940e276f9c6ab4596631b69a7d70a944d35e3250b24cf70bbf06166c"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function (anonymous) (cyclomatic 19, cognitive 15): (anonymous) has cyclomatic complexity 19 and cognitive complexity 15; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive sits below cyclomatic here, so much of the count is breadth \u2014 arms side by side rather than stacked \u2014 and splitting per arm would leave a function per arm; group the work between the checks into named steps instead. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":678}}}],"partialFingerprints":{"codehealthFindingId/v1":"15a4fa510638bb4a152d769b462689ea2a9c1143bf0d860e293736d1c3ebd0ac"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function updateDetailsPanel (cyclomatic 18, cognitive 19): updateDetailsPanel has cyclomatic complexity 18 and cognitive complexity 19; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"131cd401614f11c8eca9cfd407e8a512a6915a6513d42720b208357261804ae7"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function getInnerText (cyclomatic 17, cognitive 19): getInnerText has cyclomatic complexity 17 and cognitive complexity 19; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2b3423751ab5bd3764b4d62195a81b9d056f7e23869f74c0cd64a9f448470a5"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function innerSortFunction (cyclomatic 15, cognitive 23): innerSortFunction has cyclomatic complexity 15 and cognitive complexity 23; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"0040b61d1f0edd48b98ac5e684aad600b343d32856179dbe5fe9452105ca75fe"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function (anonymous) (cyclomatic 15, cognitive 18): (anonymous) has cyclomatic complexity 15 and cognitive complexity 18; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e6a67ca024a42a57a39663a37256fb26c239330acfb1ef7cfad491154d674a2"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function formatMetricValue (cyclomatic 15, cognitive 16): formatMetricValue has cyclomatic complexity 15 and cognitive complexity 16; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":344}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7c6e2ef2392b21071f49fcf563970142c07671c63a48dd68248ce4c197a7f70"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function (anonymous) (cyclomatic 15, cognitive 12): (anonymous) has cyclomatic complexity 15 and cognitive complexity 12; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive sits below cyclomatic here, so much of the count is breadth \u2014 arms side by side rather than stacked \u2014 and splitting per arm would leave a function per arm; group the work between the checks into named steps instead. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1118}}}],"partialFingerprints":{"codehealthFindingId/v1":"be4e24e979fd41e23da55c60c76eb25086891ef47b9f744064882e99933ee873"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function makeSortable (cyclomatic 14, cognitive 22): makeSortable has cyclomatic complexity 14 and cognitive complexity 22; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbb84cbe36c3e3a40f0c337c4e81148dec897f6ba6985b0b5c0357f3d45c65d0"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function (anonymous) (cyclomatic 14, cognitive 14): (anonymous) has cyclomatic complexity 14 and cognitive complexity 14; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/environmentpage.js"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"eed8863e7bedd425f6b0ec08fbc76e79535a0e0aed21d68e16c11987d3b46196"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function reselectCheckboxesBasedOnTaskTableState (cyclomatic 12, cognitive 18): reselectCheckboxesBasedOnTaskTableState has cyclomatic complexity 12 and cognitive complexity 18; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"6283b2f2dc712fcd4f6fe4e9bef25453d883759706aea1882a0d56f185046b61"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function zoomToNode (cyclomatic 12, cognitive 9): zoomToNode has cyclomatic complexity 12 and cognitive complexity 9; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive sits below cyclomatic here, so much of the count is breadth \u2014 arms side by side rather than stacked \u2014 and splitting per arm would leave a function per arm; group the work between the checks into named steps instead. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1047}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b43097724ac6ae3d01f708349519d1ec3c3793dedf941b62a23c854768d15c6"}},{"ruleId":"R2","level":"warning","message":{"text":"Complex function (anonymous) (cyclomatic 11, cognitive 12): (anonymous) has cyclomatic complexity 11 and cognitive complexity 12; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side \u2014 extracting each decision into its own named function is the change that pays. Measured by this repository\u0027s own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":951}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f1de1b0447f68bbdf63977b7688d4b00b0a13c6e727d0de2bd5b83c70c9b355"}},{"ruleId":"R3","level":"warning","message":{"text":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js: 1077 lines of code: core/src/main/resources/org/apache/spark/ui/static/stagepage.js has 1077 significant lines (blank lines excluded), over the 400-line bar, and contains logic \u2014 a file this long is usually several responsibilities in one module."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aad137ba9e919781ba419b6a0d614cf03471e7de03bb1c996d4af0077e173512"}},{"ruleId":"R3","level":"warning","message":{"text":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js: 1065 lines of code: sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js has 1065 significant lines (blank lines excluded), over the 400-line bar, and contains logic \u2014 a file this long is usually several responsibilities in one module."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b515daa1b5b456203e5555fed411631b653e4971390ccc4ccc86e342fb0b4ec"}},{"ruleId":"R3","level":"warning","message":{"text":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js: 907 lines of code: core/src/main/resources/org/apache/spark/ui/static/executorspage.js has 907 significant lines (blank lines excluded), over the 400-line bar, and contains logic \u2014 a file this long is usually several responsibilities in one module."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8122661ddf6bbbbea06c6f983863ccb91f8cfebf191067f28d6d629ad8659095"}},{"ruleId":"R3","level":"warning","message":{"text":"core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js: 529 lines of code: core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js has 529 significant lines (blank lines excluded), over the 400-line bar, and contains logic \u2014 a file this long is usually several responsibilities in one module."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eae001bb55fdc6a8d377fda42f65b87776cc28588e62e0accabb306e02e19227"}},{"ruleId":"R3","level":"warning","message":{"text":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js: 459 lines of code: core/src/main/resources/org/apache/spark/ui/static/sorttable.js has 459 significant lines (blank lines excluded), over the 400-line bar, and contains logic \u2014 a file this long is usually several responsibilities in one module."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0635edefa73f074b57058e13d3eb7e0bd9dc2b2b46d8fad4534104b64801e3f3"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/stagepage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1129ecb162ebf31a93268ee3ddd2d2519cf338d657c27c150dfc505398510f84"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3278d9cd787e3b5255553a533ba291031c56463f02f102c877328f6c6f7af2b8"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/sorttable.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ef148c086544b8dccd634e4a4fe357904513a887806d13198709f1b6b00ccde"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/timeline-view.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"32c62a821fc49e9884c694103784f1b3e97463e0f79672ab264c6e3a203f5754"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/historypage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2cdbbe68d7b4507bd082cb47fcaaa2d5055500435495dc5b99e924a6b98d916"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/sql-table-utils.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d13faa091d665fdb5ea2fc5eda52e1b12e6801259e7a38a18ac604349da58d4"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/dataTables.rowsGroup.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bce3c7c28bd2a6bbddfdfced8af6064bdb2d33cae54489f42682775d2b8fc7f"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"11d5e5d5ef932a5fa7498d65e37e11d41ef7b29509ec518a626665ba11e1a59f"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/webui.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb3b855f17549cd2cb77ef80aab2db63bc0166a89439c9cbc47ba911e0ed7754"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/executionpage.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7f7080facb928fa679352c495a32c18653c254f96f7d36c98412a25fa7b57f6"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/historypage-common.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dad274aa9205c95ccb39752ebf3408159d2c2dd46b6f09d4d86b4fc2501dc4dd"}},{"ruleId":"R4","level":"warning","message":{"text":"No test reaches this file: No test imports this module directly or transitively. Import reachability cannot see a test that executes a file by path instead of importing it, nor one that drives it through a running browser by navigating to a URL \u2014 if neither does, no test reaches this one."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/initialize-tooltips.js"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6de634874197201a1759eb3455883c81ddfb50b02b0ae6b2b5664345d540e39c"}},{"ruleId":"R8","level":"warning","message":{"text":"Unused dependency \u0027ansi-regex\u0027: Declared in dev/package.json but never imported anywhere in that package or its workspace members \u2014 no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"148fd747cc42f57a40e6914c6192b11870efd66e091ec9c7a83c346204b0f9fd"}},{"ruleId":"R8","level":"warning","message":{"text":"Unused dependency \u0027brace-expansion\u0027: Declared in dev/package.json but never imported anywhere in that package or its workspace members \u2014 no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"017e627a7ef90accfcff931a5b357108b116162491ebbdef25c1aa88fcf19d1a"}},{"ruleId":"R8","level":"warning","message":{"text":"Unused dependency \u0027minimatch\u0027: Declared in dev/package.json but never imported anywhere in that package or its workspace members \u2014 no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"0a823e0e288bb9022a688662cb46da78acfc9babd2e3980cf676cda35c1388b2"}},{"ruleId":"R8","level":"warning","message":{"text":"Unused dependency \u0027jquery\u0027: Declared in ui-test/package.json but never imported anywhere in that package or its workspace members \u2014 no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"3558d7366af476e7eb024a934b72268cae9477fa223da29863f386f4fe01ecc1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!idx.parent().isEmpty() \u0026\u0026 !idx.value().equals(KVIndex.NATURAL_INDEX_NAME)\u0060 appears character-identically in 2 files \u2014 common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java, common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"48ffad441a6c1339fd3102720e639afd965aa635839b72af12180724e90b7444"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!index.isChild() || params.parent != null\u0060 appears character-identically in 2 files \u2014 common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java, common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBIterator.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec3a25206cff81becc6ed1dbc1c191b74fef1ccb488edf58cf3a320cff628039"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(memory.pageNumber == MemoryBlock.NO_PAGE_NUMBER) || (memory.pageNumber == MemoryBlock.FREED_IN_TMM_PAGE_NUMBER)\u0060 appears character-identically in 2 files \u2014 common/unsafe/src/main/java/org/apache/spark/unsafe/memory/HeapMemoryAllocator.java, common/unsafe/src/main/java/org/apache/spark/unsafe/memory/UnsafeMemoryAllocator.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/memory/HeapMemoryAllocator.java"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f359276ad2fbc28c635ff28d992d0e94e572c5ae82749eaf4f4d5a2bcb83418"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(sizeInBytes == o.sizeInBytes) \u0026\u0026 ByteArrayMethods.arrayEquals(baseObject, baseOffset, o.baseObject, o.baseOffset, sizeInBytes)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java, sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java"},"region":{"startLine":371}}}],"partialFingerprints":{"codehealthFindingId/v1":"afd4c08f808a07adf3cafac1c4d718e691ac1e26ae60a3b9c15703db1900d9e3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060Integer.parseInt(blockIdParts[1]) != shuffleId || Integer.parseInt(blockIdParts[2]) != shuffleMergeId\u0060 appears character-identically in 2 files \u2014 common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalBlockHandler.java"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"e09839c111ed59f64734e817eb2eb0361904678c501fb91f848c8cb9dd7d4551"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060Objects.equals(appId, o.appId) \u0026\u0026 Objects.equals(execId, o.execId) \u0026\u0026 Arrays.equals(blockIds, o.blockIds)\u0060 appears character-identically in 2 files \u2014 common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveBlocks.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/OpenBlocks.java"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"d58171911ab8df06f57ecd1bcbfaef3afcd4b93100fbc1e2ea0bb38aa73dd923"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060Objects.equals(appId, o.appId) \u0026\u0026 appAttemptId == o.appAttemptId \u0026\u0026 shuffleId == o.shuffleId \u0026\u0026 shuffleMergeId == o.shuffleMergeId\u0060 appears character-identically in 2 files \u2014 common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/RemoveShuffleMerge.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/FinalizeShuffleMerge.java"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"07fc5dd1c8a778fa5bee71c6405c202a667c14f8baf9e4968cae8062c8b42f5f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060Objects.equals(name(), that.name()) \u0026\u0026 Arrays.equals(columns, that.columns()) \u0026\u0026 enforced() == that.enforced() \u0026\u0026 Objects.equals(validationS\u2026\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java, sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Unique.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b87cd2f3fa4d9553c340b1aab8d5170ec90111c8f4f7ad8117cd2f0d3aad41f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060base instanceof byte[] bytes \u0026\u0026 offset \u003E= BYTE_ARRAY_OFFSET\u0060 appears character-identically in 2 files \u2014 common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java, common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java"},"region":{"startLine":215}}}],"partialFingerprints":{"codehealthFindingId/v1":"e05701561f14acbff86171bdf39949ccab5a51e3c67e36d755ea8539c8638365"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060body instanceof InputStream || body instanceof ChunkedStream\u0060 appears character-identically in 2 files \u2014 common/network-common/src/main/java/org/apache/spark/network/protocol/EncryptedMessageWithHeader.java, common/network-common/src/main/java/org/apache/spark/network/protocol/SslMessageEncoder.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/EncryptedMessageWithHeader.java"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbec3477163afa6191f9ace8cbfcbd0449adac470f310499eb0123090ab16068"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060currentPage == null || pageCursor \u002B required \u003E currentPage.getBaseOffset() \u002B currentPage.size()\u0060 appears character-identically in 2 files \u2014 core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java, core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":446}}}],"partialFingerprints":{"codehealthFindingId/v1":"271229d59fed1e784c8af6cafa12b7cb152b07d613d15d71271924139a9a0cbf"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060dataType instanceof IntegerType || dataType instanceof YearMonthIntervalType\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java, sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"697cc8920c4a630e085b0ab44dd0562234beb5cd7b7b46ce473be9e0a16c1a88"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060dataType instanceof LongType || dataType instanceof DayTimeIntervalType\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java, sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatchRow.java"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"d47b5ba74172f85ef5e0f5a0a6da9f99e9535853eb08f06649e6bb238724f9cd"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060db != null \u0026\u0026 AppsWithRecoveryDisabled.isRecoveryEnabledForApp(appId)\u0060 appears character-identically in 3 files \u2014 common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java, common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java, common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleService.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bb5c8db1161984aa073e1ce577198e6a8dba25e08eaf2521220d51afa2ad05b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060dt instanceof IntegerType || dt instanceof DateType || dt instanceof YearMonthIntervalType\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarArray.java, sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/ValueCopier.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/vectorized/ColumnarArray.java"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"67d8b0e929d8e02226a4b75db10ad07f6f1cdada97d0efdd85b673a3606fe3a6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060expiresAt != null \u0026\u0026 !now.isBefore(expiresAt)\u0060 appears character-identically in 2 files \u2014 core/src/main/java/org/apache/spark/security/ServiceCredential.java, core/src/main/java/org/apache/spark/security/UserContext.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/security/ServiceCredential.java"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"564f0c146a216814fda053a6d558ce6b8422def6a17500a10faf2c6741802bcb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060idx.parent().isEmpty() || idx.value().equals(KVIndex.NATURAL_INDEX_NAME)\u0060 appears character-identically in 2 files \u2014 common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java, common/kvstore/src/main/java/org/apache/spark/util/kvstore/RocksDBTypeInfo.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBTypeInfo.java"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e6bdfd5a7b013bf3fad40e56c9dca0696226df0313e59ed767fd74ebf2a4d88"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060input != null \u0026\u0026 input.changePrecision(precision, scale)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/codegen/UnsafeArrayWriter.java, sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/codegen/UnsafeRowWriter.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/codegen/UnsafeArrayWriter.java"},"region":{"startLine":173}}}],"partialFingerprints":{"codehealthFindingId/v1":"b43484bef98ee16d5b35f09fdf1d7f6aad62dbf81b6d4dd527b4016bbea989db"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060msg instanceof ByteBuf || msg instanceof FileRegion\u0060 appears character-identically in 2 files \u2014 common/network-common/src/main/java/org/apache/spark/network/crypto/CtrTransportCipher.java, common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/crypto/CtrTransportCipher.java"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e9717fe51faf58c86e0b384aafd315226a2cdb0efbe17d913cc0f0889a92407"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060numRows \u003E= capacity || page == null || page.size() - pageCursor \u003C recordLength\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java, sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/VariableLengthRowBasedKeyValueBatch.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/FixedLengthRowBasedKeyValueBatch.java"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bfdad97413458cb8ac2b15168d855740e1ce6dc578843587636dd9db0e4beb8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060obj == null || getClass() != obj.getClass()\u0060 appears character-identically in 2 files \u2014 sql/api/src/main/java/org/apache/spark/sql/types/Geography.java, sql/api/src/main/java/org/apache/spark/sql/types/Geometry.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/java/org/apache/spark/sql/types/Geography.java"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"eac5577bd2b30a9148865542474f34df75b7bdcbc23be6b1ff61efbe34e02e01"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060offset == BYTE_ARRAY_OFFSET \u0026\u0026 base instanceof byte[] bytes \u0026\u0026 bytes.length == numBytes\u0060 appears character-identically in 2 files \u2014 common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java, common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe77d39587e2d7bebaa9f4d43b81a26360638b0526f731784ecaea7785471f00"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060other == null || getClass() != other.getClass()\u0060 appears character-identically in 6 files \u2014 sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/ColumnExpressionBase.java, sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/Check.java, sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/ForeignKey.java, sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/constraints/PrimaryKey.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/ColumnExpressionBase.java"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b962c1090b18467c9b4135cdea52dde938ea6e00dc949f5fb7feb577ad02624"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060principal.isEmpty() || keyTabFile.isEmpty()\u0060 appears character-identically in 2 files \u2014 sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java, sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/CLIService.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e7141d42f80e2d408a374ab6cec12b67d38c66bb66ebe48d0faa9402839cf99"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060requestId == o.requestId \u0026\u0026 super.equals(o)\u0060 appears character-identically in 3 files \u2014 common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java, common/network-common/src/main/java/org/apache/spark/network/protocol/RpcResponse.java, common/network-common/src/main/java/org/apache/spark/network/protocol/UploadStream.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/protocol/RpcRequest.java"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"59afd098b0c6486f65f36e3df346495cca7ec88df5139b8651a03345b562b31e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060spill.file.exists() \u0026\u0026 !spill.file.delete()\u0060 appears character-identically in 2 files \u2014 core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java, core/src/main/java/org/apache/spark/shuffle/sort/UnsafeShuffleWriter.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4f50174c255b312d65a358975b9b5c7216bd317394e5b2a6f0f27cc1dc45292"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060srid == other.srid \u0026\u0026 java.util.Arrays.equals(value, other.value)\u0060 appears character-identically in 2 files \u2014 sql/api/src/main/java/org/apache/spark/sql/types/Geography.java, sql/api/src/main/java/org/apache/spark/sql/types/Geometry.java. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/java/org/apache/spark/sql/types/Geography.java"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd8453090ff97e4462bd1860a11b717149769bee95b9fb025da22feef505fb38"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060\u0022options\u0022 in options and isinstance(options.get(\u0022options\u0022), dict) and len(options) == 1\u0060 appears character-identically in 4 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/generic.py, python/pyspark/pandas/namespace.py, python/pyspark/pandas/spark/accessors.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":5562}}}],"partialFingerprints":{"codehealthFindingId/v1":"01e93ae3968e73c5550d4141dc4f8460f463de5a72e68e02c7e8cfc0b1b9b062"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(inds.size == 0) or (index \u003E inds.item(-1))\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":837}}}],"partialFingerprints":{"codehealthFindingId/v1":"080508c339ac5cb9c2c51fc46f4e2f80d80695421fc5fceb6c72f20ec75e8b13"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(limit_area is not None) and (limit_area not in [\u0022inside\u0022, \u0022outside\u0022])\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6493}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b74a4e17cc4929468f47f00122617aef6ff05b1e9d9916c7fe0a889966f61e2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(limit_direction is not None) and ( limit_direction not in [\u0022forward\u0022, \u0022backward\u0022, \u0022both\u0022] )\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6489}}}],"partialFingerprints":{"codehealthFindingId/v1":"38671b008bcca2ab27caabcc1d1ceffc70e516b8e3fb77c2c066912034e4bdb2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060_have_scipy and scipy.sparse.issparse(d)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"62b1439d3564a75329788863269856e9918b0b9214bb61a6029734cffd713ade"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060_have_scipy and scipy.sparse.issparse(other)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":395}}}],"partialFingerprints":{"codehealthFindingId/v1":"428aa81ad7220d7dd470c114e894da7595df66a45b7dabf7ab4819c82a052deb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060_have_scipy and scipy.sparse.issparse(v)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"098f2b1bbe03c3d2e2c4e8e5d1235d04c4281cfb8cb15f6d54534da174354e01"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060bw_method is not None and isinstance(bw_method, (int, float))\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/plot/core.py, python/pyspark/sql/plot/core.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":424}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fbb84fdc64f446599e90a8b1391f3bae7387e4d3c9cb0901ded7a1ca261b7c2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060clsName != \u0022JavaRDD\u0022 and clsName.endswith(\u0022RDD\u0022)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/common.py, python/pyspark/mllib/common.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"b765d826296b9531d27f762a4c977049299a9be693f0c2638e9db39c66fe51c2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060columns is not None and not is_list_like(columns)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/namespace.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":10623}}}],"partialFingerprints":{"codehealthFindingId/v1":"73368b6808daea1b7d8f3ec5a7aba480527d419f8949bb7c0bfb6527c2785f22"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060extended is None and isinstance(mode, str)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c29117b36b27cb3f8b7d7a7cca2f904e2275639046c28dbfe5c5dc7c667c0cf"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060extended is not None and mode is not None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"dba9d463e0c163e2584029305e098cd61141b074f5f128330ee4a21b95258ec2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060f is None or isinstance(f, (str, DataType))\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/connect/functions/builtin.py, python/pyspark/sql/functions/builtin.py, python/pyspark/sql/pandas/functions.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":5831}}}],"partialFingerprints":{"codehealthFindingId/v1":"715147fa9cd1d13ec36123fbd527be7b50f2c14712ab28d5dd5566dcfd2ff188"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060field is None or field.struct_field is None\u0060 appears character-identically in 3 files \u2014 python/pyspark/pandas/indexes/base.py, python/pyspark/pandas/internal.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/indexes/base.py"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"3518fe5f0596a034db2a6fa0059e430007bc10cc3fff37be8eef69614472bf7c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060gateway is not None and SparkContext._jvm is not None\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/pipeline.py, python/pyspark/ml/tuning.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/pipeline.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2ff25039649056d9feb73e67ced101a73223b200436f9657a4272ada5780336"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060grouping_sets is None or isinstance(grouping_sets, list)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/group.py, python/pyspark/sql/connect/plan.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"dac1c43598e3c7783553707faf28bf036cbe435acf0161b804027a9e997df24f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060handle_dtype_as_extension_dtype(dtype) or is_str_dtype(dtype)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/base.py, python/pyspark/pandas/data_type_ops/boolean_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"24d088235abd443cb63e5fd5be7fe38f82f9aae34c1b97041445fba8fbb430ef"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060i \u003C len(self.indices) and j \u003C len(other.indices)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":767}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f06b73556f103bdf82ff82edb7c973b0088da9ea450cb03e4920beb90edd8f8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060ind \u003C colEnd and self.rowIndices[ind] == i\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1305}}}],"partialFingerprints":{"codehealthFindingId/v1":"c09281f591c8b08a2a3b83a7538fb8659ebe4eed5fbfe20fc5ba6a96ad4cd4e0"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060index \u003E= self.size or index \u003C -self.size\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":832}}}],"partialFingerprints":{"codehealthFindingId/v1":"f47f7fcb4b397da5d3119a02b69c56c8bdd1365aa76823b2f2b683d5d585fce9"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060is_datetime64_dtype(t) or isinstance(t, pd.DatetimeTZDtype)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/session.py, python/pyspark/sql/pandas/conversion.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":658}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2de9e0434cb135befe3f4ba18d12474286a432949eb0d5540c59a2e556c50b3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060is_integer_dtype(dtype) and not handle_dtype_as_extension_dtype(dtype)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/boolean_ops.py, python/pyspark/pandas/data_type_ops/num_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"f16c6d725416eeb5fd0f4353837259d922035d8bf2034b331e04707512b53168"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060is_list_like(lower) or is_list_like(upper)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":6724}}}],"partialFingerprints":{"codehealthFindingId/v1":"57e21ce510434f27c1c9557aa8b38b7bd57be360b5b8605b4ba1654093e36608"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060is_no_argument or is_extended_case or is_extended_as_mode or is_mode_case\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"85d8e268e402024eadcefe0ce598666a00ea5297edf51becc5251be8a54348f4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060is_remote() and \u0022PYSPARK_NO_NAMESPACE_SHARE\u0022 not in os.environ\u0060 appears character-identically in 3 files \u2014 python/pyspark/ml/util.py, python/pyspark/sql/observation.py, python/pyspark/sql/utils.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7297a1e3e8bba3ee008478da10140cf89539f1124d53986e635a472f96d13ea"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(c, int) and not isinstance(c, bool)\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py, python/pyspark/sql/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1051}}}],"partialFingerprints":{"codehealthFindingId/v1":"45faa29eeebaf7a00fd117490df7820a5903611bb7e13a932f0ec04b7adecfd3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(col, np.ndarray) and col.ndim == 1\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/functions/builtin.py, python/pyspark/sql/functions/builtin.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"1dfa0c1ac4e915b227d84b9aa577311a9aeb08d36b1066f623eca79c8e33974b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(data_source_cls, type) and issubclass(data_source_cls, DataSource)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/worker/create_data_source.py, python/pyspark/sql/worker/write_into_data_source.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/create_data_source.py"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"80d6ef8dec765aca7c8d91367f0d6bcfd11848b2515c320568f45555371a8637"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(extended, bool) and mode is None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"84359733259b3b06c147e1575231063ecc4dfe9e01365b5c996c0e1450382659"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(extended, str) and mode is None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfa107749ba82e72ddad6d30e6d0582d61eaa17cbb934070a3b2bcce9535b8c5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(group_type, str) and group_type in [ \u0022groupby\u0022, \u0022rollup\u0022, \u0022cube\u0022, \u0022pivot\u0022, \u0022grouping_sets\u0022, ]\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/group.py, python/pyspark/sql/connect/plan.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbe8f1465fcc56711d84d2f8be5a34d5ab232c817eeb9dfdbf3ab23fec25acf7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(other, np.ndarray) and other.ndim != 1\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":749}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c4aaf651b9bf19cd915736a782db3b9be324f35248fa1e93c77a8d7be1c94c5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(other, np.ndarray) or isinstance(other, DenseVector)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":748}}}],"partialFingerprints":{"codehealthFindingId/v1":"bed79111b047ca285b353fb08e057f5a581eaea6b5249f7e9202006cc2a7c859"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(other, self.__class__) and self.__dict__ == other.__dict__\u0060 appears character-identically in 2 files \u2014 python/pyspark/serializers.py, python/pyspark/sql/types.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/serializers.py"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"162d82ca74ce4da47feaa47dbcebfd90e474195ac716bbd819b203979d838986"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(return_type, StructType) and not isinstance(result, pd.DataFrame)\u0060 appears character-identically in 2 files \u2014 python/pyspark/eval_handlers/_elementwise.py, python/pyspark/eval_handlers/_pandas.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/eval_handlers/_elementwise.py"},"region":{"startLine":494}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0c342985bcafed53a4de114bcd479dc126ced5482e8c8ecf5c38665b6d39954"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(right, IndexOpsMixin) and handle_dtype_as_extension_dtype(right.dtype)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/boolean_ops.py, python/pyspark/pandas/data_type_ops/num_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/boolean_ops.py"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa6eeb268cd499c498267773f34dfac01691f48b68f8fe71fa2f4f65e4a03ae2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, BooleanType)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/base.py, python/pyspark/pandas/data_type_ops/boolean_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/base.py"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"493ea8193aef4f9f93286d7666cc518baa82680f69f0b2b01bbdbfec20bebe17"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/num_ops.py, python/pyspark/pandas/data_type_ops/string_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/num_ops.py"},"region":{"startLine":344}}}],"partialFingerprints":{"codehealthFindingId/v1":"20ab207e4fd2c968834abf19a3b24238e5c50fa5c8821e0f5ba344fe676be965"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(stage, Estimator) or isinstance(stage, Transformer)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/connect/pipeline.py, python/pyspark/ml/pipeline.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/connect/pipeline.py"},"region":{"startLine":189}}}],"partialFingerprints":{"codehealthFindingId/v1":"d27f9869c2f2cc6888d10d57a244c0ae4be50ee20510b58904689638adc4eafd"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(to_replace, (list, tuple)) and isinstance(value, (list, tuple))\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1615}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3b2dee092061184e418ee5a41119faa42e43803a3344494e21d28bec1ee15ab"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(udf, Column) or not hasattr(udf, \u0022func\u0022) or ( udf.evalType != PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF )\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/group.py, python/pyspark/sql/pandas/group_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba68680c6a5bbbf18360049a011ddae6a925016796b0b6f7d3e4357e889aa423"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(value, (float, int, str)) or value is None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1646}}}],"partialFingerprints":{"codehealthFindingId/v1":"1894fccae1e9bbd6df68405d7743284c82080cf977849003f62a3e12803107b4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len is not None and not isinstance(len, (int, str, Column))\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/functions/builtin.py, python/pyspark/sql/functions/builtin.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2849}}}],"partialFingerprints":{"codehealthFindingId/v1":"02e624a43f49fd30767e7ac895693d2437e8f31b78e4fbde56dd0114974af830"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(cols) == 1 and isinstance(cols[0], (list, set))\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/classic/column.py, python/pyspark/sql/connect/column.py, python/pyspark/sql/functions/builtin.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"be9763ecf434333c5e7187d78a5020c3e5f4d15f6348ccc1297c7775d17a0c96"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(cols) == 1 and isinstance(cols[0], (list, tuple))\u0060 appears character-identically in 4 files \u2014 python/pyspark/sql/connect/readwriter.py, python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/readwriter.py"},"region":{"startLine":639}}}],"partialFingerprints":{"codehealthFindingId/v1":"95e3e8e46d6177579ef8fc3dc0a9ec31a8d5f40b4e4e923b5420dc979870abce"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(cols) == 1 and isinstance(cols[0], DataFrame)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/column.py, python/pyspark/sql/connect/column.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"870fcd5c496efe6e2aceb28f97be1e3dce65c5d34d84b84fff306ba71abcf86e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(cols) == 1 and isinstance(cols[0], list)\u0060 appears character-identically in 6 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/classic/table_arg.py, python/pyspark/sql/classic/window.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1063}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e833a82ef2e2b8b08aa7ac1d597e3b33767ae41d493f848630763bb1c94e845"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(cols) == 1 and not isinstance(cols[0], (int, str, Column)) and isinstance(cols[0], Sequence)\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py, python/pyspark/sql/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1043}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2a44032d23f8aa51d54fcfeebede84c9c77b6d489c7d8832a1de213d3ef67d3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(elements) == 1 and not isinstance(elements[0], (float, int))\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":950}}}],"partialFingerprints":{"codehealthFindingId/v1":"70ce0070ec795ae50f490011bbab04dacda86effeb8f909957ec666558b9f2c9"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(expr) == 1 and isinstance(expr[0], list)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1148}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cc07296f3a084c36cf3ab0d907994246054b13920f4858537f46aee0623afdb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(exprs) == 1 and isinstance(exprs[0], dict)\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/connect/dataframe.py, python/pyspark/sql/connect/group.py, python/pyspark/sql/group.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/dataframe.py"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"88cb22e468bb42928029ba83ddaaf658b64353946c0c2b743e9e6f8b193a2b90"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060len(parameters) == 1 and isinstance(parameters[0], list)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":443}}}],"partialFingerprints":{"codehealthFindingId/v1":"6896e7fae9c9b3f9fa679b2caacb7e0e5fbc435c6c07aadc600651b7af8ad38f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060message is not None and not isinstance(message, WriterCommitMessage)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/worker/commit_data_source_write.py, python/pyspark/sql/worker/python_streaming_sink_runner.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/commit_data_source_write.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b19c0e29e6e53545b2e24ac02985a9b867449e82fd6f350b1df36ad764d2fae"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060min_periods is not None and not isinstance(min_periods, int)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":1605}}}],"partialFingerprints":{"codehealthFindingId/v1":"979b4e9083c036a9125318cdaec250f82991f9c0d1728a4f4fc5673fc58c1d27"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060name is not None and not isinstance(name, str)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1264}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dee8364d3a1cb0a03b38a5216df898f0f2a1802437f0c394303fb64d398a67d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not delayThreshold or type(delayThreshold) is not str\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ffc9cb17c5f7a964cdbffc27a09715a0a77d6a78b10946dafdc7ca704425a0f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not eventTime or type(eventTime) is not str\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"d20f178e21f34511ccaf13e685c0f13996176144bf42be6d3e7adb642774ba3e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not is_list_like(indices) or isinstance(indices, (dict, set))\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/base.py, python/pyspark/pandas/frame.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/base.py"},"region":{"startLine":1642}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e11ab6da65e8494e76fd87b3cdef5dd95256518cebea87d2b34dfc41161366e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(continuous, str) or len(continuous.strip()) == 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"37a6a5db994b30dca0a555c523b5130425cbd173893cc661ba4986c9be8cbbef"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(n, int) or isinstance(n, bool)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"85ef7c1a0be4a9e3985ce6af08727e05dd2ec9a35bdd86d7a9363f182e0582cb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(path, str) or len(path.strip()) == 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"67b785283cbb91053d44cbbaa851a1f99d729efa3016d2fbc1f6c664d8a490b8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(processingTime, str) or len(processingTime.strip()) == 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":594}}}],"partialFingerprints":{"codehealthFindingId/v1":"514854fd9f15230aac2e4895425f5303e53e6653a7ca49ef280739fe6ebb2dda"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(realTime, str) or len(realTime.strip()) == 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":621}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ad551b8afcbf33c15dbc729429ae927e6e242961c7a86bd64ef977ff9964bae"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(right, IndexOpsMixin) and is_list_like(right)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/data_type_ops/null_ops.py, python/pyspark/pandas/data_type_ops/num_ops.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/data_type_ops/null_ops.py"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"b933f55f22f5bbda59efc187bb928cfc0732948a54645e31efdd37663591adee"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(timeout, (int, float)) or timeout \u003C= 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/query.py, python/pyspark/sql/streaming/query.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/query.py"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"636edd108e74034301b97be2eefb65ced41a467d92b3f30ca9f6167e7d9eeb85"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not isinstance(value, valid_types) and value is not None and not isinstance(to_replace, dict)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1602}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c666f4832dd684db23051c27894be3cd341b6a1017bda713ace28a9be057274"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060not queryName or not isinstance(queryName, str) or len(queryName.strip()) == 0\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/streaming/readwriter.py, python/pyspark/sql/streaming/readwriter.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/streaming/readwriter.py"},"region":{"startLine":546}}}],"partialFingerprints":{"codehealthFindingId/v1":"cabc55475156b7a2348e866f57462e56b312b3c8e83c332a1d1db0e03d7a26d5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060on is None and not isinstance(self.index, DatetimeIndex)\u0060 appears character-identically in 2 files \u2014 python/pyspark/pandas/frame.py, python/pyspark/pandas/series.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":14116}}}],"partialFingerprints":{"codehealthFindingId/v1":"00db551e704eb1b5a13760f0f1df57fa3eef5202bb7833bdb0c37199d254dd8e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060options is not None and not isinstance(options, dict)\u0060 appears character-identically in 3 files \u2014 python/pyspark/pipelines/api.py, python/pyspark/sql/avro/functions.py, python/pyspark/sql/connect/avro/functions.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pipelines/api.py"},"region":{"startLine":512}}}],"partialFingerprints":{"codehealthFindingId/v1":"65c073f8e15531f34dc882a78e6e35f5058b58681030bc42bc0a341e1e2cbf83"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060os.path.isfile(\u0022../RELEASE\u0022) and len(glob.glob(\u0022../jars/spark*core*.jar\u0022)) == 1\u0060 appears character-identically in 3 files \u2014 python/packaging/classic/setup.py, python/packaging/client/setup.py, python/packaging/connect/setup.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/packaging/classic/setup.py"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1d8366e87ce1aa2f82248df9affc3eb49e13451d3bb21e2480c1c096409a3e1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060other.size == self.size and np.array_equal(other.indices, self.indices) and np.array_equal(other.values, self.values)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":816}}}],"partialFingerprints":{"codehealthFindingId/v1":"98953861dbd7f56f6e9b30a36b68b5e5c793fbb71c1fd24cca0ae64c92475be4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parent_func and getattr(parent_func, \u0022__doc__\u0022, None)\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/common.py, python/pyspark/mllib/common.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/common.py"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ca1bea30e31a8907ffdf4ee2e31e4fc3c14d575d9909846f445c71016b9e03d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060pivot_col is not None and isinstance(pivot_col, Column)\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/group.py, python/pyspark/sql/connect/plan.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/group.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"42e7e041bae948c98bb5787f72a68ff5c5bd1ad6f59aa2da24aacd5927714386"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060sc is not None and sc._gateway is not None\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/classification.py, python/pyspark/ml/feature.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/classification.py"},"region":{"startLine":3900}}}],"partialFingerprints":{"codehealthFindingId/v1":"168450308564113388692e51891a99076165f832ab391ad0679fce0e84ec4b02"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060schema is not None and isinstance(schema, StructType)\u0060 appears character-identically in 3 files \u2014 python/pyspark/sql/connect/client/core.py, python/pyspark/sql/connect/dataframe.py, python/pyspark/sql/conversion.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1312}}}],"partialFingerprints":{"codehealthFindingId/v1":"e10f283d2238ad67b63c271517f42db0cae826888ddbc0e19b05665f1eb6a8c4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.numRows != other.numRows or self.numCols != other.numCols\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1157}}}],"partialFingerprints":{"codehealthFindingId/v1":"c22336917b937bcfbeb046d792fc18b6049657a298fc175437ac8b977923fbdd"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060session is None or session._sc._jsc is None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/session.py, python/pyspark/sql/session.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":1285}}}],"partialFingerprints":{"codehealthFindingId/v1":"a32007e5b1d223586ec1eb53753793e892f3a99f1da8924932750b784370c8d3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060start is not None and occurrence is None\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/connect/functions/builtin.py, python/pyspark/sql/functions/builtin.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":2820}}}],"partialFingerprints":{"codehealthFindingId/v1":"6573d7d0d13812a99a8df1fd0d5553ebff0be489a8fee5d1458d619fc06cb582"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060subset is None or isinstance(subset, (list, tuple, str))\u0060 appears character-identically in 2 files \u2014 python/pyspark/sql/classic/dataframe.py, python/pyspark/sql/connect/dataframe.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/dataframe.py"},"region":{"startLine":1627}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fb1a25289e5357f4a3d8ae2202121d90ae95545ef91e963b67c81e8ab799753"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060v1_indices[k1] == v2_indices[k2] and v1_values[k1] == v2_values[k2]\u0060 appears character-identically in 2 files \u2014 python/pyspark/ml/linalg/__init__.py, python/pyspark/mllib/linalg/__init__.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/linalg/__init__.py"},"region":{"startLine":1008}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f002145bc56afd2df5e445d54b78677b953bbd25ea3157219a7bf82e2a8e161"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!conf.exchangeReuseEnabled || buildKeys.isEmpty\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveDynamicPruningFilters.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PlanDynamicPruningFilters.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveDynamicPruningFilters.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"5003f2c5369609eda54429fbe3bb744e326c26566df1bc62dc7ecd9911dd0763"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!context.isInterrupted() \u0026\u0026 !context.isCompleted()\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousWriteRDD.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1340}}}],"partialFingerprints":{"codehealthFindingId/v1":"816a6113b2e0d63a0c3784592ca9ad55fdb62e6c3d3171dc09140622de5afa15"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!hasInput \u0026\u0026 groupingExpressions.isEmpty\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b9047ea973271bddd9a7a8956496cf75dca4317cee8006a5fdb11d26f1f1a74"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!hasInput \u0026\u0026 groupingExpressions.nonEmpty\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a803cee1da2b76dbcdb3959766b14f2fff092dc6bb4d38ea203d623ac7ea00"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!m.schemaEvolutionEnabled || (m.schemaEvolutionReady \u0026\u0026 m.pendingSchemaChanges.isEmpty)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveRowLevelCommandAssignments.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1814}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4c2d8dc7e371df7f95b54eff239ab7fda0b6ced2f1e732ac69be3fa7603f5e7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!o2.isInstanceOf[Array[Byte]] || !java.util.Arrays.equals(b1, o2.asInstanceOf[Array[Byte]])\u0060 appears character-identically in 3 files \u2014 sql/api/src/main/scala/org/apache/spark/sql/Row.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/Row.scala"},"region":{"startLine":498}}}],"partialFingerprints":{"codehealthFindingId/v1":"c61c05ae6d83f38b086e85d02c9e1dd93fb1919de62fa6698ae436b466401af9"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!o2.isInstanceOf[Double] || ! java.lang.Double.isNaN(o2.asInstanceOf[Double])\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"edd523cfb119b21576c1080dbc7c1f181e66943704531cd39e671b2ff7cdeb7c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!o2.isInstanceOf[Float] || ! java.lang.Float.isNaN(o2.asInstanceOf[Float])\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GenericArrayData.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"aba522293d2a055a3235a26e2372d01dfd947cf55b96d84704f6638a51ef355a"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!plan.isInstanceOf[Subquery] \u0026\u0026 plan.containsPattern(CTE)\u0060 appears character-identically in 3 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InlineCTE.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/PushdownPredicatesAndPruneColumnsForCTEDef.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InlineCTE.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"a66b45d860c552313ec13336ff498e9c0d4aacbe8f35c4a7481098ebc0ed642c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!t1.isInstanceOf[DecimalType] \u0026\u0026 !t2.isInstanceOf[DecimalType]\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5969a6591a9da337297d444e1148ea7a4958344f1140b1867cbdc2b23ed23d8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060$(inputCol).nonEmpty \u0026\u0026 $(outputCol).nonEmpty\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala, mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"0526b024f67ff9379ff0ebad5e82fe69db12963215123e4f76f65466c6c1025b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060$(predictionCol).nonEmpty || $(leafCol).nonEmpty\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala, mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bc7b02665523c1d123bd13312b6cc6649791e515dfa17d077ffe1097123cd02"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(bufferIterator != null \u0026\u0026 bufferIterator.hasNext) || nextRowAvailable\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":345}}}],"partialFingerprints":{"codehealthFindingId/v1":"d83ca18a41f6919f2018e2aae431b90aceb519124268af09e9e04a14627dec09"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(bufferIterator == null || !bufferIterator.hasNext) \u0026\u0026 nextRowAvailable\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactory.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dd1e7f1bcc370dbd39a76bdbbd40336bbb7c4ff161c9dd31111ce6ab2e2c67d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(nnz(i) \u003C totalCnt) \u0026\u0026 (currMax(i) \u003C 0.0)\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala, mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":750}}}],"partialFingerprints":{"codehealthFindingId/v1":"35a8a77d2b80a790c97fbb670c50da1b9dab8729d510c33fab3ac23e15a5a9c4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(nnz(i) \u003C totalCnt) \u0026\u0026 (currMin(i) \u003E 0.0)\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala, mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":765}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a7a3e2c33077bdee9b301ec9057b6222d4cec73ecad3ea1e6ab9f899b6a7125"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(outputMode.contains(Append) || outputMode.contains(Update)) \u0026\u0026 eventTimeWatermarkForEviction.isDefined \u0026\u0026 newInputWatermark \u003E eventTimeWate\u2026\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"64d34863a26330391423eb0a8648c34da2d5033ceb1f7bcc50d6604854572b0b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(safeEnd - safeStart) % step == 0 || (safeEnd \u003E safeStart) != (step \u003E 0)\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/SparkContext.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/SparkContext.scala"},"region":{"startLine":1099}}}],"partialFingerprints":{"codehealthFindingId/v1":"1cc08161716c955e0eef41d88109ffd87257bcc93cda0edb7f970c41bac0d0cb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060CatalogV2Util.isSessionCatalog(catalog) || catalog.isInstanceOf[TableCatalog]\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RelationResolution.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala"},"region":{"startLine":1498}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a001a2489e4ba55e8e3b08587d3dfbba8a5ffe450f0cedd823e7acc9bb7d65e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060SQLConf.get.legacyTimeParserPolicy == LegacyBehaviorPolicy.LEGACY || options.timestampFormatInRead.isEmpty\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f7976ef8ac700b74de9c04c6747105a572636bb2dbdf11a670d0990122fe744"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060X.numRows == Y.numRows \u0026\u0026 X.numCols == Y.numCols\u0060 appears character-identically in 2 files \u2014 mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ff3c96ebc76a97cee8d8cf7dccde09fac8889ed9c9ec252acfb300b23e5ceec"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060agg.isDistinct \u0026\u0026 listAgg.hasDistinctOrderAmbiguity\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/resolver/AggregateExpressionResolver.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":694}}}],"partialFingerprints":{"codehealthFindingId/v1":"d173c39f04dc5c00d446d72cdea051fe60ab4f1a6a6eff849ebd6efc30c56a28"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060appInfo.attempts.nonEmpty \u0026\u0026 appInfo.attempts.head.completed\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/deploy/history/HistoryAppStatusStore.scala, core/src/main/scala/org/apache/spark/deploy/history/HistoryPage.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/HistoryAppStatusStore.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"f43abc642dce0c9df3d845791742c1944e9853c92c9c3c299cd2e5a28935f6bf"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060archiveEnabled \u0026\u0026 SupportsArchiveFormat.isArchivePath(currentFile.getPath)\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"a43ab5f39f3afc0c70019c1cc52ee420b198f193e212baf8d5f4146e32da0fd6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060archiveFormatEnabled \u0026\u0026 SupportsArchiveFormat.isArchivePath(file.toPath)\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"36fd88d6fc4ff27af93243a37590c45fd1c835378a7532db4a2af1f691dfb188"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060args.primaryRFile != null \u0026\u0026 (args.primaryRFile.endsWith(\u0022.R\u0022) || args.primaryRFile.endsWith(\u0022.r\u0022))\u0060 appears character-identically in 2 files \u2014 resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala, resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala"},"region":{"startLine":750}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e853b4686dfe28e04c49604d95b99d13da216603a67f716c0b50417bd25b6c1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060bcScaledMean != null \u0026\u0026 bcScaledMean.value.length == bcInverseStd.value.length\u0060 appears character-identically in 4 files \u2014 mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala, mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HingeBlockAggregator.scala, mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/HuberBlockAggregator.scala, mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/MultinomialLogisticBlockAggregator.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/optim/aggregator/BinaryLogisticBlockAggregator.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0918dcaad10c0eb3d665e90d12d07a8ca4fafdd6c9f918f170b665682c69446"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060c == \u0027\u003E\u0027 \u0026\u0026 prevC == \u0027/\u0027 \u0026\u0026 canSelfClose\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1148}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d6357a65379f9ae2fef24330018c6005051fcb563a568ea71010ad0c49996d7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060codec == null || codec.isInstanceOf[SplittableCompressionCodec]\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/util/Utils.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/Utils.scala"},"region":{"startLine":3100}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c3cfc2a4edefd309739aa25b9e0c09bac5edd4771935fe7829ed4bac4770b4e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060conf.cboEnabled || conf.planStatsEnabled\u0060 appears character-identically in 3 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala"},"region":{"startLine":1212}}}],"partialFingerprints":{"codehealthFindingId/v1":"06a042dda0b80292595792cf33a05e7a13f746898282d3bfbab12e23ca19c103"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060conf.getConf(SQLConf.DECORRELATE_SUBQUERY_PREVENT_CONSTANT_FOLDING_FOR_COUNT_BUG) \u0026\u0026 mayHaveCountBug.nonEmpty \u0026\u0026 mayHaveCountBug.get\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala"},"region":{"startLine":431}}}],"partialFingerprints":{"codehealthFindingId/v1":"6352472cd036160a0c7621108844e7cebe724cd37c6f3319a50e3d3a4e09d204"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060conf.getConf(SQLConf.MAP_KEY_DEDUP_POLICY) == mapKeyDedupPolicy \u0026\u0026 conf.getConf(SQLConf.DISABLE_MAP_KEY_NORMALIZATION) == disableMapKeyNorma\u2026\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/toFromProtobufSqlFunctions.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/avroSqlFunctions.scala"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae8375a785b184d8ffc565ae018594b0edbcff063874c74683af0c6ca1d7045a"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060creds.numberOfTokens() \u003E 0 || creds.numberOfSecretKeys() \u003E 0\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/scheduler/SupportsDelegationToken.scala, resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/KerberosConfDriverFeatureStep.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/SupportsDelegationToken.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab7f8179bc3a0fba50b8728c043a61240f00261565a68982798e0d5e7767eb33"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060datum != null \u0026\u0026 options.ignoreSurroundingSpaces\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":794}}}],"partialFingerprints":{"codehealthFindingId/v1":"a29dc01f0125b3da1494bf3d1d65a55d8bc1d29a6ee05c92e773468fd012ecf4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060datum == options.nullValue || datum == null\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0fa753b7ba441cec0c732e4ecf961575357299bf463a91baa4b41db1d59cc9e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060driverUrl == null || executorId == null || cores \u003C= 0 || appId == null\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala, resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBackend.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala"},"region":{"startLine":598}}}],"partialFingerprints":{"codehealthFindingId/v1":"facb38d2da6d207119f91de645a239115df01d6b45be44fa6d3b3e0ebfe61eb6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060e.foldable \u0026\u0026 e.dataType.isInstanceOf[StringType]\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala"},"region":{"startLine":525}}}],"partialFingerprints":{"codehealthFindingId/v1":"aae9d3e5d05d7cf9f052aacc6cf33a8b48d64ce853284c91234b59d1903c54ee"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060eventTimeWatermarkForEviction.isDefined \u0026\u0026 newInputWatermark \u003E eventTimeWatermarkForEviction.get\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/join/StreamingSymmetricHashJoinExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/transformwithstate/TransformWithStateExecBase.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"23e0b3cab6de64677837c94114ebe519f30ab4b81b4b9858941f3241ea6e8a13"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060f.deterministic \u0026\u0026 !SubqueryExpression.hasSubquery(f) \u0026\u0026 !f.exists(_.isInstanceOf[PythonUDF])\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/PruneHiveTablePartitions.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"28cfa3701b58a48904e63d5b27065d4fb58378963105ac0e20d5985e5fb6eb46"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060featuresStd(i) == 0.0 \u0026\u0026 featuresMean(i) != 0.0\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala, mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala"},"region":{"startLine":609}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2d5553f3cb1a27bfc463cd4b3b9cdac360fdacd59ef143d2bb2cbaddc3fe092"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060field.getName == \u0022metadata\u0022 \u0026\u0026 field.getField.getMetadata .containsKey(\u0022variant\u0022) \u0026\u0026 field.getField.getMetadata.get(\u0022variant\u0022) == \u0022true\u0022\u0060 appears character-identically in 2 files \u2014 sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala, sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowSerializer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/arrow/ArrowDeserializer.scala"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"a599105234df9a24f5b64cb39f26ba697be0a764a242fda683275241b2fa8901"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060filter.isDefined \u0026\u0026 translatedFilterToExpr.isDefined\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala"},"region":{"startLine":751}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8634db5646cee50435dfff35ecdac5846ba1c78ca7c2f4fb4864dae5f772965"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060finishTimestamp \u003E 0L \u0026\u0026 !isExecutionActive\u0060 appears character-identically in 2 files \u2014 sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerAppStatusStore.scala, sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2AppStatusStore.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerAppStatusStore.scala"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"e064164aea45b4308415b8dbaf128aa5e9b0081832e2df82e9ccca60d531b54d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060i \u003C indices.length \u0026\u0026 j \u003C selectedFeatures.length\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala, mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/feature/Selector.scala"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"8604915ff35536cdef7cb32a36b70b9b44910325cd74ffa829ee3abd185b2b6d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060i \u003C validFieldIndexes.length \u0026\u0026 !skipRow\u0060 appears character-identically in 2 files \u2014 connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala, sql/core/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDeserializer.scala"},"region":{"startLine":494}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1f4c1373c547280e23e4e2eb3c3e251eed5ac1668b33c53b65fa997add7eb1c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060i == (startTag.length - 1) \u0026\u0026 Character.isWhitespace(c)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1053}}}],"partialFingerprints":{"codehealthFindingId/v1":"03a02b7a916d3a933a586f2f88b3b8ce78c0b3d48197d26b684058cc175a2ccd"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060ignoreCorruptFiles \u0026\u0026 DataSourceUtils.shouldIgnoreCorruptFileException(e)\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FilePartitionReader.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d2f0573dd09c071b6d05996b577a8850e6211501ea85f5a1c0a52626a87b878"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060ignoreMissingFiles \u0026\u0026 ExceptionUtils.getThrowables(e).exists(_.isInstanceOf[FileNotFoundException])\u0060 appears character-identically in 3 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ffc2999679dd74f3b4ed21e6e54327c53c1fe3f85b52c67e2e698cca6ca0c86"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060incorrectOffsets.nonEmpty \u0026\u0026 attempt \u003C maxOffsetFetchAttempts\u0060 appears character-identically in 2 files \u2014 connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala, connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"53250269723725b3dce837eeab862e8afc784646578c97504bbc29e23aecacf7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isAtDriverSide \u0026\u0026 lastAttemptAccumulatorInitialized \u0026\u0026 !lastAttemptAccumulatorInvalid\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/util/LastAttemptAccumulator.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/metric/SQLLastAttemptAccumulator.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/LastAttemptAccumulator.scala"},"region":{"startLine":680}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d2601c560ac68153b98cec9c1c7195f5f4d81db0fb0ef0924a1d826a6f0e1a6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isCancelled() || Thread.currentThread().isInterrupted\u0060 appears character-identically in 2 files \u2014 common/utils/src/main/scala/org/apache/spark/util/MavenUtils.scala, common/utils/src/main/scala/org/apache/spark/util/RuntimeDependencyResolver.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/MavenUtils.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"263c8cdaba9c37d930fa7125abd20b4a8ce549c32269fea8cdd6905891c558f8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isDefaultNTZ \u0026\u0026 timestampNTZFormatter.parseWithoutTimeZoneOptional(field, false).isDefined\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchema.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchema.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"7766ac8ba7960cfa9ba786828f953cec20072706c2b7d17e5220e0f37aa5be06"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isDefined(validationIndicatorCol) \u0026\u0026 $(validationIndicatorCol).nonEmpty\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala, mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala"},"region":{"startLine":177}}}],"partialFingerprints":{"codehealthFindingId/v1":"25eb0d7d5d4101fec53b3652719c780ff9a158fa1e1ada419bda593676b9c5d8"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isDefined(varianceCol) \u0026\u0026 $(varianceCol).nonEmpty\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala, mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b1039bb7f6b92438e0df1375f4405321732af928317b9fb4ced0d34a18c6d63"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isDistinct \u0026\u0026 distinctUnsupportedAggregateFunctions.contains(funcName)\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala, sql/core/src/main/scala/org/apache/spark/sql/jdbc/H2Dialect.scala, sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala, sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/jdbc/DB2Dialect.scala"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"3eea9cf3782a79b2d2b0e24795f59e21740334afa472d2012a54e6eb52f15cf5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isFromBarrier || dependencies.exists(_.rdd.isBarrier())\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala, core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a0fe1529ea4facdf3f09f7010109df1096d0ea990ef4058d9d64d02d61fc988"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isTimeTypeEnabled \u0026\u0026 timeFormatter.parseOptional(field).isDefined\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchema.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVInferSchema.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad9cd4d1d583190d02c5fac6672a1844d97d46f9d4594b2222b8c2906e6b63f3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060joinType.isInstanceOf[InnerLike] \u0026\u0026 !hintToNotBroadcastAndReplicate(hint)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fa899681c6d27a02f72de9d29e7f9cc3cb3805c126afa34f0d8e3c263ff9c72"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060killEnabled \u0026\u0026 parent.securityManager.checkModifyPermissions(request.getRemoteUser)\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala, core/src/main/scala/org/apache/spark/ui/jobs/StagesTab.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7cbeb133e8ecc997c04cd609ce8d99d45868fc8ad0af5ead6c79744979f76fc"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060kv1 \u003E= nnzv1 || (kv2 \u003C nnzv2 \u0026\u0026 v2Indices(kv2) \u003C v1Indices(kv1))\u0060 appears character-identically in 2 files \u2014 mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":409}}}],"partialFingerprints":{"codehealthFindingId/v1":"900760785aa68c0c2f84ef1c4b0bad62d3987b7006c7739f787f47cc2c37cd50"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060kv2 \u003E= nnzv2 || (kv1 \u003C nnzv1 \u0026\u0026 v1Indices(kv1) \u003C v2Indices(kv2))\u0060 appears character-identically in 2 files \u2014 mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":406}}}],"partialFingerprints":{"codehealthFindingId/v1":"e098af6dd92f6d702f2f83a59dc03b40e12e63ba0849b4d7e206ff9db1a82ae5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060leftSortExprs.nonEmpty \u0026\u0026 rightSortExprs.nonEmpty\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeAsOfJoinExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala"},"region":{"startLine":2683}}}],"partialFingerprints":{"codehealthFindingId/v1":"ebb3971ac9108d795e1b96e321d81e434d0173dc9ee475ec9792a63a1f55dc1c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060live \u0026\u0026 liveUpdatePeriodNs \u003E= 0 \u0026\u0026 now - entity.lastWriteTime \u003E liveUpdatePeriodNs\u0060 appears character-identically in 3 files \u2014 core/src/main/scala/org/apache/spark/status/AppStatusListener.scala, sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ui/SparkConnectServerListener.scala, sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/HiveThriftServer2Listener.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/status/AppStatusListener.scala"},"region":{"startLine":1270}}}],"partialFingerprints":{"codehealthFindingId/v1":"c83724c80b6592a2aa51aa10cd725fd96a95439b72cb51e670b6c784b5130e10"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060lowerBound \u003C upperBound \u0026\u0026 lbound.compare(lowerRow, lowerBound, current, index) \u003C 0\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/window/SegmentTreeWindowFunctionFrame.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/window/SlidingWindowMinMaxFunctionFrame.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/SegmentTreeWindowFunctionFrame.scala"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca6208f88a4a66db6fe6874271f9b02cf706e7ed0492f8d8bbaa6033b6f540a3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060matchedActions.isEmpty \u0026\u0026 notMatchedActions.isEmpty \u0026\u0026 notMatchedBySourceActions.isEmpty\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala, sql/core/src/main/scala/org/apache/spark/sql/classic/MergeIntoWriter.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala"},"region":{"startLine":1345}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb3d7ed86ab6244024cfd4d2f06a55d203ada77e6d935b5d22566fd28f165619"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060minOffsetPerTrigger.isDefined \u0026\u0026 maxOffsetsPerTrigger.isDefined\u0060 appears character-identically in 2 files \u2014 connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala, connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSource.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc22767eb98283683f8d75c0e84dbe65577702f19fcfa318d69c93496fca1114"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060minPartitions.map(_ \u003E offsetRanges.size).getOrElse(false) || offsetRanges.exists(_.size \u003E maxRecordsPerPartition.getOrElse(Long.MaxValue))\u0060 appears character-identically in 2 files \u2014 connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala, connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"dee7cab1f35d8f843876cace978676644d648dd8e032d6fd96e8b3284cf6f597"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060mode != PermissiveMode \u0026\u0026 mode != FailFastMode\u0060 appears character-identically in 6 files \u2014 connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroDataToCatalyst.scala, connector/avro/src/main/scala/org/apache/spark/sql/avro/SchemaOfAvro.scala, connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csv/CsvExpressionEvalUtils.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroDataToCatalyst.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"0de9b92767a403b07ff8493aaf83663a1e61d20ee000f494928e61dfd4749154"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060modes.contains(Final) || modes.contains(Complete)\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregateCodegenSupport.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregationIterator.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregateCodegenSupport.scala"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"29f006f0ad31ca4cfc3b2bb43c77b864b1a8830021bb4f09ff2f6cf7289f24c1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060modes.contains(Partial) || modes.contains(PartialMerge)\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregateCodegenSupport.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregationIterator.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/AggregateCodegenSupport.scala"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"7eef3ccdeadbe324ca1630e089e6c7265d18afca71c0ca7a5f13b0c3acfd5ffa"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060nameParts(0).equalsIgnoreCase(CatalogManager.SYSTEM_CATALOG_NAME) \u0026\u0026 nameParts(1).equalsIgnoreCase(CatalogManager.SESSION_NAMESPACE)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/VariableResolution.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogs.scala"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"b285e56f0ba08f749556125a9537f80638493f451d89d35a2c17c7626a1da387"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060nextRow != null \u0026\u0026 ubound.compare(nextRow, upperBound, current, index) \u003C= 0\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/window/SlidingWindowMinMaxFunctionFrame.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowFunctionFrame.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/window/SlidingWindowMinMaxFunctionFrame.scala"},"region":{"startLine":152}}}],"partialFingerprints":{"codehealthFindingId/v1":"90c2b14f01e7327600b029fde447f6ea44fa501ea81f9cd18de3e899fe186453"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060nextRowAvailable \u0026\u0026 nextGroup == currentGroup\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowGroupLimitExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowWindowPythonEvaluatorFactory.scala"},"region":{"startLine":321}}}],"partialFingerprints":{"codehealthFindingId/v1":"bffe744153fa9365e522ea03e9ea81f7f4df064b49a32f56b10f945667339154"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060numRemovalsCurrRecord \u003C incrementalCleanupFactor \u0026\u0026 evictionIter.hasNext\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StatefulStreamlineAggregateExec.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a0088180e6f8fa1a24274b9e6d7c930dfb16ff8176b1111b247dccd4a8b407f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060originalThrowable != null \u0026\u0026 originalThrowable != t\u0060 appears character-identically in 2 files \u2014 common/utils/src/main/scala/org/apache/spark/util/SparkErrorUtils.scala, core/src/main/scala/org/apache/spark/util/Utils.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkErrorUtils.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"a955cfc563d750ae76b144aaa11f35d56e6a563bc07cf13b7a4bdf1f39883ce1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060outputMode != OutputMode.Append \u0026\u0026 outputMode != OutputMode.Update\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala, sql/core/src/main/scala/org/apache/spark/sql/classic/RelationalGroupedDataset.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/KeyValueGroupedDataset.scala"},"region":{"startLine":165}}}],"partialFingerprints":{"codehealthFindingId/v1":"5be8d6d93eb52d6b0625c0e3e6f39a494a358feabbc12c0dc8d1bf7dde8b52e2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060outputsMerged == 0 || counter.count == 0\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/partial/MeanEvaluator.scala, core/src/main/scala/org/apache/spark/partial/SumEvaluator.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/partial/MeanEvaluator.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7ad59a91655b48164927059bc5bcc175ffefab548f7387f7e2bfc367685f70f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060p \u003C TimestampLTZNanosType.MIN_PRECISION || p \u003E TimestampLTZNanosType.MAX_PRECISION\u0060 appears character-identically in 2 files \u2014 sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala, sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":547}}}],"partialFingerprints":{"codehealthFindingId/v1":"de227d331b873f7c65c1906352d05708bb68a37b3f708ae7f507cf4d6f5a63b5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060p \u003C TimestampNTZNanosType.MIN_PRECISION || p \u003E TimestampNTZNanosType.MAX_PRECISION\u0060 appears character-identically in 2 files \u2014 sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala, sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala"},"region":{"startLine":566}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fc84f692b7787c8b4e4b9d89b46805874c31a908b8b93d0bd655c06a5807c20"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parameterId != null \u0026\u0026 parameterId.nonEmpty\u0060 appears character-identically in 5 files \u2014 core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala, core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala, core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala, sql/core/src/main/scala/org/apache/spark/sql/streaming/ui/StreamingQueryStatisticsPage.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc6eb2661a8ce8b25a24e395e8aa02d60ceeab50a05e19452630411091bd4a69"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parent.sc.isDefined \u0026\u0026 parent.conf.get(UI_THREAD_DUMPS_ENABLED)\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/ui/exec/ExecutorsTab.scala, core/src/main/scala/org/apache/spark/ui/jobs/StagesTab.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/exec/ExecutorsTab.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"6897aa081fef3cd37b910fe48a1229fa43250686fb39f05eeda7ec7c55262a1a"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parsed != null \u0026\u0026 s.length == parsePosition.getIndex\u0060 appears character-identically in 2 files \u2014 sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala, sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe6f2756f9db7c6ce1f73b29b7973d035353811ca50e1e3df99100601e3023df"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parsedOptions.archiveFormatEnabled \u0026\u0026 SupportsArchiveFormat.isArchivePath(file.toPath)\u0060 appears character-identically in 3 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"29fa5b851209099576c19a631801a8f0d75c9c3321f095308a0058f35a75fa8d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060parsedOptions.archiveFormatEnabled \u0026\u0026 SupportsArchiveFormat.isArchivePath(path)\u0060 appears character-identically in 3 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroFileFormat.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2158d58f35873931ef863c1e6ed3f5fc33420895ed28164d8d630df87944fd7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060partitionId \u003E= 0 \u0026\u0026 partitionId \u003C numPartitions\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/LowLatencyMemoryStream.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"9478ebb2d45227d47aff1ba95c6d52d6087c40ef2351adffc92cad5f3f3788db"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060partitioning.nonEmpty \u0026\u0026 clustering.nonEmpty\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriterV2.scala, sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/DatasetManager.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/DataFrameWriterV2.scala"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"eef1bece14012f21dc4e9a5600b8505292f8060ec9614a63d6f157de4b50eb34"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060primaryPyFile != null \u0026\u0026 primaryRFile != null\u0060 appears character-identically in 2 files \u2014 resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala, resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2ad369f00c54b44ed67f6f4c76e12ba97270439e6d7b11725f7e09aefb6ed30"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060range.fromOffset \u003C 0 || range.untilOffset \u003C 0\u0060 appears character-identically in 2 files \u2014 connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala, connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchPartitionReader.scala"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"415024e661ca8ecc5e2c098b7c5946f26ac11292d0ab1a805061107cb6dc0d53"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060rangeIter.hasNext \u0026\u0026 removedValueRow == null\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StreamingSessionWindowStateManager.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/statefulOperators.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/StreamingSessionWindowStateManager.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"7100aca248de42ab478f5f02a3aef6bc24ba2f0e507727f013e2a19f9575a8fa"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060rawDataSize.isDefined \u0026\u0026 rawDataSize.get \u003E 0\u0060 appears character-identically in 2 files \u2014 sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/PruneHiveTablePartitions.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1437}}}],"partialFingerprints":{"codehealthFindingId/v1":"b108e2a8ea3e6e8771c5eb9d089d99513a895d274e16262197b65577c1d190c2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060readDataSchema.length == 1 \u0026\u0026 readDataSchema.head.name == parsedOptions.columnNameOfCorruptRecord\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonScan.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3fd122b397c4a10d0c19dd284eaa8bb2a8054fd8f8b1bcf5c888f36e86ba869"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060requiredSchema.length == 1 \u0026\u0026 requiredSchema.head.name == parsedOptions.columnNameOfCorruptRecord\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a45ca0c47963c733192a05d2db346de346264e3f89ffed6ae172ddd5d807b4b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060result.isEmpty \u0026\u0026 attempt \u003C= maxOffsetFetchAttempts \u0026\u0026 !Thread.currentThread().isInterrupted\u0060 appears character-identically in 2 files \u2014 connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala, connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderConsumer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala"},"region":{"startLine":501}}}],"partialFingerprints":{"codehealthFindingId/v1":"255e3f298f340c0c8e04f9ee607092d4ab4a864339432b38926c44e2b28c224d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060root.isInstanceOf[IOException] \u0026\u0026 !root.isInstanceOf[FileNotFoundException]\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"2748998c135bb2075696dadc770d7d36b1acb2ef72a9bbc8f9ce202122e601e7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060s.isMaterialized \u0026\u0026 s.mapStats.isDefined \u0026\u0026 s.shuffle.shuffleOrigin == ENSURE_REQUIREMENTS\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ConvertSortMergeJoinToShuffledHashJoin.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeSkewedJoin.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ConvertSortMergeJoinToShuffledHashJoin.scala"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7f11a98618af61a4d5cb8e9bee1104edac091ff941ea1b7ef6fe1794b6a73d3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060s1.collationId == s2.collationId \u0026\u0026 StringHelper.isMoreConstrained(s1, s2)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AnsiTypeCoercion.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"96c04b46cfbe19e2e68de01099c37bca2d3a70923c59b3da3f2874bb58264438"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060sc.isDefined \u0026\u0026 store .environmentInfo() .sparkProperties .contains((SCHEDULER_MODE.key, SchedulingMode.FAIR.toString))\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala, core/src/main/scala/org/apache/spark/ui/jobs/StagesTab.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/jobs/JobsTab.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"c799d66d27e4f232edd2795f6b48b8c4fa5dcdf11768fa5abfe18fb679dd3779"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060selected == 0 \u0026\u0026 idleTimeoutMillis \u003E 0 \u0026\u0026 (end - start) \u003E= idleTimeoutMillis\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonPlannerRunner.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1449}}}],"partialFingerprints":{"codehealthFindingId/v1":"03429a16b9a37e2539c610a6f268c271a2e17c30d6368ccd039027caeab7dcf2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060shuffle.outputPartitioning != SinglePartition \u0026\u0026 super.isSupported(shuffle)\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/CoalesceShufflePartitions.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeShuffleWithLocalRead.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/CoalesceShufflePartitions.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fa07647e36e858368e342ed74e55bf8965b937cc28fe4583a1ff532d877b740"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060si == (startTag.length - 1) \u0026\u0026 Character.isWhitespace(c)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlInputFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala"},"region":{"startLine":1157}}}],"partialFingerprints":{"codehealthFindingId/v1":"50eb6ee39c0aea44ad9c82d5fecf7387e5810bbe391951af956f8a5ae287551b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060speculationEnabled \u0026\u0026 outputCommitterClass.contains(\u0022Direct\u0022)\u0060 appears character-identically in 2 files \u2014 core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala"},"region":{"startLine":1041}}}],"partialFingerprints":{"codehealthFindingId/v1":"6af1909aa3c26eec8b6b56b5b657f996715c763eaa95c50cada52da090544c70"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060state == YarnApplicationState.FINISHED || state == YarnApplicationState.FAILED || state == YarnApplicationState.KILLED\u0060 appears character-identically in 2 files \u2014 resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala, resource-managers/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala"},"region":{"startLine":1274}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f15232f7b3abb64232bda99e132c70ea45f7531453aa7d37518e63603f7cd95"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060state.timeoutTimestamp != NO_TIMESTAMP \u0026\u0026 state.timeoutTimestamp \u003C timeoutThreshold\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/FlatMapGroupsInPandasWithStateExec.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/operators/stateful/flatmapgroupswithstate/FlatMapGroupsWithStateExec.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/FlatMapGroupsInPandasWithStateExec.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"e85d60db7704f0dbf8718109f2e87dc03e809ce58ef186a1c7c120aebd814855"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060supportDataType(keyType) \u0026\u0026 supportDataType(valueType)\u0060 appears character-identically in 6 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9adb857d167b846da5d0c5efa737760e586125ed9082372f1ebdad60b6ca70e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060supportsDataType(keyType) \u0026\u0026 supportsDataType(valueType)\u0060 appears character-identically in 4 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonTable.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcTable.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetTable.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala"},"region":{"startLine":134}}}],"partialFingerprints":{"codehealthFindingId/v1":"c66f6a5d486d40a2a3f5928380bdc734d1024ab6af73f4c6449ca796ca448911"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060t.containsPattern(PLAN_EXPRESSION) \u0026\u0026 cond(t)\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/AnalysisHelper.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":632}}}],"partialFingerprints":{"codehealthFindingId/v1":"72f968cf7344468ad76fab7909179fc5ac90b731099fd1d9909db9959edb847b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060tableExists \u0026\u0026 mode != SaveMode.Overwrite\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateHiveTableAsSelectCommand.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc72440628f87e226752ce37cfbc6656d83f1895e15622227e439b0032596ea5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060this.child == that.child \u0026\u0026 this.messageName == that.messageName \u0026\u0026 ( (this.binaryFileDescriptorSet.isEmpty \u0026\u0026 that.binaryFileDescriptorSet.\u2026\u0060 appears character-identically in 2 files \u2014 connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala, connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufDataToCatalyst.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/CatalystDataToProtobuf.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"a101c58e8ef9b94ef5829e6cfe6027f52d5b36baabdeb0340b1b3ba7c0c724b3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060this.totalWeightSum != 0.0 \u0026\u0026 other.totalWeightSum != 0.0\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala, mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f60dcb2a52d3b9bd6d5d61c6b9726fe6e794a5c8ba58752b66f1e3e0c994276"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060timestampConversion \u0026\u0026 !isCreatedByParquetMr\u0060 appears character-identically in 2 files \u2014 sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala, sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7766d41337d042384d6068123d3b59e2d509ba26b5fbbe622200808d959c654"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060totalSize.isDefined \u0026\u0026 totalSize.get \u003E 0L\u0060 appears character-identically in 2 files \u2014 sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala, sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/PruneHiveTablePartitions.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala"},"region":{"startLine":1435}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb309db17c9f8772acb753a958dcd0ffc6123de5b3605342a41f472f786a3dd3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060totalWeightSum == 0.0 \u0026\u0026 other.totalWeightSum != 0.0\u0060 appears character-identically in 2 files \u2014 mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala, mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala"},"region":{"startLine":630}}}],"partialFingerprints":{"codehealthFindingId/v1":"22cc0f2f09ca9f72ad6be29730d2beb27cc8097a87edd822e517aab6e1c05f45"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060udfDeterministic \u0026\u0026 children.forall(_.deterministic)\u0060 appears character-identically in 3 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExternalUserDefinedFunction.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/PythonUDF.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExternalUserDefinedFunction.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"63ec3eaba14d3873ae309bfbcd7ed78eba3a19f4c03e150aa78e35177a848418"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060up.canBeCoercioned \u0026\u0026 !up.valuesTypeCoercioned\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercionBase.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala"},"region":{"startLine":925}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9e5775b22e7ed13f2c21050040312133c6a65ac5f91f0cbba16fd1ade427e5c"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060v.offset == 0 \u0026\u0026 v.stride == 1 \u0026\u0026 v.length == v.data.length\u0060 appears character-identically in 2 files \u2014 mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"db6689bf1dad213ef2212662458fb038917a0380548e3fe42f191efbb2972aff"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060v1Indices(k1) == v2Indices(k2) \u0026\u0026 v1Values(k1) == v2Values(k2)\u0060 appears character-identically in 2 files \u2014 mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala, mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala"},"region":{"startLine":490}}}],"partialFingerprints":{"codehealthFindingId/v1":"6069f49976cf72d27a9022ab15b19790e7f201cb95aabc23b64b4050806c3103"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060valueContainsNull \u0026\u0026 valueArray.isNullAt(i)\u0060 appears character-identically in 2 files \u2014 connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala, sql/core/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"b819b52dc6279952bbb25ea72687959fb6a1199c6f75ce5c886eee7e99303d28"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060withSinglePartition \u0026\u0026 partitionByExpressions.nonEmpty\u0060 appears character-identically in 2 files \u2014 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/FunctionTableSubqueryArgumentExpression.scala, sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/PythonUDF.scala. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/FunctionTableSubqueryArgumentExpression.scala"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"e95f176ef391b5ccc3da42be3a96ebc7e3a20e0a18fe599eee2116229b455b6a"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060length\u0060 is read from the bytes being parsed at line 88 (\u0060getInt\u0060), then used to size a \u0060ByteBuffer.allocate\u0060 at line 90 \u2014 and nowhere in its scope is \u0060length\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060length\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/dstream/RawInputDStream.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b121c1328ee22e68d61029b6b243592c238dd9e777eae26b46badb5cc52f4be"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060length\u0060 is read from the bytes being parsed at line 107 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 108 \u2014 and nowhere in its scope is \u0060length\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060length\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/api/python/PythonDStream.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"8acd66db68783b675b9ec06092fb471b762cd7778e37bca48c7d5c8f75e7f4ec"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060functionInBytesLength\u0060 is read from the bytes being parsed at line 184 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 185 \u2014 and nowhere in its scope is \u0060functionInBytesLength\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060functionInBytesLength\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"649a417b061754537f6d19746429705869fd7f17d700956ee489854cdc28796e"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060keySize\u0060 is read from the bytes being parsed at line 866 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 873 \u2014 and nowhere in its scope is \u0060keySize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060keySize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":873}}}],"partialFingerprints":{"codehealthFindingId/v1":"faf04b8751481d5a3da4bce4b39002b1ccf39ac224991269b17aa38f3a821b73"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060valueSize\u0060 is read from the bytes being parsed at line 878 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 892 \u2014 and nowhere in its scope is \u0060valueSize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060valueSize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":892}}}],"partialFingerprints":{"codehealthFindingId/v1":"4315b23062de3e100eff4d8eb95865f3966ccb441fa2af4c25d4c8e63c4e5d17"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060keySize\u0060 is read from the bytes being parsed at line 1028 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 1035 \u2014 and nowhere in its scope is \u0060keySize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060keySize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":1035}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbb0ec3f5beda01b01359fb26ee047e6b801c83e817cebe0ddc1c2b89d6649ce"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060valueSize\u0060 is read from the bytes being parsed at line 1041 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 1046 \u2014 and nowhere in its scope is \u0060valueSize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060valueSize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala"},"region":{"startLine":1046}}}],"partialFingerprints":{"codehealthFindingId/v1":"818fc85156187289682b729a2bd38bed220ed4edb0a3bdb0db4f9a4ba55b3fb8"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060keySize\u0060 is read from the bytes being parsed at line 506 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 516 \u2014 and nowhere in its scope is \u0060keySize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060keySize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"eeeade7064e9d7f774a79a3d6f466c2b3a34ff1ab472ba18edcde2d188d5afc7"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060valueSize\u0060 is read from the bytes being parsed at line 518 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 523 \u2014 and nowhere in its scope is \u0060valueSize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060valueSize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala"},"region":{"startLine":523}}}],"partialFingerprints":{"codehealthFindingId/v1":"3363abbccb057e198bbdcd11bd8a241702a4671cb19070a71d51aa61c1929bdf"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060blockSize\u0060 is read from the bytes being parsed at line 546 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 547 \u2014 and nowhere in its scope is \u0060blockSize\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060blockSize\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreChangelog.scala"},"region":{"startLine":547}}}],"partialFingerprints":{"codehealthFindingId/v1":"2256ec2a339d052b9bb85a035b52ff6cc7fff0cad6e5bfb318433df440299333"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060size\u0060 is read from the bytes being parsed at line 157 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 158 \u2014 and nowhere in its scope is \u0060size\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060size\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/RowQueue.scala"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"930483389dc343d32075f3292fd53f61c782cb04548a7e7d976b8223c655346d"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060size\u0060 is read from the bytes being parsed at line 67 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 71 \u2014 and nowhere in its scope is \u0060size\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060size\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkDeserializer.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"98e1086bbc3a9faaf93d37c4b98e79dd3753ce8707dccbf0e775cc66387c1617"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060messageLen\u0060 is read from the bytes being parsed at line 244 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 245 \u2014 and nowhere in its scope is \u0060messageLen\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060messageLen\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/python/streaming/TransformWithStateInPySparkStateServer.scala"},"region":{"startLine":245}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bc1ae57555b4d7aa8ef646cc38ba0f35e36a10270e45f2107e94e5bad50bd4e"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060length\u0060 is read from the bytes being parsed at line 602 (\u0060getInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 603 \u2014 and nowhere in its scope is \u0060length\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060length\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala"},"region":{"startLine":603}}}],"partialFingerprints":{"codehealthFindingId/v1":"6138e725d7b86dfb1b5388cda6969f7e2820f0873e12d95b83baf64f28efb673"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060typeLength\u0060 is read from the bytes being parsed at line 772 (\u0060getInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 773 \u2014 and nowhere in its scope is \u0060typeLength\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060typeLength\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala"},"region":{"startLine":773}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f9e9a050d5d6869d87043d5748187d9b60e18e0209ec847dc9486b3150f6c50"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 863 (\u0060readInt\u0060), then used to size a \u0060new Array[Int]\u0060 at line 864 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":864}}}],"partialFingerprints":{"codehealthFindingId/v1":"297c02ce3d3570bfbcbf3b9e95b3bd65b1d8b2cbe1f6de84ff3502a56f04d316"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 879 (\u0060readInt\u0060), then used to size a \u0060new Array[Long]\u0060 at line 880 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":880}}}],"partialFingerprints":{"codehealthFindingId/v1":"15272abeefa6ff068ce456e1244e25e0f1465afd2cf686c229a08a842ec81473"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 895 (\u0060readInt\u0060), then used to size a \u0060new Array[Float]\u0060 at line 896 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":896}}}],"partialFingerprints":{"codehealthFindingId/v1":"45082033ce13fffbf5c3225a5412a46e39f075abd51c491c46718f3eb7438490"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 911 (\u0060readInt\u0060), then used to size a \u0060new Array[Double]\u0060 at line 912 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":912}}}],"partialFingerprints":{"codehealthFindingId/v1":"455d35b372d5404d2c1f409bcfe4046e9b9595423fa6dcdba377dbb7277197f9"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 944 (\u0060readInt\u0060), then used to size a \u0060new Array[(]\u0060 at line 945 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":945}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a8e2e85fd9fb95af17adc2252b611efe36af4b5ddd6c2a4415253c03791db22"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 1036 (\u0060readInt\u0060), then used to size a \u0060new Array[T]\u0060 at line 1037 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"76e786cc9eb654224c9bf39be416405f379a00d10ce972dcd45de0ddd19b332f"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060chunksNum\u0060 is read from the bytes being parsed at line 106 (\u0060readInt\u0060), then used to size a \u0060new Array[ByteBuffer]\u0060 at line 109 \u2014 and nowhere in its scope is \u0060chunksNum\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060chunksNum\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/io/ChunkedByteBuffer.scala"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39059bb4d9955154b72e0e8eca4cabaf475ef0162c08908180f74dde8430739"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 116 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 117 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/security/SocketAuthHelper.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"820d8686930e0b44ad55e1f22cebf3e7808434ff3d45f88db872101f3cf72fb7"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060len\u0060 is read from the bytes being parsed at line 174 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 175 \u2014 and nowhere in its scope is \u0060len\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060len\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/MapStatus.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"6934469523cf8c2a5810c3a4e9b8d195beeb55b0bed5aa172b6f334a678fb339"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060valueLength\u0060 is read from the bytes being parsed at line 240 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 241 \u2014 and nowhere in its scope is \u0060valueLength\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060valueLength\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskDescription.scala"},"region":{"startLine":241}}}],"partialFingerprints":{"codehealthFindingId/v1":"900a84c1f84ab47b0bd94923800aa3d6b037b35e4d600deca8bc99f3fdf3438a"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060length\u0060 is read from the bytes being parsed at line 255 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 256 \u2014 and nowhere in its scope is \u0060length\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060length\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskDescription.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bf2eb0eb1525fac804643430ac5a54e0ed1958f33ec498cbf7b5daca2c65212"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060numMetrics\u0060 is read from the bytes being parsed at line 82 (\u0060readInt\u0060), then used to size a \u0060new Array[Long]\u0060 at line 86 \u2014 and nowhere in its scope is \u0060numMetrics\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060numMetrics\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/scheduler/TaskResult.scala"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"d81482574947a2f4a610676482f6140a2c08340a1cf3ed014e93ebf269d934b4"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060contentPairsLength\u0060 is read from the bytes being parsed at line 64 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 65 \u2014 and nowhere in its scope is \u0060contentPairsLength\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060contentPairsLength\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/RRunner.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"4df910addd226bcb7b3dd1403b00a6ea576af9aa9d505bd9535fbe74f07e7cd3"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060length\u0060 is read from the bytes being parsed at line 251 (\u0060readInt\u0060), then used to size a \u0060new Array[Byte]\u0060 at line 252 \u2014 and nowhere in its scope is \u0060length\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060length\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala"},"region":{"startLine":252}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6b7d4b7d8140a2a0e356b5f8db1c7fac5fd5261b145dc28fd6cbcef49e7a586"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060n\u0060 is read from the bytes being parsed at line 267 (\u0060readInt\u0060), then used to size a \u0060new byte[]\u0060 at line 268 \u2014 and nowhere in its scope is \u0060n\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060n\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java"},"region":{"startLine":268}}}],"partialFingerprints":{"codehealthFindingId/v1":"71d19c35639a70f9e93171b69d6fd229d17a6cf6507eb68cf24e93f5789c0d7f"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060n\u0060 is read from the bytes being parsed at line 289 (\u0060readInt\u0060), then used to size a \u0060new byte[]\u0060 at line 290 \u2014 and nowhere in its scope is \u0060n\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060n\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/types/BinaryView.java"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"f940414d2e648d1959e648198fb3bc9eba047934eefe3fe7486eb4f164f71a4e"}},{"ruleId":"X15","level":"warning","message":{"text":"Length read from the parsed input is spent without ever being bounded: \u0060numWords\u0060 is read from the bytes being parsed at line 107 (\u0060readInt\u0060), then used to size a \u0060new long[]\u0060 at line 108 \u2014 and nowhere in its scope is \u0060numWords\u0060 bounded from above \u2014 compared to a limit, clamped, or checked against the input that remains (a zero or sign test, or the loop that counts up to it, bounds nothing). Whoever wrote those bytes therefore chooses the allocation directly: a 32-bit length asks for up to 2 GiB before a single byte of the payload is known to exist, which either exhausts the heap with an \u0060OutOfMemoryError\u0060 or, negative, throws \u0060NegativeArraySizeException\u0060 out of a parser whose failure path was written for malformed input, not for hostile input. Bound \u0060numWords\u0060 against the bytes actually remaining and a maximum the format allows before allocating."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/BitArray.java"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"36b3424a3629d32d2c8c85c342a038edf3a345d1dbc1e2ab999206aa4877ec5d"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060addInPlace\u0060 is public and takes \u0060value1: Dict[str, Any]\u0060 from its caller, and it calls itself at line 181 (\u0060self.addInPlace\u0060) with a piece of \u0060value1\u0060 \u2014 and nowhere in \u0060addInPlace\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060addInPlace\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/profiler.py"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfcfdde584be83c6c831bd0c02e80e7111796d50df1063d1286b746669a42265"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060assert_eq\u0060 is public and takes \u0060left: Any\u0060 from its caller, and it calls itself at line 487 (\u0060self.assert_eq\u0060) with a piece of \u0060left\u0060 \u2014 and nowhere in \u0060assert_eq\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060assert_eq\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/pandasutils.py"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca958ae9bda301a11c40aea953cf85c9eecdf2ac7dac58bec81a292cc0c85e3c"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060enum_to_value\u0060 is public and takes \u0060value: Any\u0060 from its caller, and it calls itself at line 226 (\u0060enum_to_value\u0060) with a piece of \u0060value\u0060 \u2014 and nowhere in \u0060enum_to_value\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060enum_to_value\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/utils.py"},"region":{"startLine":226}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd68ff04eaa1d775608344604ab842bf68c757d1af73a541f43c2280d16caa2e"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060lit\u0060 is public and takes \u0060col: Any\u0060 from its caller, and it calls itself at line 290 (\u0060lit\u0060) with a piece of \u0060col\u0060 \u2014 and nowhere in \u0060lit\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060lit\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/functions/builtin.py"},"region":{"startLine":290}}}],"partialFingerprints":{"codehealthFindingId/v1":"871d348bc56a4d8dc9d1c15b94c52be06b85fedf6c3c4a96b4275e6f3d1e1b6e"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060lit\u0060 is public and takes \u0060col: Any\u0060 from its caller, and it calls itself at line 286 (\u0060lit\u0060) with a piece of \u0060col\u0060 (and at line 294) \u2014 and nowhere in \u0060lit\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060lit\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/functions/builtin.py"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbff4dd78326f76e7436cbe8553e053b93eeef43a9dbc3a8d8491af7da4ac060"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060from_dict\u0060 is public and takes \u0060dct: dict\u0060 from its caller, and it calls itself at line 262 (\u0060self.from_dict\u0060) with a piece of \u0060dct\u0060 \u2014 and nowhere in \u0060from_dict\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060from_dict\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/tblib.py"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"6627d0dc43a4962f20707db5feb89fac2798d5455eab30c8c01ad5e81fb7782a"}},{"ruleId":"X18","level":"warning","message":{"text":"Disposable created and abandoned in the function that made it: \u0060File.open\u0060 is called here without a block, so it hands back an open descriptor the caller must close \u2014 and its first and only use reads \u0060.read\u0060 through it and drops it. Nothing closes it: it stays open until the garbage collector happens to finalize it, which is one leaked descriptor per call (a child process too, for \u0060IO.popen\u0060), \u0060Errno::EMFILE\u0060 under load, and for a written file data that is not flushed when the program next reads it. Use the block form, which closes on every path including a raise (\u0060File.open(\u2026) { |io| \u2026 }\u0060), or the one-call reader/writer (\u0060File.read\u0060, \u0060File.write\u0060, \u0060File.foreach\u0060)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/_plugins/include_example.rb"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"374ab43b46caf6fe2e19fe0f86afa825a078100dd0913915e05f7b1c55374bd7"}},{"ruleId":"X18","level":"warning","message":{"text":"Disposable created and abandoned in the function that made it: \u0060new ServerSocket(\u2026)\u0060 opens something that has to be given back \u2014 a file descriptor, a socket, a directory handle \u2014 and it is held in \u0060serverSocket\u0060, and every later use of \u0060serverSocket\u0060 in its block reads a member through it \u2014 it is never returned, passed, stored, captured by a lambda, reassigned or released, so this expression both creates the value and is the last place that can release it, and does not. Every call leaks one more open handle until the collector happens to reach it: \u0060Too many open files\u0060 under load, and on Windows a file that cannot be replaced or deleted while it is held. Open it with \u0060scala.util.Using.resource(new ServerSocket(\u2026)) { r =\u003E \u2026 }\u0060, which releases it on every path including a throw, or hold it and call \u0060.close()\u0060 in a \u0060finally\u0060."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/util/RawTextSender.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"76dbe4112703ba840e6b34afcb1f39e7ff2a061feecf591cbef37167dc5a18b4"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060container.innerHTML\u0060 is text this program did not author, and it is written into the text of an element through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. Encode it for HTML at this site, render it through the framework\u0027s escaping output, or sanitise it if it must stay markup."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec9b5be03ecd75dd649e8b55bfcb2899ebdeae4cc9a802f9ff994e39953b78e2"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060url\u0060 is text this program did not author, and it is written into the start of a URL attribute, where it chooses the scheme through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. HTML encoding does not help here \u2014 a \u0060javascript:\u0060 URL contains nothing it changes; allow only http(s) or a relative path."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"44293d1847c7689da4d8e0744feec9efb00368098dc9d9208d4d36ac597ae4d0"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060url\u0060 is text this program did not author, and it is written into the start of a URL attribute, where it chooses the scheme through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. HTML encoding does not help here \u2014 a \u0060javascript:\u0060 URL contains nothing it changes; allow only http(s) or a relative path."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/executorspage.js"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce29292ccddc35e8ae673df031700a77076695f81d069bb7053886c3892c5ff7"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060(summary.totalQueries||0)\u0060 is text this program did not author, and it is written into the text of an element through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. Encode it for HTML at this site, render it through the framework\u0027s escaping output, or sanitise it if it must stay markup."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a84821004c93d214c0da8a348b89f2c50e3ae36ef7d72d3936d0c0f146d5aa8"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060(summary.runningQueries||0)\u0060 is text this program did not author, and it is written into the text of an element through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. Encode it for HTML at this site, render it through the framework\u0027s escaping output, or sanitise it if it must stay markup."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"777e0eec9a65d6193c346d81e777fb26e582273de8e4817b1c5325cc9e8fee59"}},{"ruleId":"X24","level":"warning","message":{"text":"Untrusted text written into markup unescaped: \u0060(summary.failedQueries||0)\u0060 is text this program did not author, and it is written into the text of an element through \u0060innerHTML\u0060 with nothing encoding it for that place. Whoever controls the value controls the markup: it can close the element or attribute it sits in and open a script of its own. Encode it for HTML at this site, render it through the framework\u0027s escaping output, or sanitise it if it must stay markup."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/allexecutionspage.js"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"defb29e9d952e32eb64ba6bc06bf59973fef2fcd074330eb6ac06d7ba7e2ec12"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala"},"region":{"startLine":406}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b74139f626a700bdb3670678139a860e8433adc573f08a11c16b633418ca3c2"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/graph/AutoCdcAuxiliaryTable.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a04e8b665e3528c37b9289e19d32aa32f25e989d9beb3568954d630ebc1a0f7"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/BaseScriptTransformationExec.scala"},"region":{"startLine":292}}}],"partialFingerprints":{"codehealthFindingId/v1":"b048cbe2a9ddb001cc73ab1691951ea7d95b3d57c3a05e67a7e3bdcb34bf196e"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlanInfo.scala"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c2ac3e2045b9710878224cfdab04ce033684f175b122d06474ef185d277e43b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(e)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/memory.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a27ac36acdc9ecefc5b9f19574b7c80833bccb96e13cd260044724abd876af1"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"40c936c3e8b0620909debcc3f8f33730b33750a4aadc8347f5a13aa260a70132"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InMemoryFileIndex.scala"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb637d5feb3d6818a87fe07df79cfe098159a488582cef6913f291ada5e266a3"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2540c690f0b4fbb01a2de721efd38e657bc99ca09864b92bad1f8afcbf6422b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. On a teardown path letting it propagate is not an option (throwing out of \u0060close()\u0060 masks the failure already in flight and abandons the rest of the cleanup), so make the swallow deliberate instead: narrow the catch to the exception this release can actually raise, and record it through whatever this codebase already uses to report problems \u2014 or, if it truly cannot matter, say why in a comment on the catch."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f4b1d9285376fe2ec93c7263b2e61467d524acef94bb1498f8adb7eb5d80b64"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"14df1a6a411325a6393fdaad868c983746778ec575dd54ac0842ea813291adc8"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"10d3f7c502de4f850d8524b1f03de60bf41b5dd7f74978a80dce0004d8a76119"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":417}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5514023a4e04a992297838d2a21dd52a4315956349085c7df35f99baa2c39de"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala"},"region":{"startLine":433}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f2ebc72ac9fabbdc2c84b492d5ddfce7a314f2345d620735c3c0cf26324d8a9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala"},"region":{"startLine":454}}}],"partialFingerprints":{"codehealthFindingId/v1":"67bd82c20ab9302a05672a1b1cca0133f0eb0cf0a6649c9783cc2c8228e948af"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateNamespaceExec.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"971a37c5941f72660692c13a4b0332693cff5a918a79fff0d44a32ef96a1f5b4"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_) | _: LinkageError\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PushDownUtils.scala"},"region":{"startLine":363}}}],"partialFingerprints":{"codehealthFindingId/v1":"afa6f15113b4a12540a448254058d48b5b5b1889ef4998f5c0d3e8878502425e"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_) | _: LinkageError\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowCreateTableExec.scala"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a41b0be1afd1a31493fd27a5cc595c52fc722566a9ba514cafc2621f3be9234"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"e31aa5cd1ca75fea790fabc99c7d9c7b609fa1230f488397afaf6de17a72004e"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":505}}}],"partialFingerprints":{"codehealthFindingId/v1":"6711b1f6bbdd866b2290f28533335463a813a5bdd7002a87a91712aeeaaa21d3"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b54adf4faff192b4e8c61c625b0953b80e1984dc4fe160ce51439234dd84417"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/classic/Catalog.scala"},"region":{"startLine":802}}}],"partialFingerprints":{"codehealthFindingId/v1":"7338e903e0210e39f29275588abf394fd1e86ff0e26ff05735dc360d9029e231"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/scala/org/apache/spark/sql/catalyst/optimizer/EvaluateParseSql.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"642c11485ff8f063278162398a09167dd14bd8e6e2dbee3cdcd33ffb7740d60e"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (e)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, or keep only the failure you expect and rethrow the rest (\u0060catch (e) { if (!(e instanceof SyntaxError)) throw e; \u2026 }\u0060, or test \u0060e.name\u0060), because a JavaScript catch takes every exception, programming errors included."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":1059}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f3caa56572200b20f8dacc79554547f444cf1241d508ded97f43e54aeccd1fd"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Throwable)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":686}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3607aaecf7fbdbdace0917b244da4183336ba414a6e65ba6cb06e8e2d84317b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Throwable)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":1314}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a01314d4b02f5c55ed6472e4744490deeb2bd65e7970d4619b755cec7d7e318"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Throwable)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":1552}}}],"partialFingerprints":{"codehealthFindingId/v1":"f113d3c458c6c7d70cb44640bea2f0c1da5a99f1e784f1e8b8e6d662e9943d64"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/utils/PlanCompressionUtils.scala"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0846a325b7c6f164125d540ec84e23efd985d6dfd65330d3f2cdf0b0f6d379a"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/server/src/main/scala/org/apache/spark/sql/connect/ml/MLHandler.scala"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b372baa0d9dda13c8e8729d8ee5728931f4272d32c8fe2ae5515e93e2130aa7"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/connect/common/src/main/scala/org/apache/spark/sql/connect/client/SparkConnectClient.scala"},"region":{"startLine":638}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cfbcd3aba2d096422045c426850374f0f3d662348c967cf7335be0268937543"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala"},"region":{"startLine":749}}}],"partialFingerprints":{"codehealthFindingId/v1":"47b99f2ed60a3c0e471cfb34dd4812bd3e3b58f3397551d30b82791e81945696"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala"},"region":{"startLine":834}}}],"partialFingerprints":{"codehealthFindingId/v1":"f21abb446333d88a41451f08d3028d286d9eb0052fe9e5e5eb916ec9e720ac57"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala"},"region":{"startLine":929}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb47361a9f40a7303cac1fd5406904408aac2bcd97604fd8e4f2bca241622698"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ProtobufDescriptorFileReader.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"6297c28369033dd32a9fb5eaee27e87e24245484df6487c648e7fb3d71ebcf12"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: RuntimeException\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala"},"region":{"startLine":1377}}}],"partialFingerprints":{"codehealthFindingId/v1":"eed059810e261b0420f9644002f9915000eef4591aba34ab32915bda800b428b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cc21e8b80ba7ab9d19641523461175128f8729c0f903da383378d0217087d24"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"6096e3ca7a4e7f82e52de826b2a469d6047eb105b29122d905ea3dffc290820b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"41d0eb310935a96523fc6a9b64a1e097032d9b2aa040b46ffdbe0bdc4202240b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala"},"region":{"startLine":1633}}}],"partialFingerprints":{"codehealthFindingId/v1":"55ab0d03fc94688715064f2394ca636a984781d22db9691d8013449dd0ccdf61"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"93b16f10416f931622462f790154a78b7f85a06120411f9ed909c030be0cf4f4"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_) | _: LinkageError\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TransformExpression.scala"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"f2393d96fb574dda4d3c6e27e9be46174cae8be50f0dd7816d0dab493a144485"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/TryEval.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8b497e344f41fb4f9567e019a89f3e8a62b6975de36778a26c9d16fdfcd50fa"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b5e18dcef12fffe1728a6d5231ad72667135cca11da395136e5002163c431e6"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"bada65d9a562a7b7b77f6cbf45ee7c40feeaba7a3daaa916725ae36446f02811"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"aac4e718e4e210f4cdee9953c0f19b63d109a3a26b27a72748af01632230daa1"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"de0c5839abc62121064ab7320f731e42ab450da233118dadcce6a766c798e783"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":996}}}],"partialFingerprints":{"codehealthFindingId/v1":"714706f5c8203f4b63eb3c4fe2046c3a4123a677ddcde54a6de9c54bb19d40b2"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1025}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d942ee26a16153fc69e1de59197dd8f4fd225437077e6846e539db4cea4cafe"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1653}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddac05525a4e39bbcd9edb55b052e3883e7105760f87b7f28bd2a873f7ca3bb9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1731}}}],"partialFingerprints":{"codehealthFindingId/v1":"5cb9554d736584b964c6cb04aee142e894796637b80a0434f69cd0ea0df8a664"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":1733}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee8cf4b675d7aee33eed4e4abc57146fca569e8e47e0c807c1f30ea1dea526f2"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_) | _: LinkageError\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala"},"region":{"startLine":2245}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d51742de330f104e4eade5de511f0d9b44642edf7ccbca3f81fddb956b971a6"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ApplyDefaultCollation.scala"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"f215f1c38bc3ff7764212013440ace1e66055d944b22a7fca8f6c934868cdb5a"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ApplyDefaultCollation.scala"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"4814fbee3566807d55aaf9bb1d2f5c5630d565574c017629c881881984708203"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CollationTypeCoercion.scala"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bd056b07cb64915e0548f28cdb866eba8b1f104fca5db9912786d83fabf7444"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionResolution.scala"},"region":{"startLine":868}}}],"partialFingerprints":{"codehealthFindingId/v1":"37618147ac2ef79295466bc448627c81353d930ce90665c33eb9698ea5f54840"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(e)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/streaming/progress.scala"},"region":{"startLine":264}}}],"partialFingerprints":{"codehealthFindingId/v1":"e057af1fc1bb6c227e8cf2dc2d70cd99c998cc098c84af551ace3cefeb3f7c53"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":638}}}],"partialFingerprints":{"codehealthFindingId/v1":"606a9a91a4b9901edfaa305b8ffdeb51deaa77fe1cc6d24fc282d8b42a5e0c1d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":928}}}],"partialFingerprints":{"codehealthFindingId/v1":"facd5f0cd65645a3d9ae4a64219ca5707d6497e7b6cf11f0c9e599e8119b80ea"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":993}}}],"partialFingerprints":{"codehealthFindingId/v1":"aee266f154da706d901d0d137b4c66b86a7434119710f47d2648b6768fed1fab"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1019}}}],"partialFingerprints":{"codehealthFindingId/v1":"3293dd45ad25122ca6238f893fe7c63af8095465888d4b40ba0c6b86a083c0ba"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1064}}}],"partialFingerprints":{"codehealthFindingId/v1":"42d59dd79aa5cc94a6d15a3d839804e9ac9fa26bb63aea47ddab268c70bc6105"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala"},"region":{"startLine":1161}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a24a0b40ec465a248ac9ed7e8cb9528513ef41e5958b3e569b420fc742fa69f"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"cba8cd2219faacb7e30718184b028ba219709650f935b3fb809700e886e39367"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimeFormatter.scala"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"a71b13f6956cda7bb0592298d9b9b1d8fece1548307f32f33e7d3b26bcae67f0"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"7247b5d8a06e9b53a6462d5b91e4b7a6879c1170145428aa330f40014356564f"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"b02ed10d6f544ec338df147d82cd6123bb709a72f0d68d3465062025f5b51719"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":311}}}],"partialFingerprints":{"codehealthFindingId/v1":"df83f63df40cc6564586f4092f148d173b69e1f94d4e70e73ae4e6686d0fc0c9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":349}}}],"partialFingerprints":{"codehealthFindingId/v1":"c815b109a3c346bee328e93e662b4e66019c17f33a5ee5613ef7f7025a5ccf1d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":377}}}],"partialFingerprints":{"codehealthFindingId/v1":"8249fc1e2ad4d208c61ea00f93810177a6ba5594b3b9e793d201f4d60b584683"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"8399f852a8fe65d5c6bdaef62959af1af732d4b2f4cde4c6df3173b30dac5b55"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala"},"region":{"startLine":702}}}],"partialFingerprints":{"codehealthFindingId/v1":"43c135196b95ee3ad516147bc6e79f8e92ee6a3dccbf17c8408c9796c99a358d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/UDTUtils.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"48f1c7c1fe1f8dcda1ea0840994a6a2377f15014ad3bc4338d38f5afcc56c7f8"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPVCResizePlugin.scala"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"f785e92993c93318fa376acad1a6e36d897877a37fd7788ce148f79d62797b46"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/daemon.py"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"071e0664ba0673770ef69fb5c96106cd80bebeebc04304a4c1260fed6c9799c8"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/memory_profiler_ext.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"331f721062741d0b5073e5113479e948b0f0a512347e2bc762e5458ad566b130"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/memory_profiler_ext.py"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"67ff0f5dc2bc69310d627472b8a9d462402096ed9737e4deeef5dca7b2ab7cc8"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except BaseException\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/worker.py"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"a49df35cb66a59bc53498c5d4d86f4b40be6ed2450d1169609b7626743c090cd"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/sqlutils.py"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4903cf45cc2e02b64b9207cac39760375c61495d435f51cdd1afb481ad615b9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/streamingutils.py"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ddbc87d202d7cf0d3478e80c5c63ea67c609fa5d856b3afadc13bdabc86d01d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/streamingutils.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"806ecf6ec25aad62f2b5fd852e1b40223545908f53b25e68ddc880740558bea7"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/testing/utils.py"},"region":{"startLine":453}}}],"partialFingerprints":{"codehealthFindingId/v1":"6073b79d53d73d43d0af20d102298dd3d845314bb8dc7030672150768948c897"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1620}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3219a072d625f6bcceea79057b48bf9036d204f8c0acfd758bec473e5b9c948"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1627}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f6b8edc26581f18797c5aa0ffcc88d87185975358354d238fe6464d901701fb"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/session.py"},"region":{"startLine":1634}}}],"partialFingerprints":{"codehealthFindingId/v1":"058c7c2b2be167260679a623f6573e9b4480f8916f1dab61f18c873f09b3dad6"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/worker/utils.py"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e2072124ea31ff29c984093410d44332b9ebd711a385fa1bf9a13ead096477e"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/plot/core.py"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5b1b2fc53ed0ceae61463027116e2cf8c57e955ffb407421753d6cea73069e4"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/column.py"},"region":{"startLine":625}}}],"partialFingerprints":{"codehealthFindingId/v1":"432cd351c71b8a5c1ecb804641655831f4d4b3971bb4af380f425b05cbf57d3a"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. On a teardown path letting it propagate is not an option (throwing out of \u0060__del__()\u0060 masks the failure already in flight and abandons the rest of the cleanup), so make the swallow deliberate instead: narrow the catch to the exception this release can actually raise, and record it through whatever this codebase already uses to report problems \u2014 or, if it truly cannot matter, say why in a comment on the catch."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/session.py"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"05d4757e70e7ae895df07057bbc1cd7109d2f32fdba6f88244df399058ed2533"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/artifact.py"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c428f0954f3cc554cce4991afdb280ac8b7a596fb1d2c11b40659b712d54a36"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1350}}}],"partialFingerprints":{"codehealthFindingId/v1":"99d632674e5132ea08c83b27f734468834238d117c781498cb452ae612550783"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2595}}}],"partialFingerprints":{"codehealthFindingId/v1":"c492803ec4eb0cd19e55543b7de4f89889afdc27f0bb04b0ba53668d7f05cd68"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2610}}}],"partialFingerprints":{"codehealthFindingId/v1":"31fe3b20cb97443845a5ad765b51866b6ca62d6ac040138293111abf999dde9c"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2614}}}],"partialFingerprints":{"codehealthFindingId/v1":"4017081b9f2842ca1e2a1ca6490671722978ec7a78ce566f859459fb239b9922"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2635}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e36da9c6b29e2e2b6179a7f017c4f6b4e9ec8f6eff638b1033940c50dea5143"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/classic/column.py"},"region":{"startLine":673}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c728e94a736f020e663c56ed3c94f13cb8c51a7e0aef742fe7509c83806253d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7591}}}],"partialFingerprints":{"codehealthFindingId/v1":"64880ee9a1d63a46a6ecd722bc0069117c0a278be54ab3fb733d9825ecaff898"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7598}}}],"partialFingerprints":{"codehealthFindingId/v1":"8644e555a44a0600c9b3c53c335017202233a59e964341a1737ffa329faa32a3"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7606}}}],"partialFingerprints":{"codehealthFindingId/v1":"03bb31808dfe4957ad0ee5cc44ab84409ad24cc3a28b36cd4bf53b22879b46c1"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/frame.py"},"region":{"startLine":7613}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e0ae08a45f30fc6edfdcae2194964d3e18458894fcc76e8e2560645d28c71f6"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/pandas/plot/core.py"},"region":{"startLine":112}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae4628b6b7190b21041e343e0d541ff882c2aa665ccbc9f90b0bad8b63f80d0d"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/util.py"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a85cd415daba44aa88c38441dd41755f8a34b86c42786c4f6450580218e7058"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. On a teardown path letting it propagate is not an option (throwing out of \u0060__del__()\u0060 masks the failure already in flight and abandons the rest of the cleanup), so make the swallow deliberate instead: narrow the catch to the exception this release can actually raise, and record it through whatever this codebase already uses to report problems \u2014 or, if it truly cannot matter, say why in a comment on the catch."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/wrapper.py"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9efdf757d9cbfafe322a035410dae3505222ca9aed88700b3ae0ca727590a49"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":795}}}],"partialFingerprints":{"codehealthFindingId/v1":"c79b3ae2e01603633275d27567174648796187f75debe39a4494be24c8a94acf"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/errors/exceptions/captured.py"},"region":{"startLine":125}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b338d1dcd23caf07300a367167a1d90a724d62af723a301d208471abb373668"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/cloudpickle/cloudpickle.py"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"6bd5c37f804f1d3de93fb77ff8268902327c5fec4dc2e3e8b18c6ce103ef86d9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/conf_vscode/sitecustomize.py"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"10a6f00385e47de580826436d1c032ed62f2ee555e175558d85cb9135272c06c"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2b7abdf15fe7f351e17b49ac60aa0a2e51c68bd9e65e1b497f542161b31d029"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/ARPACK.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"e41a035d3cf54af50a654e81c7aaa2de45d2f7e0ba25ec6c1eadd2276392075a"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2e0d67ef4ad57a8ffcab106593583c8d4d3b6841e5c62024a5bf6be6026e797"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"mllib/src/main/scala/org/apache/spark/mllib/linalg/LAPACK.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"d53e96df3ee44f95c13adc9487d52ef7b152c4f476737fe5f45d6d702c7b532f"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/util/SparkUncaughtExceptionHandler.scala"},"region":{"startLine":110}}}],"partialFingerprints":{"codehealthFindingId/v1":"d13128740f2ca2876810093a15697590303f319306517a703284bdd8830ac15c"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/env/EnvironmentPage.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"a91f15a2228232ffd39276e11d3d3d83915a7162cb90d9efc63f4224d663eb01"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"31bc9915b8783d90cfc6c24a0c60bae0826bf1dbef0bb3adf979395e27feb76f"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala"},"region":{"startLine":672}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fa259491e7c42e61625045414c456c0a3c148198d5d6b0bc03a086244504844"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/serializer/SerializationDebugger.scala"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"92781fb80a95880e5ada6a6ac2d1d15c853621b38d646ec428cde44ba06d8ba8"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/metrics/source/JVMCPUSource.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb3fa00573fb3998a43a21c6eed90bd92b5ad09266247bb8e47ccaf64e3e9413"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case e: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/memory/UnifiedMemoryManager.scala"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b28f8e223547d759d89b8da8ea4c9fa61219c68ab71c0da7c6ce75e31d4e328"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala"},"region":{"startLine":907}}}],"partialFingerprints":{"codehealthFindingId/v1":"94d3ec897e57078c1b69ecad135ecefcb1ca1937be2a69074d8323580723dcf6"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case e: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/RUtils.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ce8930d0fc68671c043d3d62673ac2993c9614c6608a86e6df82e9e1f1de60b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala"},"region":{"startLine":1719}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd04ad9cbd6ec667d1e0431f3454c23bde381878fa830744318dead593df4520"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Throwable\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a6beb5d5959e598003155e8088c850edba6fdbac9415b7e4f035aba23a01949"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/resources/org/apache/spark/ui/static/environmentpage.js"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7a616774ecbee5f37d4a0694ff1ef875321cc8085b9bf3fff405b7d13a2ebe2"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case NonFatal(_)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"connector/kafka-0-10-token-provider/src/main/scala/org/apache/spark/kafka010/KafkaTokenUtil.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"6dfd4652f4468191fe96ca2e725277c3a05e4bc5bb1fa2c6cf2a0a0ef6700a40"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkErrorUtils.scala"},"region":{"startLine":151}}}],"partialFingerprints":{"codehealthFindingId/v1":"9756c1019140e82aa4ec8c95b26b4acf87a4c2b2f5725e4ed7a6438301c1bdd5"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkErrorUtils.scala"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"af2da6ff9364265d375604104f4dacf2d4f83ae958e05cf5dfa940ed80da1d79"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060case _: Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/utils/src/main/scala/org/apache/spark/util/SparkTestUtils.scala"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffb00e0bca17b81357fa034fe076fe0621a596db30f05312a7558f3191186d28"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Throwable)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/unsafe/src/main/java/org/apache/spark/unsafe/Platform.java"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5bd290ef8fdcd3165e6306fa83c84a713014283c23c12a686ac8307f7d043bc"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Throwable)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/sketch/src/main/java/org/apache/spark/util/sketch/Platform.java"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"85f550169c1aa073cc60788fef815b06f806fff1a39b943ec83a3b259d09944c"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Exception)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/NettyMemoryMetrics.java"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"060a39288ad86e3056a0f7f127e7aada02830f1ed3990282bf672224151114e7"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060catch (Exception)\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/NettyMemoryMetrics.java"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7137c447f6adaeaffa212ba3e9b0fda0f32d57a4407ee0d155784a8b315e47a"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 314 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b43997f995925b8944bcf7b93d5dba2a89c775623fac721fc2279a1268e950a"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 324 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":324}}}],"partialFingerprints":{"codehealthFindingId/v1":"38e430b565d4e0777c1e8af721d2a183395ee575dde73db92363591f59fdd0ee"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1248 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1248}}}],"partialFingerprints":{"codehealthFindingId/v1":"5868e829891186296363914aad127bb881eef0a5b797087ced940fe28eae6e06"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1267 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1267}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd2b2116a76b2c086695c2ab4cc3c37f4f302455bbca1e9bede121989c26ce83"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1286 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1286}}}],"partialFingerprints":{"codehealthFindingId/v1":"be783665315094d47287404bbfe996644c1e5ba38c8cfe32dab48808f910bee2"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1413 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1413}}}],"partialFingerprints":{"codehealthFindingId/v1":"17f5be08bc178a0b1b063f5ab5daafdf44d3b3a9622cd58022e9c886f6648b23"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1427 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1427}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e1256e6e56fb6c76d38efca25b80737f9dcc68dab282016427dcb4144611d92"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1445 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1445}}}],"partialFingerprints":{"codehealthFindingId/v1":"317cb5bebb5d50a89181619104f83dd13e80c28600666002589f8caade17dddd"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1469 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1469}}}],"partialFingerprints":{"codehealthFindingId/v1":"5357e465ca9aa8764152245c6dae4c9c1a1f9f7e67eaa494d1d76fc2cfc55084"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1759 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1759}}}],"partialFingerprints":{"codehealthFindingId/v1":"390699befebf2b10dd4005d0eec6e4e86b0260a1730fb54a6b90bf47bbd9ab72"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1777 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1777}}}],"partialFingerprints":{"codehealthFindingId/v1":"99d904386a4c32e45778fc36a3c3db7929553d9a9a41d77d79d01f8719e0abd0"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060warning\u0060 at line 1804 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.warning(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.warning(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1804}}}],"partialFingerprints":{"codehealthFindingId/v1":"8243fa515762eceabef465f828243e2d9e39efbd19be9e73314ddc65341fe8bc"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1858 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1858}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc662b13115e799614d429e471ceb0dfb0bb3be37ffda5a0d4c3a008d45aff8d"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1902 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1902}}}],"partialFingerprints":{"codehealthFindingId/v1":"18e63f6da48f55557c1eb29afc81e2eceb488ece366afff78fe8d14044a6cf39"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 1963 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":1963}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ecc49d17da514a4d7a423a8217303d68248ddf003a393ab78d5df7f2980c665"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 2446 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2446}}}],"partialFingerprints":{"codehealthFindingId/v1":"1196f2c43d82122f49e882b19238c0bb7ec61005f98c15b89ab0d46295fde1f6"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 2716 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2716}}}],"partialFingerprints":{"codehealthFindingId/v1":"6ab8dbf48674253248e6f71493a38666a824d1ca6d6760906be8d2b4b680d25e"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 2746 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.debug(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.debug(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/sql/connect/client/core.py"},"region":{"startLine":2746}}}],"partialFingerprints":{"codehealthFindingId/v1":"478368f038d23624463309eeba915785cd53de6676aaf7887187781fb68f8163"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060warning\u0060 at line 232 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.warning(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.warning(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"98ab4601fcb29ba6244d43b3e43e76f56d76f81668d0c7bfddc1aacd0fec4c08"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 637 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.info(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.info(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"81c339077ad6190365560e86033bedad28302694fc043425fc8901676bd66ead"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 646 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.info(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.info(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":646}}}],"partialFingerprints":{"codehealthFindingId/v1":"157555d25fb3a48cb516435190bfb099980137ee9275ca01423fc1177bc8e818"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 856 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.info(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.info(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":856}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4534e963db759d92b65e59f097e5d7df0272bbec5dd6ec8b292f0b6c94f1508"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 872 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.info(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.info(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/ml/torch/distributor.py"},"region":{"startLine":872}}}],"partialFingerprints":{"codehealthFindingId/v1":"d80369fe206549be0b420bc5af5e8bced8ff73e60f2b43b97df95a7b429c3f74"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 317 is handed a message assembled at the call \u2014 a string concatenated with a value, or \u0060String.format\u0060 \u2014 through SLF4J or log4j 2, so the logger receives one finished string: the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the level is filtered out. Pass a constant pattern and the values beside it instead: \u0060log.debug(\u0022Order {} moved to {}\u0022, orderId, status)\u0060, which keeps the pattern and its arguments apart on the event for a structured encoder (logstash-logback-encoder, log4j 2\u0027s JsonTemplateLayout, OpenTelemetry), or \u0060log.atInfo().addKeyValue(\u0022order_id\u0022, orderId).log(\u0022order moved\u0022)\u0060 with SLF4J 2\u0027s fluent API. An exception goes last, as the throwable argument, not into the text."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/operation/LogDivertAppender.java"},"region":{"startLine":317}}}],"partialFingerprints":{"codehealthFindingId/v1":"5069fcc649fe57c03c8bdb5b98db3fa75a7b5d2bf4a0dcf8116d9de56787587e"}},{"ruleId":"X5","level":"note","message":{"text":"Scala\u0027s null is not held to the type system everywhere: No build over this repository\u0027s 3397 Scala product file(s) passes \u0060-Yexplicit-nulls\u0060, enables WartRemover\u0027s \u0060Null\u0060 wart or runs Scalafix\u0027s \u0060DisableSyntax.noNulls\u0060, so every reference type admits null and nothing reports a \u0060null\u0060 written into the code or returned from a Java API \u2014 the first one to reach a method call is a \u0060NullPointerException\u0060. \u0060Option\u0060 by convention is a habit no tool here holds the code to."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"23e7c3c6da50151f07723c64ca4f881fd5903e713d143161a7c0594ad7ba29cc"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060getROptions\u0060 swallows every exception into \u0060\u0022--vanilla\u0022\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it propagate. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch case or in the Scaladoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/api/r/BaseRRunner.scala"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5040220514d6cb6ce410e31c68791360ee7b40feaccc5b5d6d3101d39d1094f"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default on parse failure: \u0060getSparkUser\u0060 answers \u0060\u0022\u003Cunknown\u003E\u0022\u0060 when \u0060NoSuchElementException\u0060 is thrown, with no log or throw \u2014 a malformed value silently becomes that default. Log the input or fail validation. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch case or in the Scaladoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"core/src/main/scala/org/apache/spark/ui/SparkUI.scala"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e77f5d17a390f0570dacff841053461ca199def483088a7d734a443d650761a"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060confHasReplUri\u0060 (in \u0060isReplContext\u0060) swallows every exception into \u0060false\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it propagate. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch case or in the Scaladoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e09f74c80881f2d6d43a391b5d7d08a7a4f5b3170f8d2c45aba2d757efb7c66"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060eclInChain\u0060 (in \u0060isReplContext\u0060) swallows every exception into \u0060false\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it propagate. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch case or in the Scaladoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeCompiler.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"8443c31bb95b35f89c4b06d94e1a592d14262b28878d2cdbc8353b76542aff79"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060registerArenaMetric\u0060 swallows every exception into \u0060return -1\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it propagate. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch or in the Javadoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"common/network-common/src/main/java/org/apache/spark/network/util/NettyMemoryMetrics.java"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd11f2eee354592bacfb62b46a0c2cb72e263d46a389aa2e15c26443e1ae5ce5"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060engineStreamGetLastError\u0060 swallows every exception into \u0060return 0\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it propagate. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment in the catch or in the Javadoc, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/java/org/apache/spark/sql/execution/datasources/v2/ffi/NativeLibrary.java"},"region":{"startLine":1552}}}],"partialFingerprints":{"codehealthFindingId/v1":"54c5584293b062b64ada5a9ba02618594030a6d75bad8bb11de85b52f52780bc"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default on parse failure: \u0060spark_connect_mode\u0060 returns \u0060\u00270\u0027\u0060 when \u0060ImportError\u0060 is raised, with no log or raise \u2014 a malformed value silently becomes that default. Log the input or fail validation. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment on the handler or in the docstring, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"python/pyspark/util.py"},"region":{"startLine":996}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ef47ad271e4d6502622ea0091632776e184c6f3accb0ec15da9c99aae423f73"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default in catch: \u0060getNodeDetails\u0060 swallows every exception into \u0060return {}\u0060 \u2014 a data error becomes a silent behavior change with no trail. Log the failure or let it raise. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment on the handler or in the docstring, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.js"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8a683f0f3c8239e3cecd9bad7f56ce909d890485f1409320daf58932eb0c2cf"}}],"taxonomies":[{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d","organization":"MITRE","informationUri":"https://cwe.mitre.org/","isComprehensive":false,"shortDescription":{"text":"The MITRE Common Weakness Enumeration (CWE)."},"taxa":[{"id":"CWE-1004","guid":"872195c9-bb07-cf51-8a32-865f4bb753ca","name":"Sensitive Cookie Without \u0027HttpOnly\u0027 Flag","shortDescription":{"text":"Sensitive Cookie Without \u0027HttpOnly\u0027 Flag"},"helpUri":"https://cwe.mitre.org/data/definitions/1004.html"},{"id":"CWE-1032","guid":"5f21e517-68aa-a650-9a25-5771ef024637","name":"OWASP Top Ten \u2014 Security Misconfiguration category","shortDescription":{"text":"OWASP Top Ten \u2014 Security Misconfiguration category"},"helpUri":"https://cwe.mitre.org/data/definitions/1032.html"},{"id":"CWE-1059","guid":"a2381a08-60f6-9554-a8b8-f3018cfaaca5","name":"Insufficient Technical Documentation","shortDescription":{"text":"Insufficient Technical Documentation"},"helpUri":"https://cwe.mitre.org/data/definitions/1059.html"},{"id":"CWE-125","guid":"98717707-96bf-ca5b-9568-8d1d257574c1","name":"CWE-125","shortDescription":{"text":"CWE-125"},"helpUri":"https://cwe.mitre.org/data/definitions/125.html"},{"id":"CWE-1357","guid":"e4d2e772-757e-0a5c-bd7d-77052949d866","name":"Reliance on Insufficiently Trustworthy Component","shortDescription":{"text":"Reliance on Insufficiently Trustworthy Component"},"helpUri":"https://cwe.mitre.org/data/definitions/1357.html"},{"id":"CWE-1395","guid":"800e09e7-c11a-8654-9fa6-86f398995fed","name":"Dependency on Vulnerable Third-Party Component","shortDescription":{"text":"Dependency on Vulnerable Third-Party Component"},"helpUri":"https://cwe.mitre.org/data/definitions/1395.html"},{"id":"CWE-16","guid":"659db3ea-affc-8453-8add-c1218fbfcb92","name":"Configuration","shortDescription":{"text":"Configuration"},"helpUri":"https://cwe.mitre.org/data/definitions/16.html"},{"id":"CWE-200","guid":"b0ce3b1d-7a29-fe50-8aab-9aba899d2988","name":"Exposure of Sensitive Information to an Unauthorized Actor","shortDescription":{"text":"Exposure of Sensitive Information to an Unauthorized Actor"},"helpUri":"https://cwe.mitre.org/data/definitions/200.html"},{"id":"CWE-259","guid":"ae9ad959-fbb6-9d5e-892d-3dca66da0b69","name":"Use of Hard-coded Password","shortDescription":{"text":"Use of Hard-coded Password"},"helpUri":"https://cwe.mitre.org/data/definitions/259.html"},{"id":"CWE-295","guid":"a706c4e2-1232-8859-ae2e-17aa2d41f8e2","name":"Improper Certificate Validation","shortDescription":{"text":"Improper Certificate Validation"},"helpUri":"https://cwe.mitre.org/data/definitions/295.html"},{"id":"CWE-319","guid":"7af97476-9f0d-4458-9163-3d2043918a1a","name":"Cleartext Transmission of Sensitive Information","shortDescription":{"text":"Cleartext Transmission of Sensitive Information"},"helpUri":"https://cwe.mitre.org/data/definitions/319.html"},{"id":"CWE-353","guid":"09d7e902-d4ee-f05d-ae6c-0a1554d0c18f","name":"Missing Support for Integrity Check","shortDescription":{"text":"Missing Support for Integrity Check"},"helpUri":"https://cwe.mitre.org/data/definitions/353.html"},{"id":"CWE-494","guid":"b8a65e0d-e459-4a55-a931-fc1136482375","name":"Download of Code Without Integrity Check","shortDescription":{"text":"Download of Code Without Integrity Check"},"helpUri":"https://cwe.mitre.org/data/definitions/494.html"},{"id":"CWE-502","guid":"f7d3b296-aac0-5c5a-b706-e07faba26c36","name":"Deserialization of Untrusted Data","shortDescription":{"text":"Deserialization of Untrusted Data"},"helpUri":"https://cwe.mitre.org/data/definitions/502.html"},{"id":"CWE-506","guid":"401d6455-56e3-0552-9a39-f77461673e3f","name":"Embedded Malicious Code","shortDescription":{"text":"Embedded Malicious Code"},"helpUri":"https://cwe.mitre.org/data/definitions/506.html"},{"id":"CWE-527","guid":"79b27cde-9d04-1a54-b64b-d5bb9b4a8ee7","name":"CWE-527","shortDescription":{"text":"CWE-527"},"helpUri":"https://cwe.mitre.org/data/definitions/527.html"},{"id":"CWE-538","guid":"3baa1f05-df1b-ae58-9ee0-1d790ff4a989","name":"Insertion of Sensitive Information into Externally-Accessible File or Directory","shortDescription":{"text":"Insertion of Sensitive Information into Externally-Accessible File or Directory"},"helpUri":"https://cwe.mitre.org/data/definitions/538.html"},{"id":"CWE-611","guid":"1afbae66-ea29-2d59-aaa2-134e3ae2e85a","name":"Improper Restriction of XML External Entity Reference","shortDescription":{"text":"Improper Restriction of XML External Entity Reference"},"helpUri":"https://cwe.mitre.org/data/definitions/611.html"},{"id":"CWE-614","guid":"faa8a6a5-7e9d-5d5e-afc9-020ff49d250a","name":"Sensitive Cookie in HTTPS Session Without \u0027Secure\u0027 Attribute","shortDescription":{"text":"Sensitive Cookie in HTTPS Session Without \u0027Secure\u0027 Attribute"},"helpUri":"https://cwe.mitre.org/data/definitions/614.html"},{"id":"CWE-732","guid":"1da27e8f-b330-7650-ab63-bd61953eae5d","name":"Incorrect Permission Assignment for Critical Resource","shortDescription":{"text":"Incorrect Permission Assignment for Critical Resource"},"helpUri":"https://cwe.mitre.org/data/definitions/732.html"},{"id":"CWE-77","guid":"332c8ade-6612-9f56-a06b-d8d90b1a8750","name":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/77.html"},{"id":"CWE-78","guid":"2e31ceaf-c7ae-2e5e-9661-cfb1362789cf","name":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/78.html"},{"id":"CWE-79","guid":"fd45580b-e8c4-fc5e-8c2f-aa8fab0b4dbf","name":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)","shortDescription":{"text":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/79.html"},{"id":"CWE-798","guid":"5e8f057d-fee3-995a-a0cb-9fc5b0d174d1","name":"Use of Hard-coded Credentials","shortDescription":{"text":"Use of Hard-coded Credentials"},"helpUri":"https://cwe.mitre.org/data/definitions/798.html"},{"id":"CWE-829","guid":"13c33925-97fb-5a5e-b40c-56d328b8a4d7","name":"Inclusion of Functionality from Untrusted Control Sphere","shortDescription":{"text":"Inclusion of Functionality from Untrusted Control Sphere"},"helpUri":"https://cwe.mitre.org/data/definitions/829.html"},{"id":"CWE-89","guid":"6d08fdad-37eb-c150-bbf0-d7d946863407","name":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/89.html"},{"id":"CWE-937","guid":"16f316ae-415c-b354-a59b-1f7905f756e9","name":"Using Components with Known Vulnerabilities","shortDescription":{"text":"Using Components with Known Vulnerabilities"},"helpUri":"https://cwe.mitre.org/data/definitions/937.html"},{"id":"CWE-939","guid":"12397742-f2c4-8254-8012-482c3356c551","name":"CWE-939","shortDescription":{"text":"CWE-939"},"helpUri":"https://cwe.mitre.org/data/definitions/939.html"},{"id":"CWE-94","guid":"75e7f50c-6c2f-dd52-bf40-bf6c52b861fd","name":"Improper Control of Generation of Code (\u0027Code Injection\u0027)","shortDescription":{"text":"Improper Control of Generation of Code (\u0027Code Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/94.html"},{"id":"CWE-95","guid":"400bba4e-483c-5c50-a695-114fa9168003","name":"Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/95.html"}]},{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61","version":"2025","organization":"OWASP Foundation","informationUri":"https://top10.owasp.org/2025/","isComprehensive":false,"shortDescription":{"text":"The OWASP Top 10:2025 web application security risks."},"taxa":[{"id":"A01:2025","guid":"df693558-c822-0452-8f7b-4d53cb6bcc59","name":"Broken Access Control","shortDescription":{"text":"Broken Access Control"},"helpUri":"https://top10.owasp.org/2025/A01_2025-Broken_Access_Control/"},{"id":"A02:2025","guid":"668dee9e-41bc-6354-97d0-fdf8f40c50c1","name":"Security Misconfiguration","shortDescription":{"text":"Security Misconfiguration"},"helpUri":"https://top10.owasp.org/2025/A02_2025-Security_Misconfiguration/"},{"id":"A03:2025","guid":"168e227c-7735-2e57-bc6e-997affe644c5","name":"Software Supply Chain Failures","shortDescription":{"text":"Software Supply Chain Failures"},"helpUri":"https://top10.owasp.org/2025/A03_2025-Software_Supply_Chain_Failures/"},{"id":"A04:2025","guid":"6a9f5bfd-1a56-6453-beec-a7eff0ba3007","name":"Cryptographic Failures","shortDescription":{"text":"Cryptographic Failures"},"helpUri":"https://top10.owasp.org/2025/A04_2025-Cryptographic_Failures/"},{"id":"A05:2025","guid":"87e86033-3231-8458-8e4a-5cb82743553a","name":"Injection","shortDescription":{"text":"Injection"},"helpUri":"https://top10.owasp.org/2025/A05_2025-Injection/"},{"id":"A06:2025","guid":"491554d7-b8e4-9652-91a9-53700dc92ece","name":"Insecure Design","shortDescription":{"text":"Insecure Design"},"helpUri":"https://top10.owasp.org/2025/A06_2025-Insecure_Design/"},{"id":"A07:2025","guid":"334ddd78-539d-d35c-83dd-253647eb7eaf","name":"Authentication Failures","shortDescription":{"text":"Authentication Failures"},"helpUri":"https://top10.owasp.org/2025/A07_2025-Authentication_Failures/"},{"id":"A08:2025","guid":"84b0c297-710e-9a5f-9335-936ecb260c36","name":"Software or Data Integrity Failures","shortDescription":{"text":"Software or Data Integrity Failures"},"helpUri":"https://top10.owasp.org/2025/A08_2025-Software_or_Data_Integrity_Failures/"}]},{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35","organization":"OWASP Foundation","informationUri":"https://owasp.org/www-project-top-10-ci-cd-security-risks/","isComprehensive":false,"shortDescription":{"text":"The OWASP Top 10 CI/CD Security Risks."},"taxa":[{"id":"CICD-SEC-3","guid":"458c83a6-ebf7-cf55-8cc3-b4d949bbf271","name":"Dependency Chain Abuse","shortDescription":{"text":"Dependency Chain Abuse"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-03-Dependency-Chain-Abuse"},{"id":"CICD-SEC-5","guid":"cc7f4610-8859-e654-9029-d5f97d992220","name":"Insufficient PBAC (Pipeline-Based Access Controls)","shortDescription":{"text":"Insufficient PBAC (Pipeline-Based Access Controls)"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-05-Insufficient-PBAC"},{"id":"CICD-SEC-6","guid":"f2ee2486-b260-2952-a41f-6b67fa713940","name":"Insufficient Credential Hygiene","shortDescription":{"text":"Insufficient Credential Hygiene"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-06-Insufficient-Credential-Hygiene"},{"id":"CICD-SEC-8","guid":"b6b2dacf-a168-4957-876e-a8c73ee00eb0","name":"Ungoverned Usage of 3rd Party Services","shortDescription":{"text":"Ungoverned Usage of 3rd Party Services"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-08-Ungoverned-Usage-of-3rd-Party-Services"},{"id":"CICD-SEC-9","guid":"b3d36727-0395-5b51-94c4-5e173d62eab3","name":"Improper Artifact Integrity Validation","shortDescription":{"text":"Improper Artifact Integrity Validation"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-09-Improper-Artifact-Integrity-Validation"}]}],"properties":{"codehealthPublication":{"public":true,"notice":"This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings \u2014 which rule fired, in which file, on which line, and how to fix it \u2014 are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.","securityFindingsRedacted":267,"secretScannerRunsExcluded":0}},"redactionTokens":["A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."]}]}