{"$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":"D10","name":"Test Quality","shortDescription":{"text":"Test Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D10"},{"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":"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":"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":"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":"AX8","name":"Test isolation","shortDescription":{"text":"Test isolation"},"helpUri":"https://codehealth.canine.dev/dimensions/AX8"},{"id":"AX9","name":"CQS / query purity","shortDescription":{"text":"CQS / query purity"},"helpUri":"https://codehealth.canine.dev/dimensions/AX9"},{"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":"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":"M4","name":"Documentation accuracy","shortDescription":{"text":"Documentation accuracy"},"helpUri":"https://codehealth.canine.dev/dimensions/M4"},{"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":"S1","name":"Web-Security Posture","shortDescription":{"text":"Web-Security Posture"},"helpUri":"https://codehealth.canine.dev/dimensions/S1"},{"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":"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":"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":"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":"X24","name":"Document value interpolated into markup unescaped","shortDescription":{"text":"Document value interpolated into markup unescaped"},"helpUri":"https://codehealth.canine.dev/dimensions/X24"},{"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":"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":"CometScanRule.transformV2Scan (cyclomatic 103): CometScanRule.transformV2Scan has cyclomatic complexity 103 (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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d0a3b038862d45fe3a56ecc685f02534ba2f45b47e8e9608ba829f41b7c0ced"}},{"ruleId":"D1","level":"warning","message":{"text":"MakeDateEvaluation.preserve (cyclomatic 86): MakeDateEvaluation.preserve has cyclomatic complexity 86 (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":"spark/src/main/scala/org/apache/comet/rules/MakeDateEvaluation.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ef19bf4c8eabce917ca5a391b6d35484b9dce92442d3aa43ece96b664f966d4"}},{"ruleId":"D1","level":"warning","message":{"text":"CometWindowExec.windowExprToProto (cyclomatic 70): CometWindowExec.windowExprToProto 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"bddd85e33c2e92111234377c406134cc87609f3f79e68cd3d66c2541c5f9eebc"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major (cyclomatic 68): datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major has cyclomatic complexity 68 (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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":823}}}],"partialFingerprints":{"codehealthFindingId/v1":"27e1389cb7aca76318a8bb8e56554f5b40bc0d6c3f95c1fe3b8aec9d0b190701"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major (cyclomatic 66): datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major has cyclomatic complexity 66 (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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbd28b0954b2a261b93d89a6fd6e50b09c8ec51aee11418dc29a6c8408d2024c"}},{"ruleId":"D1","level":"warning","message":{"text":"ShimSparkErrorConverter.convertErrorType (cyclomatic 65): ShimSparkErrorConverter.convertErrorType has cyclomatic complexity 65 (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":"spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c25e3e6b94a5a9bd07d65aaf625fb4cd4d1eda95b009597d4517e72e1352c61"}},{"ruleId":"D1","level":"warning","message":{"text":"FuzzDataGenerator.generateColumn (cyclomatic 62): FuzzDataGenerator.generateColumn 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":"spark/src/main/scala/org/apache/comet/testing/FuzzDataGenerator.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c3ad41f6b84cf05d372e74d60b204fc7a35cdc785b7a0070c1169e101389fb8"}},{"ruleId":"D1","level":"warning","message":{"text":"ShimSparkErrorConverter.convertErrorType (cyclomatic 62): ShimSparkErrorConverter.convertErrorType 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"1034abc9e87661b555894e55a5d72873211274661cbb863ab7c524396d13b025"}},{"ruleId":"D1","level":"warning","message":{"text":"CometExecRule.transform (cyclomatic 55): CometExecRule.transform 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"af21b814ef4ba757b285a9f74d31056132b4c6caeca91d54df50d6e5a5dd0391"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::abs::abs (cyclomatic 54): datafusion_comet_spark_expr::math_funcs::abs::abs has cyclomatic complexity 54 (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":"native/spark-expr/src/math_funcs/abs.rs"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0ea42282cc8ad57e20cccf44d9d41d776fa5802d6f20295e1218dda8f26c005"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_field (cyclomatic 53): datafusion_comet_shuffle::spark_unsafe::row::append_field has cyclomatic complexity 53 (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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"d69c4cb90bb210b83146ceb364a70a3d7ac485369a9b8972270b6c5c22e5843c"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_columns (cyclomatic 53): datafusion_comet_shuffle::spark_unsafe::row::append_columns has cyclomatic complexity 53 (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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1079}}}],"partialFingerprints":{"codehealthFindingId/v1":"35292ed281d89f50bf7acbf616b7446dbe1e2496704300a92318f3605419a025"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::cast::cast_array (cyclomatic 53): datafusion_comet_spark_expr::conversion_funcs::cast::cast_array 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8df9dfa036a015a695a3358b76ffd8f6841c0439fc88a785e1b70bd8ee311c1"}},{"ruleId":"D1","level":"warning","message":{"text":"DeltaScanSupport.declineReason (cyclomatic 50): DeltaScanSupport.declineReason has cyclomatic complexity 50 (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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf18323ab96766c891558b6110bc1f3aadc9da6ac40eae514b7983f75fb242ff"}},{"ruleId":"D1","level":"warning","message":{"text":"PhysicalPlanner::create_agg_expr (cyclomatic 44): PhysicalPlanner::create_agg_expr 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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"b79f8a9bea43f09bc4ad96204c6c517900333a60a82c9944841852651800e114"}},{"ruleId":"D1","level":"warning","message":{"text":"PhysicalPlanner::create_expr (cyclomatic 44): PhysicalPlanner::create_expr has cyclomatic complexity 44 (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":"native/core/src/execution/planner.rs"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"50bae51d0a23ea5cd322f46986ecbae57a5824141d594c3c49df3eb55233fc4b"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::execution::planner::literal::literal_to_scalar (cyclomatic 42): datafusion_comet::execution::planner::literal::literal_to_scalar has cyclomatic complexity 42 (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":"native/core/src/execution/planner/literal.rs"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb173e24f6ac45cbf9789154751e30220b7161366daaaab5ed73af889d398cea"}},{"ruleId":"D1","level":"warning","message":{"text":"CometNativeExec.buildNativeContext (cyclomatic 41): CometNativeExec.buildNativeContext 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":991}}}],"partialFingerprints":{"codehealthFindingId/v1":"216b7764ce0770b34cd053d316317fc9a2e2be374d98df6800be9de440aef893"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold (cyclomatic 38): datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0d1b6a13847c38d4b2a12f05c450ca0ba7100faec9d5163c12c71278ef11d6b"}},{"ruleId":"D1","level":"warning","message":{"text":"DirectColumnarToRowConverter.writeColumnFixedWidth (cyclomatic 38): DirectColumnarToRowConverter.writeColumnFixedWidth 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":"spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java"},"region":{"startLine":382}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c9ad8e4dfe9207d9396be729239ed61e270ecd2fe2c8e53b32fbebb54cf2c35"}},{"ruleId":"D1","level":"warning","message":{"text":"CometCast.isSupported (cyclomatic 37): CometCast.isSupported 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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aefbdb3512f23df4a6cca9ca72379f49ceda79e2c6167c322e1104de61052a5"}},{"ruleId":"D1","level":"warning","message":{"text":"CometIcebergNativeScan.icebergLiteralToProto (cyclomatic 36): CometIcebergNativeScan.icebergLiteralToProto 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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"20f6a09e1bd7511c7c579df0d10d5a4ea7b07d49effb32ac6f9e5669298edd57"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_list_column_batch (cyclomatic 35): datafusion_comet_shuffle::spark_unsafe::row::append_list_column_batch 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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":623}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a56369e9850224f05dc2695f3dbe72e3a0eaa5c15c161ec910deed49f66fc32"}},{"ruleId":"D1","level":"warning","message":{"text":"QueryPlanSerde.serializeDataType (cyclomatic 35): QueryPlanSerde.serializeDataType 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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":646}}}],"partialFingerprints":{"codehealthFindingId/v1":"e47ce46e9058bba686219a9002e70f408ddd8a2acfa3010046208eec0a027fdd"}},{"ruleId":"D1","level":"warning","message":{"text":"FixedWidthArrowFieldWriter.copyValues (cyclomatic 35): FixedWidthArrowFieldWriter.copyValues 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"a49addc39a4581a4a3c0b73444a5c52cca9c86db2044755839623850f7f2a6cf"}},{"ruleId":"D1","level":"warning","message":{"text":"PhysicalPlanner::create_plan (cyclomatic 34): PhysicalPlanner::create_plan 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":"native/core/src/execution/planner.rs"},"region":{"startLine":1643}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf7b34bbfef92ad8bfd05712f1be4f4fa2585b07d29db9551de484521dfbe408"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::list::append_to_builder (cyclomatic 32): datafusion_comet_shuffle::spark_unsafe::list::append_to_builder has cyclomatic complexity 32 (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":"native/shuffle/src/spark_unsafe/list.rs"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cbf59b6cae7a044ea747355e948bcb677c62ae46bed701b6963b3557fa409fb"}},{"ruleId":"D1","level":"warning","message":{"text":"CometBaseAggregate.doConvert (cyclomatic 32): CometBaseAggregate.doConvert 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":2221}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b9348d9f90724a32e17361c4f38928f92a7d7815ca457b1690cb545ba007f74"}},{"ruleId":"D1","level":"warning","message":{"text":"CometHashJoin.doConvert (cyclomatic 32): CometHashJoin.doConvert 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":2861}}}],"partialFingerprints":{"codehealthFindingId/v1":"922e27740d9024930ee26fe11e95be41e611ad57a60ab7927d5abb36162a2870"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornShufflePartitionPusher.\u003Cinit\u003E (cyclomatic 32): CelebornShufflePartitionPusher.\u003Cinit\u003E 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c3defa2bb594badef37052d253bb8eb27f66625fb03b37d7b7fddbe6d3b4324"}},{"ruleId":"D1","level":"warning","message":{"text":"CometShuffleExchangeExec.nativeShuffleFailureReasons (cyclomatic 31): CometShuffleExchangeExec.nativeShuffleFailureReasons 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab59b3b14bf9c68f6e4917f895d0d2fb94a89e65e7ec82c4010bee2c3f58ecba"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornShufflePartitionPusher.pushClaimedPartitionData (cyclomatic 31): CelebornShufflePartitionPusher.pushClaimedPartitionData 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":532}}}],"partialFingerprints":{"codehealthFindingId/v1":"00847d4d7d4c5bf8a263dfab52ff6e85d356fc5b5d2bd0482436b5e58eb56299"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_common::bin::analyze_trace::main (cyclomatic 29): datafusion_comet_common::bin::analyze_trace::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":"native/common/src/bin/analyze_trace.rs"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"df7a185ff6e3376ea24e09cd38e9eb9459e2feec3f4c42ea2e62c26ddd329a4c"}},{"ruleId":"D1","level":"warning","message":{"text":"PhysicalPlanner::create_window_expr (cyclomatic 29): PhysicalPlanner::create_window_expr 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":"native/core/src/execution/planner/window.rs"},"region":{"startLine":309}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e4d3b0d4fa7dbe492e4f175b727c77404d7b69bec7efc31618c293d5e699809"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_common::utils::decode_long_or_non_ascii_utf8_spark_lossy (cyclomatic 28): datafusion_comet_common::utils::decode_long_or_non_ascii_utf8_spark_lossy 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":"native/common/src/utils.rs"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5a50c29e5c16cb124a313ab51ca4d350a6fe715291958a60c3ebca6064eb211"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::execution::serde::to_arrow_datatype (cyclomatic 28): datafusion_comet::execution::serde::to_arrow_datatype 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":"native/core/src/execution/serde.rs"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c67dd273b8ad345b2631e3f36dedc91384fd2e0379456d6258130447e40c22d"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::violates_jackson_limits (cyclomatic 28): datafusion_comet_spark_expr::string_funcs::get_json_object::violates_jackson_limits 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"5dba45b4f4574b9b4e0b448f1467a2890448acfb2962e048a5390107d5574412"}},{"ruleId":"D1","level":"warning","message":{"text":"CometBatchKernelCodegenInput.emitStructScalarGetters (cyclomatic 28): CometBatchKernelCodegenInput.emitStructScalarGetters 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":868}}}],"partialFingerprints":{"codehealthFindingId/v1":"9331437a9410b053468096bef83abd2bc8414ce728fbb4d0ae81b9e5ab586b60"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string (cyclomatic 27): datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":898}}}],"partialFingerprints":{"codehealthFindingId/v1":"3e2e534cebf70a7496484ddc7f1d00f72aed186829ed5297565def6915e68d83"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::execution::planner::literal_to_array_ref (cyclomatic 26): datafusion_comet::execution::planner::literal_to_array_ref 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":"native/core/src/execution/planner.rs"},"region":{"startLine":2803}}}],"partialFingerprints":{"codehealthFindingId/v1":"da0d45e2f95da2ab46ce8f4a8bbb413c726c37218cb4d4eddab9d7eea16035cc"}},{"ruleId":"D1","level":"warning","message":{"text":"PhysicalPlanner::create_binary_expr_with_options (cyclomatic 25): PhysicalPlanner::create_binary_expr_with_options 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":"native/core/src/execution/planner.rs"},"region":{"startLine":1391}}}],"partialFingerprints":{"codehealthFindingId/v1":"7eebf7e9fddfa7f6a330b5cead6ec1d125c30510c8a0978ec32043707c0487da"}},{"ruleId":"D1","level":"warning","message":{"text":"AtLeastNNonNulls::evaluate (cyclomatic 25): AtLeastNNonNulls::evaluate 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":"native/spark-expr/src/predicate_funcs/at_least_n_non_nulls.rs"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b7aa36933042adf47964c740c1315bf4b2573bbbfff8b2cb9a5aff1563598b7"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::json_funcs::from_json::append_field_value (cyclomatic 25): datafusion_comet_spark_expr::json_funcs::from_json::append_field_value 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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5551e4f1a5834ea9b813653588e359027ffa1beb1e58eaabc4c14528d7569db"}},{"ruleId":"D1","level":"warning","message":{"text":"check-ci-config.check_fork_runs (cyclomatic 25): check-ci-config.check_fork_runs 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/ci/check-ci-config.py"},"region":{"startLine":1618}}}],"partialFingerprints":{"codehealthFindingId/v1":"370c761403e624d721df27940fa5352f6d056e933d11cc8ae9f883062bd42040"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::parquet_support::parquet_convert_array_impl (cyclomatic 24): datafusion_comet::parquet::parquet_support::parquet_convert_array_impl 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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"e579765c9ff95d9a128c43573444ee7b3ce93eb72eec53a1df35ec27b6fccc03"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::date_parser (cyclomatic 24): datafusion_comet_spark_expr::conversion_funcs::string::date_parser has cyclomatic complexity 24 (threshold 15). Of this number, 18 points are the body\u0027s own statements and 6 belong to 3 function items 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":2322}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b9b7c725bb1bafa036a6289bb14c0bbb62685f15ff4e4a2d78c322e83e4e3be"}},{"ruleId":"D1","level":"warning","message":{"text":"CometArrowEvalPythonExec.getSupportLevel (cyclomatic 24): CometArrowEvalPythonExec.getSupportLevel 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":"spark/src/main/spark-4.1\u002B/org/apache/spark/sql/comet/CometArrowEvalPythonExec.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"df940ab5cb43cf37fd7c7681a1951dd5754dc0548aa568be029f48d61dad2a6b"}},{"ruleId":"D1","level":"warning","message":{"text":"DirectColumnarToRowConverter.convertRow (cyclomatic 24): DirectColumnarToRowConverter.convertRow 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":"spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"67591d85aa3be3396e2d8b0353ba5e8e83941d92cd8392926750cc501dd0cd9f"}},{"ruleId":"D1","level":"warning","message":{"text":"RssPartitionWriter::compact_array (cyclomatic 23): RssPartitionWriter::compact_array 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":926}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9d24dc7160161bd94fc560c85bf8679ad3ca931daf4e1cc5dbf9145804ec951"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornRawPartitionReader.openPartitions (cyclomatic 23): CelebornRawPartitionReader.openPartitions 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.scala"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"37b9faad22028688413e3ac9b7141cd65bb24a4951899d762cbe6ee3d6efc377"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::parse_json_path (cyclomatic 22): datafusion_comet_spark_expr::string_funcs::get_json_object::parse_json_path 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c67d8209b80328892a7db65598132be48f5af9e1a1610ea711a291992e27791"}},{"ruleId":"D1","level":"warning","message":{"text":"CometExecRule._apply (cyclomatic 22): CometExecRule._apply 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1107}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3b6f18be1c3068304228f01ff01e9f5272e4bb3cdaf27cb6f136f305ecfde5c"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornShufflePartitionPusher.reconcileAcceptedPushes (cyclomatic 22): CelebornShufflePartitionPusher.reconcileAcceptedPushes 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0c7038531d64535bc012bdf0d02c952471b52d9bf2da016375ef43e76f2a14e"}},{"ruleId":"D1","level":"warning","message":{"text":"EagerPageIndexReader::get_metadata (cyclomatic 21): EagerPageIndexReader::get_metadata 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":"native/core/src/parquet/eager_page_index_reader_factory.rs"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"60855c2cb2472911e0c93a5d51677acbe1be7dc447bbed34bdda8fbec4f17cb2"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::schema_adapter::spark_has_updater (cyclomatic 21): datafusion_comet::parquet::schema_adapter::spark_has_updater 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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"179c1ebd4b6617af33ede03460285ecf50a6c38b9367e38d3ed0ae45abf5a6a6"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_upstream (cyclomatic 21): datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_upstream 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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":1109}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dd0ca3271cb2b9c916039124d52b3fe8f5e718637490e25c942390439f19d51"}},{"ruleId":"D1","level":"warning","message":{"text":"CometExecRule.revertUnsafePartialAggregates (cyclomatic 21): CometExecRule.revertUnsafePartialAggregates 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1991}}}],"partialFingerprints":{"codehealthFindingId/v1":"d9d4ca8058ba8454530c4dcda03a5f3e4a535abd747fc2a338e595412df1b96a"}},{"ruleId":"D1","level":"warning","message":{"text":"check-iceberg-shards.verify_manifests (cyclomatic 21): check-iceberg-shards.verify_manifests 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":"dev/ci/check-iceberg-shards.py"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d069a34ae427884237676378f2c73ffbd7b6187b0a15948943fa023378e2879"}},{"ruleId":"D1","level":"warning","message":{"text":"generate-changelog.generate_changelog (cyclomatic 21): generate-changelog.generate_changelog 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":"dev/release/generate-changelog.py"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3df7820998e50a77924c295e1b49d5027fda46d306fa024634d1507edebca9b"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::execution::operators::dynamic_filter::early::place (cyclomatic 20): datafusion_comet::execution::operators::dynamic_filter::early::place 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":"native/core/src/execution/operators/dynamic_filter/early.rs"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6d0d0c098f051605c86009c2c1b4c7677959dcabe45f5d29eefaf0dfbdee56b"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::execution::operators::dynamic_filter::parquet_reader::try_attach_parquet_reader_filter (cyclomatic 20): datafusion_comet::execution::operators::dynamic_filter::parquet_reader::try_attach_parquet_reader_filter 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":"native/core/src/execution/operators/dynamic_filter/parquet_reader.rs"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d43a888b6171f6d4240e9341afabbca3a99f2690066a5cc62d543d0533895d3"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::parse_sign_offset (cyclomatic 20): datafusion_comet_spark_expr::conversion_funcs::string::parse_sign_offset 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1691}}}],"partialFingerprints":{"codehealthFindingId/v1":"35d83a7274ddc85687ae446724c830e106bfe0c0cedafd6978e95540fc9e3d48"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::datetime_funcs::to_time::string_to_time (cyclomatic 20): datafusion_comet_spark_expr::datetime_funcs::to_time::string_to_time 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":"native/spark-expr/src/datetime_funcs/to_time.rs"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e38e945bf928ead9133318d4db3a3733fc9832cbbdacfdbed62de7802942097"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein (cyclomatic 20): datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca5c81100f4ed9086ea2403a06acdbc5dc6658afc0ccf0b3ab9479ad28281118"}},{"ruleId":"D1","level":"warning","message":{"text":"CometMakeDate.unsupportedParentReason (cyclomatic 20): CometMakeDate.unsupportedParentReason 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":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef829d64f5277c2f72dc923e4032eae06ab409f889235c2e0eb15ed4a3b2c4d2"}},{"ruleId":"D1","level":"warning","message":{"text":"RssPartitionWriter::push_batch_within_limit (cyclomatic 19): RssPartitionWriter::push_batch_within_limit 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"014a0ecca7df80953457353ae5653e9d56c4bf36fb41523e433d797a05b57d75"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::csv_funcs::to_csv::to_csv_inner (cyclomatic 19): datafusion_comet_spark_expr::csv_funcs::to_csv::to_csv_inner 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":"native/spark-expr/src/csv_funcs/to_csv.rs"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"253b6a8a9bfbd1d5cac8daf4cf34f1a679159fdadbd9658dc11e1ef1edf6dec4"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::div::spark_decimal_div_internal (cyclomatic 19): datafusion_comet_spark_expr::math_funcs::div::spark_decimal_div_internal 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":"native/spark-expr/src/math_funcs/div.rs"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"69529fb59015f4ec84aab16394ebbbd8a6cf7651e90040177089b937b166871d"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::url_funcs::parse_url::parse_url_component (cyclomatic 19): datafusion_comet_spark_expr::url_funcs::parse_url::parse_url_component 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":"native/spark-expr/src/url_funcs/parse_url.rs"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"70d06f269d2f5af901f37e1394a3151812d9914452cf931e42df3a5ba9eea361"}},{"ruleId":"D1","level":"warning","message":{"text":"CometBatchKernelCodegenInput.emitTypedGetters (cyclomatic 19): CometBatchKernelCodegenInput.emitTypedGetters 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4707f859e6f018cc4071d40a9d0ff589a8a9d44692cfe74d8bf85821195a672"}},{"ruleId":"D1","level":"warning","message":{"text":"CometBatchKernelCodegenOutput.emitWrite (cyclomatic 19): CometBatchKernelCodegenOutput.emitWrite 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: CometBatchKernelCodegenOutput.outputVectorClass (cyclomatic 21) 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenOutput.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"6adcf53caa2f35231d61d0458ae919060df822302da576abec0a36ae53cc02b4"}},{"ruleId":"D1","level":"warning","message":{"text":"CometLiteral.makeListLiteral (cyclomatic 19): CometLiteral.makeListLiteral 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":"spark/src/main/scala/org/apache/comet/serde/literals.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"07242ece9d2115be5b67e6bd2461f07624165d285dd685ffac53a9ae67cca02d"}},{"ruleId":"D1","level":"warning","message":{"text":"CometWindowExec.rangeBoundLiteral (cyclomatic 19): CometWindowExec.rangeBoundLiteral 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":754}}}],"partialFingerprints":{"codehealthFindingId/v1":"406634e0c89e3012847aa9f7612a5b2278a59711e742b291ce7304da225cb0b3"}},{"ruleId":"D1","level":"warning","message":{"text":"CometShuffleExchangeExec.columnarShuffleFailureReasons (cyclomatic 19): CometShuffleExchangeExec.columnarShuffleFailureReasons 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":749}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fee4a8df4c018266ac912f568c5c4874b19e20d059924d412703fce8fb5364e"}},{"ruleId":"D1","level":"warning","message":{"text":"check-ci-config.check_event_policy (cyclomatic 19): check-ci-config.check_event_policy 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":"dev/ci/check-ci-config.py"},"region":{"startLine":785}}}],"partialFingerprints":{"codehealthFindingId/v1":"95edc2ef150328356a483da46178b1f8df16a741feb64e01c4ea756cd4098128"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::append_spark_variant (cyclomatic 18): datafusion_comet::parquet::cast_column::variant::append_spark_variant 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":870}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff304840aad80e92cfd82479c15952d7dd4968a046e431de47fdfeeaea3e15fa"}},{"ruleId":"D1","level":"warning","message":{"text":"RankLimitStream::process_batch (cyclomatic 18): RankLimitStream::process_batch 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":"native/operators/src/rank_limit.rs"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"c87068675722e5a86220f540cd0ae0a046cbde103d3fbe5b7384b5b6a511a27f"}},{"ruleId":"D1","level":"warning","message":{"text":"NegativeExpr::evaluate (cyclomatic 18): NegativeExpr::evaluate 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":"native/spark-expr/src/math_funcs/negative.rs"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dc6928ea14b3172de4e0c57988be7f4816ec15fd381adaedffbb097f3d89df5"}},{"ruleId":"D1","level":"warning","message":{"text":"SegmentVisitor::visit_seq (cyclomatic 18): SegmentVisitor::visit_seq 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":768}}}],"partialFingerprints":{"codehealthFindingId/v1":"af90057a529c9dd9e2b04aa4558d0272bb32267eb425845d435a77149117b671"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner (cyclomatic 18): datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner 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":"native/spark-expr/src/array_funcs/arrays_zip.rs"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"1623870f5f3d1f9d2d2070fd39fca443be30d21a83ed669689645d962bbaf38f"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::checked_arithmetic::checked_arithmetic_internal (cyclomatic 18): datafusion_comet_spark_expr::math_funcs::checked_arithmetic::checked_arithmetic_internal 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":"native/spark-expr/src/math_funcs/checked_arithmetic.rs"},"region":{"startLine":322}}}],"partialFingerprints":{"codehealthFindingId/v1":"655c777fd1d3ec5a1d6da02a0fc6c0e37065ef0b9465a469bc9260c2c0db7cec"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::spark_get_json_object_impl (cyclomatic 18): datafusion_comet_spark_expr::string_funcs::get_json_object::spark_get_json_object_impl 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f2bc2278530b6d3273c15f32c6123adc2bb553d7d71c3ad97350a6fad782a4b"}},{"ruleId":"D1","level":"warning","message":{"text":"CometExecRule.canApplySparkToColumnar (cyclomatic 18): CometExecRule.canApplySparkToColumnar 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1605}}}],"partialFingerprints":{"codehealthFindingId/v1":"c47b2514d79ba455922cca03fa366234e83ba62dc91103584ed8068dc48b5099"}},{"ruleId":"D1","level":"warning","message":{"text":"CometScanRule.nativeScan (cyclomatic 18): CometScanRule.nativeScan 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"e519c6ea2471ed9c2c2a98eb625b748989311bc6ffff9b23db9304aed0e3bac0"}},{"ruleId":"D1","level":"warning","message":{"text":"DecimalWriter.writeColumnSlice (cyclomatic 18): DecimalWriter.writeColumnSlice 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: ArrowWriter.createFieldWriter (cyclomatic 24) 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":1293}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f281dbf2a394e37374b6fa16cd6836999a8a4dac2c7e2838f651e58daf21d50"}},{"ruleId":"D1","level":"warning","message":{"text":"ShimSparkErrorConverter.getDataType (cyclomatic 18): ShimSparkErrorConverter.getDataType 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e19e9b1134d8ac10991337fc55c26df9e728355765d11235bd4fae7b0215eec"}},{"ruleId":"D1","level":"warning","message":{"text":"ShimSparkErrorConverter.getDataType (cyclomatic 18): ShimSparkErrorConverter.getDataType 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":"spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"62b7d64758d9e1c82e7f36fd2b63c9bb313e21b557b964f09393cab8a08e17ec"}},{"ruleId":"D1","level":"warning","message":{"text":"CometArrowPythonRunnerBase.inputBatchRanges (cyclomatic 18): CometArrowPythonRunnerBase.inputBatchRanges 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":"spark/src/main/spark-4.x/org/apache/spark/sql/execution/python/CometArrowPythonRunnerBase.scala"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf34447af43fc53ec99c181499303b4c49cd33c0e76f8ab453e3dd1fb69ac704"}},{"ruleId":"D1","level":"warning","message":{"text":"HashAggBuilder::build (cyclomatic 17): HashAggBuilder::build 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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"528ad9b0a13aee3723e3515b874186aecdd819d7466569e15c47ccdb7bee5edb"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::datetime_rebase::push_unrequested_leaves (cyclomatic 17): datafusion_comet::parquet::datetime_rebase::push_unrequested_leaves 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":"native/core/src/parquet/datetime_rebase.rs"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"80ab37239e00e286ec7eee2ffd374127d1d2b136bb63e5cba33c0b70f4ceaf96"}},{"ruleId":"D1","level":"warning","message":{"text":"RssPartitionWriter::estimated_array_compaction_scratch (cyclomatic 17): RssPartitionWriter::estimated_array_compaction_scratch 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":798}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5ea068bca074b3f35cc507078ff2e4c40cbe966b61003cff2896a6d6978944a"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_map_column_batch (cyclomatic 17): datafusion_comet_shuffle::spark_unsafe::row::append_map_column_batch 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: datafusion_comet_shuffle::spark_unsafe::row::make_builders (cyclomatic 20) 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 function is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":714}}}],"partialFingerprints":{"codehealthFindingId/v1":"0325861f89949781216b08e3a7ffca75a3638e010d259e9f633693c35b7c61f7"}},{"ruleId":"D1","level":"warning","message":{"text":"WideDecimalBinaryExpr::evaluate (cyclomatic 17): WideDecimalBinaryExpr::evaluate 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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"a0e2f426af350247072e1718783b7e843e8378f5f789cf4424bfcee80c4c0fef"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_list_generic (cyclomatic 17): datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_list_generic 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: datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_rows (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 function is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/array_funcs/arrays_overlap.rs"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1ba6dd3338ef17c5d760401b4bf4729fcf42cead38f2a3003250e61423495e8"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::nested_compaction::has_excess_nested_capacity (cyclomatic 17): datafusion_comet_spark_expr::nested_compaction::has_excess_nested_capacity 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":"native/spark-expr/src/nested_compaction.rs"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1efb157a0e454c2743642882e796c700366c917b528504306b241f85c190cf6"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2 (cyclomatic 17): datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2 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":"native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d20b68fe42f68586f9ed079a30d53ad968887dc1df9535b0aa86a544bd70108"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance (cyclomatic 17): datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"611e3c8aa883cec8020cac8129bd5eb3007bf74c99434597f849a9922d59ddf9"}},{"ruleId":"D1","level":"warning","message":{"text":"DeltaScanSupport.attributesUnusedAbove (cyclomatic 17): DeltaScanSupport.attributesUnusedAbove 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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":1968}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6e56e79128fdc778eb2dcbb2edc2092de50eec034540ac1fdca49ae58904f6a"}},{"ruleId":"D1","level":"warning","message":{"text":"CometBatchKernelCodegen.canHandle (cyclomatic 17): CometBatchKernelCodegen.canHandle 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. This is NOT this file\u0027s highest cyclomatic complexity: CometBatchKernelCodegen.vectorClassBySimpleName (cyclomatic 18) 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a93f9971a97b64f1d29f6397cd5bc7aa1d5077e8c00d9fe39c6e692d1e365dd"}},{"ruleId":"D1","level":"warning","message":{"text":"Scanner.parseCountedQuantifier (cyclomatic 17): Scanner.parseCountedQuantifier 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":"spark/src/main/scala/org/apache/comet/expressions/CometRegex.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"46bdbedba17d706add708180ddea6ff54941a5a531a1f864353900a7ae5bf1f1"}},{"ruleId":"D1","level":"warning","message":{"text":"CometScanRule.validateIcebergFileScanTasks (cyclomatic 17): CometScanRule.validateIcebergFileScanTasks 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":1545}}}],"partialFingerprints":{"codehealthFindingId/v1":"f404d0977bdf47f007649551013890b440b81dff438749a7e216fcf565d745b6"}},{"ruleId":"D1","level":"warning","message":{"text":"EliminateRedundantTransitions._apply (cyclomatic 17): EliminateRedundantTransitions._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":"spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"5918bf1f47a8808fd7830799fa5dc06d46f2f973ecb01d92623aa564a3d4628d"}},{"ruleId":"D1","level":"warning","message":{"text":"CometNativeScan.isSupported (cyclomatic 17): CometNativeScan.isSupported 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":"spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"88653b0d48314403dd3219a5be6e89aa07b572ea725b27434fa555852b62eafe"}},{"ruleId":"D1","level":"warning","message":{"text":"ComparisonUtils.staticFloatingInList (cyclomatic 17): ComparisonUtils.staticFloatingInList 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":"spark/src/main/scala/org/apache/comet/serde/predicates.scala"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"33e382443d161ae23710cebe8e688e7a2465b3cbb50db9bf863340d5cf021d9f"}},{"ruleId":"D1","level":"warning","message":{"text":"Projection.load (cyclomatic 17): Projection.load 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"145fe5b517e19288411607e93dca6862388033cd56d36aa17a0e46d0f8a000c0"}},{"ruleId":"D1","level":"warning","message":{"text":"CometSortMergeJoinExec.convert (cyclomatic 17): CometSortMergeJoinExec.convert 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":3683}}}],"partialFingerprints":{"codehealthFindingId/v1":"72c396b72206453767d9ac67733943ef5c2cf7fea4673ef58206dae31f1bbd7e"}},{"ruleId":"D1","level":"warning","message":{"text":"bench_delta_comet.main (cyclomatic 17): bench_delta_comet.main 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":"contrib/delta-spark/dev/bench_delta_comet.py"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e15ccadf17d8e1c7a823a78cdd3370949bf6548a889a776480476a3b944b157"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet_common::utf8::decode_string_arrays (cyclomatic 16): datafusion_comet_common::utf8::decode_string_arrays 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":"native/common/src/utf8.rs"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"45adeb69e378163dbae0e6aeb1ca105d6a5992cef9bffaca4081cb26447634cf"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::rewrite_shredding_state (cyclomatic 16): datafusion_comet::parquet::cast_column::variant::rewrite_shredding_state 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"01fc6d79b4a03b9df91cc40ca8e97ba9217d22f3433e6a6ae90ae1a940e1d580"}},{"ruleId":"D1","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::rewrite_residual_values (cyclomatic 16): datafusion_comet::parquet::cast_column::variant::rewrite_residual_values 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"1bc65c0f056b5237d2e8d21260590260ba1dc7ad85eadbcef8d48b75d7d4477a"}},{"ruleId":"D1","level":"warning","message":{"text":"PivotIndex::try_new (cyclomatic 16): PivotIndex::try_new 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":"native/spark-expr/src/agg_funcs/pivot_first.rs"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd771be5b9049ca9575223aaf7fef6d03d8086d8397b8ac4b174e0ef58d987dd"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornShuffleGenerationCoordinator.claimMapAttempt (cyclomatic 16): CelebornShuffleGenerationCoordinator.claimMapAttempt 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"69076d0ef38829364a4458e03ce6f82e25e510b3b362e91c3f179e66df3df13b"}},{"ruleId":"D1","level":"warning","message":{"text":"CometNativeShuffleWriter.writeInternal (cyclomatic 16): CometNativeShuffleWriter.writeInternal 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"76893353d585408601a6affadb7006a2d0c84b5d6110b0d8532e55d0d61d62ac"}},{"ruleId":"D1","level":"warning","message":{"text":"CelebornShufflePartitionPusher.finish (cyclomatic 16): CelebornShufflePartitionPusher.finish 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5ba1a7850c3bb9dc77a5bac840047c173de76689327195a2fe974e5b71c24a8"}},{"ruleId":"D1","level":"warning","message":{"text":"summarize-iceberg-writes.summarize (cyclomatic 16): summarize-iceberg-writes.summarize 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":"dev/ci/summarize-iceberg-writes.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"beb53c3fae5545a7910e81440b1f38798bc258c220213ee3c1a767812440a0e1"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major (cognitive 222): datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major has cognitive complexity 222 (threshold 15). Drivers by points: if/else 64 (169 pts), loops 19 (51 pts), match/switch 1 (2 pts) (nesting depth added 138). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":823}}}],"partialFingerprints":{"codehealthFindingId/v1":"0965a2cab027468236002fec91bb248cb232ddb0052ef33a26a941898ba74d00"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major (cognitive 218): datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major has cognitive complexity 218 (threshold 15). Drivers by points: if/else 62 (166 pts), loops 18 (50 pts), match/switch 1 (2 pts) (nesting depth added 137). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5c70a9f585abfcdcdd0f4aee59de7e42cb1fbbcd3928804dcc3d127849656a6"}},{"ruleId":"D2","level":"warning","message":{"text":"CometScanRule.transformV2Scan (cognitive 195): CometScanRule.transformV2Scan has cognitive complexity 195 (threshold 15). Drivers by points: if/else 69 (121 pts), match/switch 17 (37 pts), error handling 8 (18 pts), boolean chains 17, loops 1 (2 pts) (nesting depth added 83). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"654675d7ec526cd7cea241c24f0446f7ec2d3627b84381e5e8ab19a95a282f71"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::abs::abs (cognitive 143): datafusion_comet_spark_expr::math_funcs::abs::abs has cognitive complexity 143 (threshold 15). Drivers by points: if/else 31 (75 pts), match/switch 20 (67 pts), boolean chains 1 (nesting depth added 91). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/math_funcs/abs.rs"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"67e62c33d487c963d1b84a19d9c4f116c9f44d246e074a6ad47fa2a11c255180"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_field (cognitive 117): datafusion_comet_shuffle::spark_unsafe::row::append_field has cognitive complexity 117 (threshold 15). Drivers by points: if/else 66 (113 pts), loops 1 (2 pts), boolean chains 1, match/switch 1 (nesting depth added 48). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c9dbf431c4986bff5af131e762a6a2ad9fa0993d56be51d15da74b67c759354"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_columns (cognitive 111): datafusion_comet_shuffle::spark_unsafe::row::append_columns has cognitive complexity 111 (threshold 15). Drivers by points: if/else 36 (73 pts), loops 17 (37 pts), match/switch 1 (nesting depth added 57). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1079}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a0516845c0c6cdeba6595350a38c4a3a78719bdcecde76d03aaf05d6ae83dd4"}},{"ruleId":"D2","level":"warning","message":{"text":"MakeDateEvaluation.preserve (cognitive 106): MakeDateEvaluation.preserve has cognitive complexity 106 (threshold 15). Drivers by points: if/else 51 (61 pts), boolean chains 25, match/switch 17 (20 pts) (nesting depth added 13). 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":"spark/src/main/scala/org/apache/comet/rules/MakeDateEvaluation.scala"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"0824f44ab35c55b62bf2cda6c8de632f9af285d74f337eab6399becd8bd3d9a6"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold (cognitive 90): datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold has cognitive complexity 90 (threshold 15). Drivers by points: if/else 46 (78 pts), loops 6 (11 pts), boolean chains 1 (nesting depth added 37). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"0187c3e030bd6bfcd2a5cd4589a7f691c14a667beb6b42204cd374dce19fdcd5"}},{"ruleId":"D2","level":"warning","message":{"text":"CometWindowExec.windowExprToProto (cognitive 89): CometWindowExec.windowExprToProto has cognitive complexity 89 (threshold 15). Drivers by points: match/switch 21 (42 pts), if/else 33 (41 pts), boolean chains 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"373e216677f171a05ff11217fab7d4430ab300b0cce49d7c0d452abed9672ecd"}},{"ruleId":"D2","level":"warning","message":{"text":"DirectColumnarToRowConverter.writeColumnFixedWidth (cognitive 75): DirectColumnarToRowConverter.writeColumnFixedWidth has cognitive complexity 75 (threshold 15). Drivers by points: if/else 20 (41 pts), loops 9 (20 pts), boolean chains 9, ternaries 1 (4 pts), match/switch 1 (nesting depth added 35). 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":"spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java"},"region":{"startLine":382}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6e6efb3136c7beb2f3b46b2dae4309a28ffe63ee2016c6ec882734ef8528c1b"}},{"ruleId":"D2","level":"warning","message":{"text":"FixedWidthArrowFieldWriter.copyValues (cognitive 72): FixedWidthArrowFieldWriter.copyValues has cognitive complexity 72 (threshold 15). Drivers by points: if/else 20 (44 pts), loops 6 (18 pts), boolean chains 8, match/switch 2 (nesting depth added 36). 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"15539669979d0c367efee7c0dbcef36ad81c5a597663417ebabd30616a162244"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_list_column_batch (cognitive 71): datafusion_comet_shuffle::spark_unsafe::row::append_list_column_batch has cognitive complexity 71 (threshold 15). Drivers by points: if/else 24 (47 pts), loops 12 (23 pts), match/switch 1 (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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":623}}}],"partialFingerprints":{"codehealthFindingId/v1":"765c597a769dd0c007cac95dd2b8dbfed02ccaf58aeeb838a1360e741e6982bc"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::parse_json_path (cognitive 70): datafusion_comet_spark_expr::string_funcs::get_json_object::parse_json_path has cognitive complexity 70 (threshold 15). Drivers by points: if/else 17 (49 pts), loops 4 (13 pts), match/switch 2 (7 pts), boolean chains 1 (nesting depth added 46). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"70e1e6a6868aa0f020d58eb9574160f8ee334226f1850ae10c0780fc6c34800e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::csv_funcs::to_csv::to_csv_inner (cognitive 64): datafusion_comet_spark_expr::csv_funcs::to_csv::to_csv_inner has cognitive complexity 64 (threshold 15). Drivers by points: if/else 14 (55 pts), boolean chains 5, loops 2 (4 pts) (nesting depth added 43). 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":"native/spark-expr/src/csv_funcs/to_csv.rs"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"4771173c72d0da5222dfa112bd327697bc0c16d61636740212d72b7ded910ed5"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_common::utils::decode_long_or_non_ascii_utf8_spark_lossy (cognitive 58): datafusion_comet_common::utils::decode_long_or_non_ascii_utf8_spark_lossy has cognitive complexity 58 (threshold 15). Drivers by points: if/else 27 (50 pts), boolean chains 7, loops 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":"native/common/src/utils.rs"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"45fcc3b0ca877261108cafc3a8259d18ec155939c8c98b3fcc680da053d1ed23"}},{"ruleId":"D2","level":"warning","message":{"text":"DeltaScanSupport.declineReason (cognitive 55): DeltaScanSupport.declineReason has cognitive complexity 55 (threshold 15). Drivers by points: if/else 39 (44 pts), boolean chains 10, match/switch 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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"31145bcec863e2db18721f132d3b72db92df1bf4357542a11a517d678ae0fa2f"}},{"ruleId":"D2","level":"warning","message":{"text":"AtLeastNNonNulls::evaluate (cognitive 54): AtLeastNNonNulls::evaluate has cognitive complexity 54 (threshold 15). Drivers by points: if/else 19 (37 pts), loops 5 (11 pts), boolean chains 6 (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":"native/spark-expr/src/predicate_funcs/at_least_n_non_nulls.rs"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0fd590c61796e9c445971e8ced058d897a13399ef797bc34591689d29614717"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.transform (cognitive 54): CometExecRule.transform has cognitive complexity 54 (threshold 15). Drivers by points: if/else 24 (37 pts), match/switch 5 (10 pts), boolean chains 7 (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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"d97ddb6cfdf7d0a30d0e8c70a0594894c63e5ed7b4a98ecbc2f10743b97cf04c"}},{"ruleId":"D2","level":"warning","message":{"text":"CometIcebergNativeScan.icebergLiteralToProto (cognitive 54): CometIcebergNativeScan.icebergLiteralToProto has cognitive complexity 54 (threshold 15). Drivers by points: match/switch 11 (32 pts), if/else 17 (21 pts), boolean chains 1 (nesting depth added 25). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own 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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"faaa88679d4100a854a00f35d7435f5474172f4997c9b8d0377f8aba719284e1"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_common::bin::analyze_trace::main (cognitive 53): datafusion_comet_common::bin::analyze_trace::main has cognitive complexity 53 (threshold 15). Drivers by points: if/else 25 (42 pts), match/switch 2 (5 pts), loops 3 (4 pts), boolean chains 2 (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":"native/common/src/bin/analyze_trace.rs"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cee8034f8a6f79f765daa86706bcc58046184157d6674ca632bbdb5ca31cbcd"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::operators::dynamic_filter::early::place (cognitive 50): datafusion_comet::execution::operators::dynamic_filter::early::place has cognitive complexity 50 (threshold 15). Drivers by points: if/else 17 (48 pts), boolean chains 2 (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":"native/core/src/execution/operators/dynamic_filter/early.rs"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e8059a06d1c3c58e1bd0209a9eef8bb51add4df5432beadc2610e1115e212cf"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule._apply (cognitive 50): CometExecRule._apply has cognitive complexity 50 (threshold 15). Drivers by points: if/else 25 (46 pts), match/switch 2 (4 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1107}}}],"partialFingerprints":{"codehealthFindingId/v1":"41a1a60cb6eea95ceebbbf8223839947781f91966ef084fc9724ce2944d2edb2"}},{"ruleId":"D2","level":"warning","message":{"text":"CometBaseAggregate.doConvert (cognitive 50): CometBaseAggregate.doConvert has cognitive complexity 50 (threshold 15). Drivers by points: if/else 24 (35 pts), match/switch 3 (8 pts), boolean chains 7 (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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":2221}}}],"partialFingerprints":{"codehealthFindingId/v1":"2db1efbe5c75606039c26c6b04a3a5c0888f3b121cbd92fd5e79fa8b973f74a7"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::violates_jackson_limits (cognitive 49): datafusion_comet_spark_expr::string_funcs::get_json_object::violates_jackson_limits has cognitive complexity 49 (threshold 15). Drivers by points: if/else 7 (20 pts), boolean chains 12, loops 4 (12 pts), match/switch 2 (5 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":348}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9dbe61f9073f8e674a7ebe7b5aae5b4291d999a668c4698d47b40f913bd4bbf"}},{"ruleId":"D2","level":"warning","message":{"text":"PhysicalPlanner::create_expr (cognitive 47): PhysicalPlanner::create_expr has cognitive complexity 47 (threshold 15). Drivers by points: if/else 18 (40 pts), match/switch 3 (5 pts), boolean chains 2 (nesting depth added 24). 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":"native/core/src/execution/planner.rs"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7e1cf9d8a6282077502991c33dbaffee628ce72ee0480684f710a42aa4ed9cc"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_fork_runs (cognitive 47): check-ci-config.check_fork_runs has cognitive complexity 47 (threshold 15). Drivers by points: if/else 17 (29 pts), ternaries 3 (10 pts), loops 4 (6 pts), boolean chains 2 (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":"dev/ci/check-ci-config.py"},"region":{"startLine":1618}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ef59b1a083ac98abf443fa8bfe25e8bf89c7da43952a4f67460840cdfd99e98"}},{"ruleId":"D2","level":"warning","message":{"text":"DecimalWriter.writeColumnSlice (cognitive 46): DecimalWriter.writeColumnSlice has cognitive complexity 46 (threshold 15). Drivers by points: if/else 11 (27 pts), loops 3 (9 pts), match/switch 2 (6 pts), boolean chains 4 (nesting depth added 26). 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":1293}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ab4a7a1a3ddf76cd62e341ab3c433c093e043c415c2baf8a15fb2bcc59ef499"}},{"ruleId":"D2","level":"warning","message":{"text":"PhysicalPlanner::create_window_expr (cognitive 42): PhysicalPlanner::create_window_expr has cognitive complexity 42 (threshold 15). Drivers by points: match/switch 15 (27 pts), if/else 9 (15 pts) (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":"native/core/src/execution/planner/window.rs"},"region":{"startLine":309}}}],"partialFingerprints":{"codehealthFindingId/v1":"23bc7164322ba72f098e0323130b8948a9f71c659b8a641b55a41539144918d0"}},{"ruleId":"D2","level":"warning","message":{"text":"DirectColumnarToRowConverter.convertRow (cognitive 42): DirectColumnarToRowConverter.convertRow has cognitive complexity 42 (threshold 15). Drivers by points: if/else 19 (37 pts), loops 2, 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":"spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"65621e4813f4bf10717613f8db7bed2d7c12cdce0d47d8637359940b0239e1b9"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornShufflePartitionPusher.pushClaimedPartitionData (cognitive 41): CelebornShufflePartitionPusher.pushClaimedPartitionData has cognitive complexity 41 (threshold 15). Drivers by points: if/else 21 (31 pts), error handling 5 (6 pts), boolean chains 3, ternaries 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":532}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ae098b983789661cbd7c67564b837b864db886dae165c21bddeb9e31ef80b1f"}},{"ruleId":"D2","level":"warning","message":{"text":"PhysicalPlanner::create_plan (cognitive 40): PhysicalPlanner::create_plan has cognitive complexity 40 (threshold 15). Drivers by points: if/else 18 (29 pts), match/switch 4 (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":"native/core/src/execution/planner.rs"},"region":{"startLine":1643}}}],"partialFingerprints":{"codehealthFindingId/v1":"12e5101ad4dadc2d4d80b04a5d43b21658b2f3e7c249a3539de08a52ac87a4a2"}},{"ruleId":"D2","level":"warning","message":{"text":"CometShuffleExchangeExec.nativeShuffleFailureReasons (cognitive 39): CometShuffleExchangeExec.nativeShuffleFailureReasons has cognitive complexity 39 (threshold 15). Drivers by points: if/else 12 (24 pts), loops 5 (9 pts), match/switch 3 (4 pts), boolean chains 2 (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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b37a55da8657b0b43d51d1750d7236a9669d4b66147d632ba822874473653ab"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string (cognitive 38): datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string has cognitive complexity 38 (threshold 15). Drivers by points: if/else 10 (22 pts), match/switch 5 (9 pts), boolean chains 6, 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":898}}}],"partialFingerprints":{"codehealthFindingId/v1":"98fe8efb7059bed763f0289c0c76d0374e16c1fd2f597f21fdf35823998576fd"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornRawPartitionReader.openPartitions (cognitive 37): CelebornRawPartitionReader.openPartitions has cognitive complexity 37 (threshold 15). Drivers by points: if/else 22 (29 pts), boolean chains 3, error handling 1 (3 pts), loops 2 (nesting depth added 9). 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.scala"},"region":{"startLine":375}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff9b2bf32e9d376666cf6479c98dd4ceea1e692e9479d89108e718bf5b87ae3e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::append_spark_variant (cognitive 36): datafusion_comet::parquet::cast_column::variant::append_spark_variant has cognitive complexity 36 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 4 (12 pts), match/switch 3 (5 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":870}}}],"partialFingerprints":{"codehealthFindingId/v1":"1aa4c4b07f1f06546c37a0927ea826d20840730aac0b2d0f3e76c278d2af7cfd"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornShufflePartitionPusher.\u003Cinit\u003E (cognitive 36): CelebornShufflePartitionPusher.\u003Cinit\u003E has cognitive complexity 36 (threshold 15). Drivers by points: if/else 18 (20 pts), error handling 7 (8 pts), boolean chains 5, loops 1 (2 pts), ternaries 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"13c34dfbe17e346a40a2ea59f5ef166293b0a231da0adcd3adb9c12cb21af74e"}},{"ruleId":"D2","level":"warning","message":{"text":"RssPartitionWriter::push_batch_within_limit (cognitive 35): RssPartitionWriter::push_batch_within_limit has cognitive complexity 35 (threshold 15). Drivers by points: if/else 13 (26 pts), match/switch 3 (6 pts), boolean chains 2, 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"c14c1d177bd2ca3f4a21c0eaad0282d7e5ea6d2f29673d60fec6fd0afc408a52"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::append_map_column_batch (cognitive 35): datafusion_comet_shuffle::spark_unsafe::row::append_map_column_batch has cognitive complexity 35 (threshold 15). Drivers by points: if/else 12 (23 pts), loops 6 (11 pts), match/switch 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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":714}}}],"partialFingerprints":{"codehealthFindingId/v1":"b16c2808c9f286505885b0fa065a89e4a92f0c67afc44a0d45d7ebb26fe0fd18"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_list_generic (cognitive 35): datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_list_generic has cognitive complexity 35 (threshold 15). Drivers by points: if/else 15 (29 pts), boolean chains 3, loops 2 (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":"native/spark-expr/src/array_funcs/arrays_overlap.rs"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"71cb3ace748adb550ef3742506876260d6225d4d7ae4112bbbc518e2f504f808"}},{"ruleId":"D2","level":"warning","message":{"text":"CometNativeExec.buildNativeContext (cognitive 35): CometNativeExec.buildNativeContext has cognitive complexity 35 (threshold 15). Drivers by points: if/else 16 (18 pts), match/switch 12 (13 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":991}}}],"partialFingerprints":{"codehealthFindingId/v1":"15caaa830007e6d9f3cc743478dfd27fed75205511447ef77a9ed26cd9b24bc1"}},{"ruleId":"D2","level":"warning","message":{"text":"generate-versions.strip_conditional_blocks (cognitive 35): generate-versions.strip_conditional_blocks has cognitive complexity 35 (threshold 15). Drivers by points: if/else 8 (23 pts), loops 3 (6 pts), ternaries 1 (5 pts), boolean chains 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":"docs/generate-versions.py"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"89103ffc5750812a4eae961d02e993cf070b5789419bc9a0d60ee2ba4e3bcabb"}},{"ruleId":"D2","level":"warning","message":{"text":"CollectListGroupsAccumulator::evaluate (cognitive 34): CollectListGroupsAccumulator::evaluate has cognitive complexity 34 (threshold 15). Drivers by points: loops 7 (18 pts), if/else 6 (14 pts), match/switch 2 (nesting depth added 19). 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":"native/spark-expr/src/agg_funcs/collect.rs"},"region":{"startLine":359}}}],"partialFingerprints":{"codehealthFindingId/v1":"5db6b3d017c9a3045a221a999198799612f86a48d93e927fa8f6ca9779c4f460"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::datetime_funcs::to_time::string_to_time (cognitive 34): datafusion_comet_spark_expr::datetime_funcs::to_time::string_to_time has cognitive complexity 34 (threshold 15). Drivers by points: if/else 20 (28 pts), boolean chains 6 (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":"native/spark-expr/src/datetime_funcs/to_time.rs"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a19a4fbdaa3adb187ed372dd80b1a9751adbda362c1cc84491ca19738440c75"}},{"ruleId":"D2","level":"warning","message":{"text":"CometHashJoin.doConvert (cognitive 34): CometHashJoin.doConvert has cognitive complexity 34 (threshold 15). Drivers by points: if/else 18 (21 pts), boolean chains 10, match/switch 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":2861}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce69f9d0b00c751441443cda8c1c04df8369bfe4cddb3344eb1f6de6e3928d37"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::json_funcs::from_json::append_field_value (cognitive 33): datafusion_comet_spark_expr::json_funcs::from_json::append_field_value has cognitive complexity 33 (threshold 15). Drivers by points: if/else 16 (25 pts), match/switch 3 (4 pts), loops 1 (3 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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb7e7a7400ed14cf6bbd10754eb76ce8927b26c919ee3c28817fe300933613bd"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance (cognitive 33): datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance has cognitive complexity 33 (threshold 15). Drivers by points: if/else 13 (21 pts), loops 6 (11 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed8c0465f5f904a293b6f35688042260307d934669266efdbf80bb766ce39789"}},{"ruleId":"D2","level":"warning","message":{"text":"check-iceberg-shards.verify_manifests (cognitive 33): check-iceberg-shards.verify_manifests has cognitive complexity 33 (threshold 15). Drivers by points: if/else 12 (23 pts), loops 4 (6 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":"dev/ci/check-iceberg-shards.py"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d6f59e638b569e54fd871be7555f70e65ad2aa6d4b3614e529a9a6eac2c3511"}},{"ruleId":"D2","level":"warning","message":{"text":"RssPartitionWriter::compact_array (cognitive 32): RssPartitionWriter::compact_array has cognitive complexity 32 (threshold 15). Drivers by points: if/else 15 (25 pts), boolean chains 6, 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":926}}}],"partialFingerprints":{"codehealthFindingId/v1":"d121ac94d8abd7b5be94e1738f18df3ce054ee75f6ecc4402953bc723635d54a"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::list::append_to_builder (cognitive 32): datafusion_comet_shuffle::spark_unsafe::list::append_to_builder has cognitive complexity 32 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 6 (12 pts), boolean chains 4, match/switch 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":"native/shuffle/src/spark_unsafe/list.rs"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"22d287c120884f0f81e35686b431a73a519a809f85d5b39a3dcd91b55d120c77"}},{"ruleId":"D2","level":"warning","message":{"text":"SegmentVisitor::visit_seq (cognitive 32): SegmentVisitor::visit_seq has cognitive complexity 32 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 4 (10 pts), match/switch 5 (10 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":768}}}],"partialFingerprints":{"codehealthFindingId/v1":"032969b8e6a1d75f13e61422a5883e4d1ff536085167f96722e1d2b7bc21c5df"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::get_json_object::spark_get_json_object_impl (cognitive 32): datafusion_comet_spark_expr::string_funcs::get_json_object::spark_get_json_object_impl has cognitive complexity 32 (threshold 15). Drivers by points: match/switch 9 (18 pts), if/else 5 (9 pts), loops 2 (4 pts), boolean chains 1 (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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c546fe6f4e823d0eff482fdfeea0f0fd3fd6a0ebadd7c3b3e2aaf83d3b79c84"}},{"ruleId":"D2","level":"warning","message":{"text":"CometMakeDate.unsupportedParentReason (cognitive 32): CometMakeDate.unsupportedParentReason has cognitive complexity 32 (threshold 15). Drivers by points: if/else 12 (26 pts), match/switch 1 (3 pts), boolean chains 2, 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":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":470}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cf13220eabaea1ad7f48452c1b28bf7bc3a8e2e24b0a899b978a44ed0826709"}},{"ruleId":"D2","level":"warning","message":{"text":"ComparisonUtils.staticFloatingInList (cognitive 32): ComparisonUtils.staticFloatingInList has cognitive complexity 32 (threshold 15). Drivers by points: if/else 15 (19 pts), match/switch 5 (9 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":"spark/src/main/scala/org/apache/comet/serde/predicates.scala"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"93499ba6be3c6adc964bd9630efcac61732b4fc7f8aea36e40eb48d1d20d46e8"}},{"ruleId":"D2","level":"warning","message":{"text":"FuzzDataGenerator.generateColumn (cognitive 32): FuzzDataGenerator.generateColumn has cognitive complexity 32 (threshold 15). Drivers by points: match/switch 10 (19 pts), if/else 8 (10 pts), loops 1 (2 pts), boolean chains 1 (nesting depth added 12). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own 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":"spark/src/main/scala/org/apache/comet/testing/FuzzDataGenerator.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"190698eed58dfc5bada3456cffbcf2bede8144f5b17b2727bf98e82ccb8712bb"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_event_policy (cognitive 32): check-ci-config.check_event_policy has cognitive complexity 32 (threshold 15). Drivers by points: if/else 11 (25 pts), boolean chains 4, loops 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":"dev/ci/check-ci-config.py"},"region":{"startLine":785}}}],"partialFingerprints":{"codehealthFindingId/v1":"670041e98ac4dd04c14aae2d74d1fa8d186784a0dd99f95ce58f885874db2202"}},{"ruleId":"D2","level":"warning","message":{"text":"PhysicalPlanner::create_binary_expr_with_options (cognitive 31): PhysicalPlanner::create_binary_expr_with_options has cognitive complexity 31 (threshold 15). Drivers by points: if/else 10 (16 pts), match/switch 4 (8 pts), boolean chains 7 (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":"native/core/src/execution/planner.rs"},"region":{"startLine":1391}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab3dff3bbec1caa26500bfe3a0332d9419d716808865b72d9c05f6bf43473d09"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_insert::array_insert (cognitive 31): datafusion_comet_spark_expr::array_funcs::array_insert::array_insert has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (29 pts), loops 1, match/switch 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":"native/spark-expr/src/array_funcs/array_insert.rs"},"region":{"startLine":203}}}],"partialFingerprints":{"codehealthFindingId/v1":"508bc88da4c707adbae8a8bef898eca8b51c0c0ddd05081c40c0b94827bec00f"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner (cognitive 31): datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner has cognitive complexity 31 (threshold 15). Drivers by points: if/else 9 (19 pts), loops 4 (6 pts), match/switch 3 (6 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":"native/spark-expr/src/array_funcs/arrays_zip.rs"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1e89f2fcfd2b890d99152b5c18b91ea40aa45b833b1dbeb950bf9a468945b17"}},{"ruleId":"D2","level":"warning","message":{"text":"GenerateDocs.generateConfigReference (cognitive 31): GenerateDocs.generateConfigReference has cognitive complexity 31 (threshold 15). Drivers by points: loops 4 (13 pts), match/switch 3 (10 pts), if/else 4 (8 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":"spark/src/main/scala/org/apache/comet/GenerateDocs.scala"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"3480aa8198948b3cc36c21855e342b399f0fb7a751b52f1d8033a5b97a286653"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornShufflePartitionPusher.reconcileAcceptedPushes (cognitive 31): CelebornShufflePartitionPusher.reconcileAcceptedPushes has cognitive complexity 31 (threshold 15). Drivers by points: if/else 9 (17 pts), boolean chains 7, loops 4 (5 pts), ternaries 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"48752b851cd9238227fe83768d1544b25920e3aaa64100cce3a48f78c0da6e94"}},{"ruleId":"D2","level":"warning","message":{"text":"EagerPageIndexReader::get_metadata (cognitive 30): EagerPageIndexReader::get_metadata has cognitive complexity 30 (threshold 15). Drivers by points: if/else 14 (19 pts), match/switch 4 (6 pts), boolean chains 5 (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":"native/core/src/parquet/eager_page_index_reader_factory.rs"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2626b0046de1000f0b83741d1dad2069a876314c78f1c6051657a40d0085157"}},{"ruleId":"D2","level":"warning","message":{"text":"GenerateDocs.renderExpressionCompatNotes (cognitive 30): GenerateDocs.renderExpressionCompatNotes has cognitive complexity 30 (threshold 15). Drivers by points: if/else 10 (19 pts), loops 4 (10 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":"spark/src/main/scala/org/apache/comet/GenerateDocs.scala"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"b80bdbec5188d6af9c5c1f2a7e8916c7012acea7e3b8aec1822aabcd5ac14269"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::rewrite_residual_values (cognitive 29): datafusion_comet::parquet::cast_column::variant::rewrite_residual_values has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (25 pts), boolean chains 3, 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":314}}}],"partialFingerprints":{"codehealthFindingId/v1":"431599da0b8751acd650cb74b50428cc320d05ced48d39ca51969d02cd6ea5b7"}},{"ruleId":"D2","level":"warning","message":{"text":"CheckOverflow::evaluate (cognitive 29): CheckOverflow::evaluate has cognitive complexity 29 (threshold 15). Drivers by points: if/else 12 (22 pts), match/switch 3 (6 pts), boolean chains 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":"native/spark-expr/src/math_funcs/internal/checkoverflow.rs"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c88771ba9a3426a2a959c70320631901d0243c171d8031e00190b462da05860"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::date_parser (cognitive 29): datafusion_comet_spark_expr::conversion_funcs::string::date_parser has cognitive complexity 29 (threshold 15). Drivers by points: if/else 16 (20 pts), boolean chains 8, loops 1 (nesting depth added 4). Of this number, 22 points are the body\u0027s own statements and 7 belong to 3 function items 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":2322}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4cfa22c4c2112e17093f95d489ca7863a3470f625cffe9d175215267b30787a"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::json_funcs::to_json::struct_to_json (cognitive 29): datafusion_comet_spark_expr::json_funcs::to_json::struct_to_json has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (22 pts), loops 2 (4 pts), boolean chains 2, match/switch 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":"native/spark-expr/src/json_funcs/to_json.rs"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d36674b324c525b0b017900831c4e872de29db1a3e2dd4f05c441476377139b"}},{"ruleId":"D2","level":"warning","message":{"text":"CometShuffleExchangeExec.columnarShuffleFailureReasons (cognitive 29): CometShuffleExchangeExec.columnarShuffleFailureReasons has cognitive complexity 29 (threshold 15). Drivers by points: if/else 9 (18 pts), loops 5 (9 pts), boolean chains 1, match/switch 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":749}}}],"partialFingerprints":{"codehealthFindingId/v1":"97364db7817e72c1a83d10fb0e0b1d5440572fd2c1eaa2fd5a55a872fb903cd8"}},{"ruleId":"D2","level":"warning","message":{"text":"WideDecimalBinaryExpr::evaluate (cognitive 28): WideDecimalBinaryExpr::evaluate has cognitive complexity 28 (threshold 15). Drivers by points: if/else 18 (24 pts), match/switch 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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"b39f2dca93cca6073beff585485635178f5bbe064c1735b1c3243aa98f5d7aa9"}},{"ruleId":"D2","level":"warning","message":{"text":"CometScanRule.validateIcebergFileScanTasks (cognitive 28): CometScanRule.validateIcebergFileScanTasks has cognitive complexity 28 (threshold 15). Drivers by points: if/else 14 (22 pts), error handling 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":1545}}}],"partialFingerprints":{"codehealthFindingId/v1":"5415363ba4bdc9563fba7eac2e1a1a05074c83653560c5c1df14e52a4d1c84f8"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_required_checks (cognitive 28): check-ci-config.check_required_checks has cognitive complexity 28 (threshold 15). Drivers by points: if/else 12 (25 pts), boolean chains 2, loops 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1124}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbbcc61e1cad8768414c4f4a080f1624770a8e3a1cddeb538b62c3dacff68949"}},{"ruleId":"D2","level":"warning","message":{"text":"RankLimitStream::process_batch (cognitive 27): RankLimitStream::process_batch has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (24 pts), 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":"native/operators/src/rank_limit.rs"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"66b71c44eb5cf3a24b51392eb1d371826eb128b455cf0dc06560b3ff163a71d4"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::div::spark_decimal_div_internal (cognitive 27): datafusion_comet_spark_expr::math_funcs::div::spark_decimal_div_internal has cognitive complexity 27 (threshold 15). Drivers by points: if/else 15 (21 pts), boolean chains 5, 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":"native/spark-expr/src/math_funcs/div.rs"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e35c4e79ad00ba13d890561cb427b264a67e9ce929510b0cbc6884bc57c348b"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornShuffleGenerationCoordinator.claimMapAttempt (cognitive 27): CelebornShuffleGenerationCoordinator.claimMapAttempt has cognitive complexity 27 (threshold 15). Drivers by points: if/else 9 (18 pts), boolean chains 7, 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"d2fac400a7a499afffe3628f931f3876e6762bcf8c9df52ebae3b2b1751f1f83"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::canonicalize_spark_empty_key_metadata (cognitive 26): datafusion_comet::parquet::cast_column::variant::canonicalize_spark_empty_key_metadata has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (23 pts), boolean chains 2, 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":679}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5726396e7e9509435679a5ebce2144fa71d4dfae5657962d0ccdaee79d67d4c"}},{"ruleId":"D2","level":"warning","message":{"text":"CometBatchKernelCodegenOutput.emitWrite (cognitive 26): CometBatchKernelCodegenOutput.emitWrite has cognitive complexity 26 (threshold 15). Drivers by points: if/else 17 (25 pts), 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenOutput.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"a83683d622e51e6486511c11e07b8fb30299242df41bd35420c84c351703eafa"}},{"ruleId":"D2","level":"warning","message":{"text":"Scanner.parseCountedQuantifier (cognitive 26): Scanner.parseCountedQuantifier has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (19 pts), match/switch 3 (5 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":"spark/src/main/scala/org/apache/comet/expressions/CometRegex.scala"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"157662684a4f173cc0142e1a17abefb4fcbf7b36edf9e98e16e0b8ca59b8f994"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.limitCollectProjectionInput (cognitive 26): CometExecRule.limitCollectProjectionInput has cognitive complexity 26 (threshold 15). Drivers by points: match/switch 5 (11 pts), if/else 7 (9 pts), loops 2 (5 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"840560fe8f24e64e893fc5cf0db5f719778ee8f72ff2859c46ba009242d72468"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.tagUnsafePartialAggregates (cognitive 26): CometExecRule.tagUnsafePartialAggregates has cognitive complexity 26 (threshold 15). Drivers by points: if/else 11 (22 pts), boolean chains 3, 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1908}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d4ac30812d440307ffcf3eb7e53ae8d6edebe5fd9c2f897a7d27c246e59ff17"}},{"ruleId":"D2","level":"warning","message":{"text":"Utils.coalesceBroadcastBatches (cognitive 26): Utils.coalesceBroadcastBatches has cognitive complexity 26 (threshold 15). Drivers by points: if/else 9 (19 pts), error handling 1 (3 pts), loops 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":"spark/src/main/scala/org/apache/spark/sql/comet/util/Utils.scala"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9b96a00a7b95411a1282e1799d855f7300162a2ac98ea3430f02ced235d2a86"}},{"ruleId":"D2","level":"warning","message":{"text":"CometArrowPythonRunnerBase.inputBatchRanges (cognitive 26): CometArrowPythonRunnerBase.inputBatchRanges has cognitive complexity 26 (threshold 15). Drivers by points: if/else 11 (16 pts), loops 3 (5 pts), boolean chains 4, 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":"spark/src/main/spark-4.x/org/apache/spark/sql/execution/python/CometArrowPythonRunnerBase.scala"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"38e4f4cf8d19c9fbcb79423fa25ced65e5d0ca3cd9e62e6d7b5125c8c21ded92"}},{"ruleId":"D2","level":"warning","message":{"text":"MergeConfig::validate (cognitive 25): MergeConfig::validate has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (15 pts), loops 3 (6 pts), match/switch 1 (3 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":"native/core/src/execution/operators/merge_rows.rs"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"93a336bf3aea9c754076fc13bc39e8f12500ad27f4699b76b84382be07ebb40f"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::operators::dynamic_filter::parquet_reader::try_attach_parquet_reader_filter (cognitive 25): datafusion_comet::execution::operators::dynamic_filter::parquet_reader::try_attach_parquet_reader_filter has cognitive complexity 25 (threshold 15). Drivers by points: if/else 15 (20 pts), match/switch 2 (3 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":"native/core/src/execution/operators/dynamic_filter/parquet_reader.rs"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3ad3f1a93c154b5dec3a052cd1a365f14d69b2cd81ece3c2cfd60306bb8e61e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::schema_adapter::spark_has_updater (cognitive 25): datafusion_comet::parquet::schema_adapter::spark_has_updater has cognitive complexity 25 (threshold 15). Drivers by points: if/else 12 (17 pts), boolean chains 5, match/switch 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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"be2918e8982547d28803c3d94aba1418fc687391044c81911f170ccba4e0a430"}},{"ruleId":"D2","level":"warning","message":{"text":"ExtendedExplainInfo.generateTreeString (cognitive 25): ExtendedExplainInfo.generateTreeString has cognitive complexity 25 (threshold 15). Drivers by points: if/else 14 (16 pts), match/switch 5 (8 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":"spark/src/main/scala/org/apache/comet/ExtendedExplainInfo.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef7e70f03e7c9468235e2f9e80c093fca880b89ab01a8dbe53ae4a220f2dde4b"}},{"ruleId":"D2","level":"warning","message":{"text":"Lz4FrameCompressionCodec.doDecompress (cognitive 25): Lz4FrameCompressionCodec.doDecompress has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9 (18 pts), error handling 2 (5 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/Lz4FrameCompressionCodec.scala"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"013c3032370c56ef89e89563fa84139b5db516f46a4ef01d5208c733b72a4908"}},{"ruleId":"D2","level":"warning","message":{"text":"HashAggBuilder::build (cognitive 24): HashAggBuilder::build has cognitive complexity 24 (threshold 15). Drivers by points: if/else 16 (19 pts), boolean chains 4, 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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb89a8b4e30a30e7fce416f3f08f99aedd4c2330af13d523901fd15c98970ee2"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conditional_funcs::case_when::merge_bytes (cognitive 24): datafusion_comet_spark_expr::conditional_funcs::case_when::merge_bytes has cognitive complexity 24 (threshold 15). Drivers by points: loops 5 (11 pts), if/else 4 (7 pts), match/switch 2 (5 pts), boolean chains 1 (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":"native/spark-expr/src/conditional_funcs/case_when.rs"},"region":{"startLine":796}}}],"partialFingerprints":{"codehealthFindingId/v1":"df0df70b077313aff35ef8bd2b29d1f46ab89908855d3e42cb1f4f8425e360b9"}},{"ruleId":"D2","level":"warning","message":{"text":"DeltaScanSupport.attributesUnusedAbove (cognitive 24): DeltaScanSupport.attributesUnusedAbove has cognitive complexity 24 (threshold 15). Drivers by points: match/switch 5 (10 pts), if/else 7 (9 pts), boolean chains 4, 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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":1968}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c1f76b3c3a2bb555e2b1c7ccc6ac3a351120c5e5525bc92986c550c801dab18"}},{"ruleId":"D2","level":"warning","message":{"text":"QueryPlanSerde.aggExprToProto (cognitive 24): QueryPlanSerde.aggExprToProto has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (20 pts), match/switch 2 (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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":807}}}],"partialFingerprints":{"codehealthFindingId/v1":"d33ce9f11b10665330aa563d258be7df8ded69ce27978f8f7f229b71fe3d898b"}},{"ruleId":"D2","level":"warning","message":{"text":"CometIcebergNativeScan.icebergExprToProto (cognitive 24): CometIcebergNativeScan.icebergExprToProto has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (15 pts), match/switch 3 (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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":920}}}],"partialFingerprints":{"codehealthFindingId/v1":"476a9ef2b76bc9e384554cfe7899f2bea9e51a65090ce5cea4f7e88a83f50f60"}},{"ruleId":"D2","level":"warning","message":{"text":"ShimSparkErrorConverter.convertErrorType (cognitive 24): ShimSparkErrorConverter.convertErrorType has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (21 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":"spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bca5e08db596f6e5c50cf5df8d7db3490c6c70d376ea9b84574431d9fc9aaf5"}},{"ruleId":"D2","level":"warning","message":{"text":"generate-changelog.generate_changelog (cognitive 24): generate-changelog.generate_changelog has cognitive complexity 24 (threshold 15). Drivers by points: if/else 5 (10 pts), loops 7 (9 pts), boolean chains 5 (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/release/generate-changelog.py"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"28c740094639dde464b21ca00c11c451c2fa32915ddcca91dc5e4c748e8aff55"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::delta_dv::build_access_plan (cognitive 23): datafusion_comet::execution::delta_dv::build_access_plan has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (16 pts), loops 2 (3 pts), match/switch 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":"native/core/src/execution/delta_dv.rs"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"209642b57d2451c938b7a518cfe29256bf4b71b31150360aa6ea24153dc5d1d0"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::planner::literal_to_array_ref (cognitive 23): datafusion_comet::execution::planner::literal_to_array_ref has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (15 pts), loops 3 (6 pts), boolean chains 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":"native/core/src/execution/planner.rs"},"region":{"startLine":2803}}}],"partialFingerprints":{"codehealthFindingId/v1":"52648f7d1c312269f91dc15cc6c6f5673fea048f242ce0edcad0090ed39cb047"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.revertUnsafePartialAggregates (cognitive 23): CometExecRule.revertUnsafePartialAggregates has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (16 pts), boolean chains 5, match/switch 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1991}}}],"partialFingerprints":{"codehealthFindingId/v1":"80d5ca44e11f1225533409d94262d908c7483b520c6a091ca5c56d14bdbc54c8"}},{"ruleId":"D2","level":"warning","message":{"text":"CometNativeShuffleWriter.writeInternal (cognitive 23): CometNativeShuffleWriter.writeInternal has cognitive complexity 23 (threshold 15). Drivers by points: if/else 12 (16 pts), match/switch 3, 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a67e2a71ffd7cda97783a84e2d01452a7fe086889f52eca4db83b2402c4346a"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::planner::parse_file_scan_tasks_from_common (cognitive 22): datafusion_comet::execution::planner::parse_file_scan_tasks_from_common has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (13 pts), match/switch 4 (6 pts), loops 2 (3 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":"native/core/src/execution/planner.rs"},"region":{"startLine":2419}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee331e42465507643d9f08aba7e4b317f8761b7ebe15a42f4b7395758156cf65"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::bin::shuffle_bench::main (cognitive 22): datafusion_comet_shuffle::bin::shuffle_bench::main has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (21 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":"native/shuffle/src/bin/shuffle_bench.rs"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4353c67a3ed7dc9f2591b93a6960c24037d9547a3333a46ce60bee3df310fd8"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::parse_sign_offset (cognitive 22): datafusion_comet_spark_expr::conversion_funcs::string::parse_sign_offset has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (12 pts), boolean chains 7, 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1691}}}],"partialFingerprints":{"codehealthFindingId/v1":"892d9453cdbd8fc21f324081c1533dc1292618d5c191081aa9950e03dd80784c"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_upstream (cognitive 22): datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_upstream has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (13 pts), match/switch 3 (6 pts), boolean chains 2, loops 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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":1109}}}],"partialFingerprints":{"codehealthFindingId/v1":"45a24a2a0ac624fcbc43059d6b1cba0a93c16fa77581c3781eff8fde28dca9b1"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::split::push_split_parts (cognitive 22): datafusion_comet_spark_expr::string_funcs::split::push_split_parts has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 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":"native/spark-expr/src/string_funcs/split.rs"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"531fa4d4482ec6f87b35eaeae7eb305e1c79b37987f8e7986653c61e76d48394"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::unbase64::decode (cognitive 22): datafusion_comet_spark_expr::string_funcs::unbase64::decode has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (18 pts), loops 2, boolean chains 1, match/switch 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":"native/spark-expr/src/string_funcs/unbase64.rs"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"c072a1ca28d8329f386fcacd36f4ab89d7c859ae0d5bac0510d9ab5db5819106"}},{"ruleId":"D2","level":"warning","message":{"text":"Scanner.parseClass (cognitive 22): Scanner.parseClass has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (9 pts), boolean chains 6, match/switch 2 (6 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":"spark/src/main/scala/org/apache/comet/expressions/CometRegex.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"edc87281431c8285ba42ec5b88db058e131e82f0b30456bcd5729ae7a71a2c0b"}},{"ruleId":"D2","level":"warning","message":{"text":"MakeDateEvaluation.eagerReferences (cognitive 22): MakeDateEvaluation.eagerReferences has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (19 pts), 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":"spark/src/main/scala/org/apache/comet/rules/MakeDateEvaluation.scala"},"region":{"startLine":133}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f577726785a6d7e3f114b5458f93129f83ba9ed9e06241c623a9576493b909c"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowFieldWriter.writeDictionaryVariableWidth (cognitive 22): ArrowFieldWriter.writeDictionaryVariableWidth 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, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":527}}}],"partialFingerprints":{"codehealthFindingId/v1":"af8f8ee6cad47cec8c5283ba54b7221d6e92f6b01a86ecccdbf65720eb56f606"}},{"ruleId":"D2","level":"warning","message":{"text":"Projection.load (cognitive 22): Projection.load has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13 (15 pts), error handling 2 (3 pts), boolean chains 2, loops 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8165ad256a3ac15d9a6d40c7ab9d1bcc73d801be7be20b97f000b3ef31f4883"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::parquet_support::parquet_convert_array_impl (cognitive 21): datafusion_comet::parquet::parquet_support::parquet_convert_array_impl has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (14 pts), match/switch 3 (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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"cea952d9ee6637caac251b1cb34e8ad7ce74ebc0372b5a2d7780b5fc6a094169"}},{"ruleId":"D2","level":"warning","message":{"text":"SumDecimalGroupsAccumulator::merge_batch (cognitive 21): SumDecimalGroupsAccumulator::merge_batch has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 4, 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":"native/spark-expr/src/agg_funcs/sum_decimal.rs"},"region":{"startLine":544}}}],"partialFingerprints":{"codehealthFindingId/v1":"16eb330f1054f7c1709e86aae1bbbca3e3089d909f8583800bc976ed8d9fc962"}},{"ruleId":"D2","level":"warning","message":{"text":"CaseWhenExpr::evaluate_eagerly (cognitive 21): CaseWhenExpr::evaluate_eagerly has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (14 pts), match/switch 2 (5 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":"native/spark-expr/src/conditional_funcs/case_when.rs"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1db24d5cf62f0a9b0aedcdc3755b7d61d8b3fba0885f6c0ff56911e4d5e988a"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein (cognitive 21): datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein has cognitive complexity 21 (threshold 15). Drivers by points: match/switch 8 (17 pts), if/else 2 (4 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"61c26046c0d4575122b876260eab308cc178b27fd20176b7caf1f0410c183ead"}},{"ruleId":"D2","level":"warning","message":{"text":"CometCast.isSupported (cognitive 21): CometCast.isSupported has cognitive complexity 21 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 5, match/switch 2 (3 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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca84588052133e52befdb6803eebd0e05ca0ad9d87a59b38205a6c7ff96fa173"}},{"ruleId":"D2","level":"warning","message":{"text":"IcebergReflection.resolveFooterReadOptions (cognitive 21): IcebergReflection.resolveFooterReadOptions has cognitive complexity 21 (threshold 15). Drivers by points: loops 6 (21 pts) (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":"spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala"},"region":{"startLine":2291}}}],"partialFingerprints":{"codehealthFindingId/v1":"77182fccb927f023d7eb997e282859d55a5251245be210f68f4ecdc9d29d3eda"}},{"ruleId":"D2","level":"warning","message":{"text":"QueryPlanSerde.serializeDataType (cognitive 21): QueryPlanSerde.serializeDataType has cognitive complexity 21 (threshold 15). Drivers by points: if/else 11 (18 pts), match/switch 2, 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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":646}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6671e288180d87c79f438cafe97e446a9f5418a6a24e56347cb6c60b3d9dfc6"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowFieldWriter.writeValidity (cognitive 21): ArrowFieldWriter.writeValidity has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (17 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bd893ed894eee34204c979e033f3081c1c3932dc4152f2db14733d3af5f19d9"}},{"ruleId":"D2","level":"warning","message":{"text":"ShimSparkErrorConverter.convertErrorType (cognitive 21): ShimSparkErrorConverter.convertErrorType has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (18 pts), 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"150d4ef5b0c054a974017124ea1c7d47ffcc9c1a22115099974c7265be4e6e21"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.asf_required_contexts (cognitive 21): check-ci-config.asf_required_contexts has cognitive complexity 21 (threshold 15). Drivers by points: if/else 10 (19 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1065}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d73bf9bd6684c5b2adc6894dad9bc83e26a78dfa3092be7694fd805d164ba1f"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_cache_save_scope (cognitive 21): check-ci-config.check_cache_save_scope has cognitive complexity 21 (threshold 15). Drivers by points: if/else 4 (13 pts), loops 4 (7 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1532}}}],"partialFingerprints":{"codehealthFindingId/v1":"96e28f99897a54945402b9349c55820a4a8730a02608243b08716ad6112a002d"}},{"ruleId":"D2","level":"warning","message":{"text":"summarize-iceberg-writes.summarize (cognitive 21): summarize-iceberg-writes.summarize has cognitive complexity 21 (threshold 15). Drivers by points: if/else 8 (10 pts), loops 6 (10 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/ci/summarize-iceberg-writes.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"dcaf7ab18911f48f5870c7773731b06a5d66ea179ec888c7b6145f745a54d8db"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::extend_shredded_metadata (cognitive 20): datafusion_comet::parquet::cast_column::variant::extend_shredded_metadata has cognitive complexity 20 (threshold 15). Drivers by points: if/else 9 (17 pts), loops 2, match/switch 1 (nesting depth added 8). Of this number, 13 points are the body\u0027s own statements and 7 belong to one function item inside it that branches. To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":604}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1c3959b0b86ac2e49817f15add68aa4fd9150b574ebb7f0a23b5fe41282608a"}},{"ruleId":"D2","level":"warning","message":{"text":"CometBatchKernelCodegenInput.emitTypedGetters (cognitive 20): CometBatchKernelCodegenInput.emitTypedGetters has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 13 (15 pts), if/else 3, boolean chains 2 (nesting depth added 2). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"e62897d80e111bccbfe2796cb1106b9b6c87bef0f52fc8ee094babb61fddd7a9"}},{"ruleId":"D2","level":"warning","message":{"text":"CometBatchKernelCodegenInput.emitStructScalarGetters (cognitive 20): CometBatchKernelCodegenInput.emitStructScalarGetters has cognitive complexity 20 (threshold 15). Drivers by points: match/switch 12, if/else 5 (6 pts), boolean chains 2 (nesting depth added 1). To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own 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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":868}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3c1a9cdde9d13ae6bd3de2484fe9c6b65a584cf8eeddc0b07ba3d20e393dfd6"}},{"ruleId":"D2","level":"warning","message":{"text":"CometIcebergNativeScan.hdfsEncryptionZoneFallback (cognitive 20): CometIcebergNativeScan.hdfsEncryptionZoneFallback has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (10 pts), boolean chains 3, loops 1 (3 pts), match/switch 3, error handling 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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":804}}}],"partialFingerprints":{"codehealthFindingId/v1":"639fb50f8f0c774b592867236154b3f8f8bf4a6e833920a09bc666f74f2edc4f"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::operators::merge_rows::run_group (cognitive 19): datafusion_comet::execution::operators::merge_rows::run_group has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (13 pts), loops 2 (3 pts), match/switch 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":"native/core/src/execution/operators/merge_rows.rs"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"995a4fe02f2dc16a3f3aa5edb3bf9aba27c119358e0d779f3b4c76b1e9f936f8"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::planner::literal::literal_to_scalar (cognitive 19): datafusion_comet::execution::planner::literal::literal_to_scalar has cognitive complexity 19 (threshold 15). Drivers by points: match/switch 5 (13 pts), if/else 4 (6 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":"native/core/src/execution/planner/literal.rs"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"b69a6ed12fd51709facd53e85a72adf2264efec2a56ffac60c2a203726092444"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::cast_column::variant::rewrite_shredding_state (cognitive 19): datafusion_comet::parquet::cast_column::variant::rewrite_shredding_state has cognitive complexity 19 (threshold 15). Drivers by points: if/else 9 (13 pts), boolean chains 5, 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"6931660d7454d0460047c26afb9df3a6dfb628c8302188ac16c6aa52c0b5dd0c"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::datetime_rebase::push_unrequested_leaves (cognitive 19): datafusion_comet::parquet::datetime_rebase::push_unrequested_leaves has cognitive complexity 19 (threshold 15). Drivers by points: if/else 3 (6 pts), match/switch 3 (6 pts), loops 2 (5 pts), boolean chains 2 (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":"native/core/src/parquet/datetime_rebase.rs"},"region":{"startLine":613}}}],"partialFingerprints":{"codehealthFindingId/v1":"58a49d675b152463edd57b4b0dd205621ab8b092875413243701bfe6c60dd9f2"}},{"ruleId":"D2","level":"warning","message":{"text":"NestedPredicate::evaluate (cognitive 19): NestedPredicate::evaluate has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (11 pts), match/switch 3 (5 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":"native/spark-expr/src/array_funcs/nested_comparison.rs"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"64b064dc7abb8e651526ea3098bf01a6d23d24c5658620fa70e6b1bf6c318ade"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::checked_arithmetic::checked_binary (cognitive 19): datafusion_comet_spark_expr::math_funcs::checked_arithmetic::checked_binary has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (9 pts), loops 3 (6 pts), match/switch 2 (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":"native/spark-expr/src/math_funcs/checked_arithmetic.rs"},"region":{"startLine":229}}}],"partialFingerprints":{"codehealthFindingId/v1":"3604e0f4b2b5cad79d63e18479108cc4e0f767f22e5bff79ac9fffe06207fb47"}},{"ruleId":"D2","level":"warning","message":{"text":"QueryPlanSerde.exprToProtoInternal (cognitive 19): QueryPlanSerde.exprToProtoInternal has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (14 pts), match/switch 3 (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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":1040}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d1514077b0957b1003c47528281c86b04be28365ffa6f21255e1cfbdf6e65cb"}},{"ruleId":"D2","level":"warning","message":{"text":"CometLiteral.makeListLiteral (cognitive 19): CometLiteral.makeListLiteral has cognitive complexity 19 (threshold 15). Drivers by points: if/else 12 (18 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":"spark/src/main/scala/org/apache/comet/serde/literals.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"7999a588527db54301d8b18ba8a3781a26a4833ff81d38bad6f0e22c6bfe58ec"}},{"ruleId":"D2","level":"warning","message":{"text":"NativeFrameInputStream.read (cognitive 19): NativeFrameInputStream.read has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (16 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"78172086e8f051a5877451f151558524772a7b023fe88c36cf92939bbf298858"}},{"ruleId":"D2","level":"warning","message":{"text":"ShimSparkErrorConverter.getDataType (cognitive 19): ShimSparkErrorConverter.getDataType has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (10 pts), error handling 2 (7 pts), boolean chains 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a2b979a852c6d4484c7944e9c3c9cd2e1b0d3d50a809f3d97ed41eafe141e4b"}},{"ruleId":"D2","level":"warning","message":{"text":"ShimSparkErrorConverter.getDataType (cognitive 19): ShimSparkErrorConverter.getDataType has cognitive complexity 19 (threshold 15). Drivers by points: if/else 5 (10 pts), error handling 2 (7 pts), boolean chains 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":"spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":437}}}],"partialFingerprints":{"codehealthFindingId/v1":"09199cdd00d5674f9536fa684ca8ec194046644edd8a02f6226c1a76f0e6dd3e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::delta_dv::deserialize_dv_bitmap (cognitive 18): datafusion_comet::execution::delta_dv::deserialize_dv_bitmap has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (14 pts), loops 1 (2 pts), boolean chains 1, 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":"native/core/src/execution/delta_dv.rs"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"30872e158d732aa33968bbb0a0a0402c2076d41e769300a3bdd478c223735782"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_operators::explode::build_batch (cognitive 18): datafusion_comet_operators::explode::build_batch has cognitive complexity 18 (threshold 15). Drivers by points: if/else 3 (7 pts), match/switch 3 (7 pts), loops 2 (4 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":"native/operators/src/explode.rs"},"region":{"startLine":781}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8d85b4e5e275bcd9fc49a0d25cfa96a4258a57683762f90e36396459d0411e1"}},{"ruleId":"D2","level":"warning","message":{"text":"AvgGroupsAccumulator::update_batch (cognitive 18): AvgGroupsAccumulator::update_batch has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc0228c45c11d0424278b0495d619d0e6e6451b7568fd864cfee14d9734d7323"}},{"ruleId":"D2","level":"warning","message":{"text":"AvgDecimalGroupsAccumulator::update_batch (cognitive 18): AvgDecimalGroupsAccumulator::update_batch has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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":"native/spark-expr/src/agg_funcs/avg_decimal.rs"},"region":{"startLine":449}}}],"partialFingerprints":{"codehealthFindingId/v1":"10209b45ffbd2005f8f416848065cfbc8d244cae8d9ea8adfc2cff3e649a4e92"}},{"ruleId":"D2","level":"warning","message":{"text":"SumDecimalGroupsAccumulator::update_batch (cognitive 18): SumDecimalGroupsAccumulator::update_batch has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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":"native/spark-expr/src/agg_funcs/sum_decimal.rs"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"d84b7e1085aceb8c90e2acc96356ce182cccfa61971a093fafa83146fdef31ba"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_extrema::float_extrema (cognitive 18): datafusion_comet_spark_expr::array_funcs::array_extrema::float_extrema has cognitive complexity 18 (threshold 15). Drivers by points: if/else 3 (10 pts), loops 2 (4 pts), match/switch 1 (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":"native/spark-expr/src/array_funcs/array_extrema.rs"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"e01ef9052ae1f2a8c6479fa86a29f646ebd19d5a34a97039b41cf4cfee563d23"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_extrema::take_extrema_values (cognitive 18): datafusion_comet_spark_expr::array_funcs::array_extrema::take_extrema_values has cognitive complexity 18 (threshold 15). Drivers by points: match/switch 5 (10 pts), loops 3 (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":"native/spark-expr/src/array_funcs/array_extrema.rs"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c055e17d08c419eb5e9dd2fe171cb69090694dd7064be97059439872eacf2cf"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::sort_array::sort_floats (cognitive 18): datafusion_comet_spark_expr::array_funcs::sort_array::sort_floats has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (9 pts), loops 4 (9 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":"native/spark-expr/src/array_funcs/sort_array.rs"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"d98733d4e417f0514fb1c1a13f5d8a493d9cbf530f1748748184c45eb50feda0"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal128_impl (cognitive 18): datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal128_impl has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (13 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. This shape REPEATS in the file: one other method here (datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal256_impl) 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":365}}}],"partialFingerprints":{"codehealthFindingId/v1":"7534bf09c748457f5df868e9a7b3244d8bc1a5bd43e8b350cc7f7169d35f8e83"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal256_impl (cognitive 18): datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal256_impl has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (13 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. This shape REPEATS in the file: one other method here (datafusion_comet_spark_expr::conversion_funcs::string::cast_string_to_decimal128_impl) 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":436}}}],"partialFingerprints":{"codehealthFindingId/v1":"820437f590e793b5c96fa11aa47d7ffe90680dd0b092412fb11c88772fcc8d33"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::string::parse_string_to_decimal (cognitive 18): datafusion_comet_spark_expr::conversion_funcs::string::parse_string_to_decimal 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":713}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c107c981891f6ea270bd2e17e01b3d2d055db662b1065e883321d83f5e21ab7"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::json_funcs::from_json::json_string_to_struct (cognitive 18): datafusion_comet_spark_expr::json_funcs::from_json::json_string_to_struct has cognitive complexity 18 (threshold 15). Drivers by points: if/else 5 (9 pts), loops 2 (6 pts), match/switch 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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"054c517115cdd14118ff9d68273a9e8fa6497d0dfb9932b1388f579eba4fbc7e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding_internal (cognitive 18): datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding_internal has cognitive complexity 18 (threshold 15). Drivers by points: match/switch 3 (7 pts), loops 3 (6 pts), if/else 2 (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":"native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"8efc334f2b08c904adbc189d0d09f54d4a1fd8370ef3ce5f7b24ab112b995f44"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.refreshedNativeOp (cognitive 18): CometExecRule.refreshedNativeOp has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11, match/switch 4 (5 pts), boolean chains 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":853}}}],"partialFingerprints":{"codehealthFindingId/v1":"92a6ff5ecce010909090dde33993c0b4f3b7d069fc54c6465885fc6279f85c74"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.rewriteInSubqueryPlan (cognitive 18): CometExecRule.rewriteInSubqueryPlan has cognitive complexity 18 (threshold 15). Drivers by points: match/switch 4 (10 pts), if/else 6 (8 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":950}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9bee807509b37499730368b8ca18d67f94b04276992e33e211f0f0ccd26e2c4"}},{"ruleId":"D2","level":"warning","message":{"text":"QueryContextInterner.walk (cognitive 18): QueryContextInterner.walk has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (7 pts), loops 2 (5 pts), match/switch 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":"spark/src/main/scala/org/apache/comet/serde/QueryContextInterner.scala"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"396fef9a132c02e1e8727ed4449022ef5eda150cc3aa950a67c18b033c4bbc2c"}},{"ruleId":"D2","level":"warning","message":{"text":"CometNativeScan.isSupported (cognitive 18): CometNativeScan.isSupported 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"741514efd89553416581debb90cb8d58984a076c4831596009302409db61c275"}},{"ruleId":"D2","level":"warning","message":{"text":"CometWindowExec.rangeBoundLiteral (cognitive 18): CometWindowExec.rangeBoundLiteral has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 2, error handling 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":754}}}],"partialFingerprints":{"codehealthFindingId/v1":"c551c2bb982bcd4941b4ae2f995703af049a36450548861994fcae3eb3006059"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowFieldWriter.writeVariableWidth (cognitive 18): ArrowFieldWriter.writeVariableWidth 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":455}}}],"partialFingerprints":{"codehealthFindingId/v1":"42dfe5b253644e1291e5d4843f58c90f5349243135e48abcad387f08e8107b10"}},{"ruleId":"D2","level":"warning","message":{"text":"bench_delta_comet.main (cognitive 18): bench_delta_comet.main has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (10 pts), boolean chains 3, loops 2, ternaries 2, error handling 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"contrib/delta-spark/dev/bench_delta_comet.py"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8f4490b4c8321f4020285def22cea687634c4b108b944aa5a51c163ffd81a59"}},{"ruleId":"D2","level":"warning","message":{"text":"HashJoinBuilder::build (cognitive 17): HashJoinBuilder::build has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (14 pts), boolean chains 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":"native/core/src/execution/planner/join.rs"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"e97f1157aa892253c47c3a7757ae60782429e62ee83ca6d6a87f3d9553225cbb"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowPythonUdf::evaluate_named (cognitive 17): ArrowPythonUdf::evaluate_named has cognitive complexity 17 (threshold 15). Drivers by points: if/else 12 (14 pts), loops 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":"native/core/src/execution/python_udf.rs"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"b672a14423e28f81b8223ee1694a1686c52fa85a75dfadb95ee71386e47861a2"}},{"ruleId":"D2","level":"warning","message":{"text":"ExplodeStream::poll_next_impl (cognitive 17): ExplodeStream::poll_next_impl has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (14 pts), 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":"native/operators/src/explode.rs"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"313c57bf9b08a3ed0c8c2513a823ba21b2ac26a26bca17ef5bd427a709b6af48"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::spark_unsafe::row::process_sorted_partitions (cognitive 17): datafusion_comet_shuffle::spark_unsafe::row::process_sorted_partitions has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (9 pts), loops 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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1616}}}],"partialFingerprints":{"codehealthFindingId/v1":"c91e2d73b0a5dcb50fe19952445a2015415a708c0204bc1f9880b9d32bbdfc47"}},{"ruleId":"D2","level":"warning","message":{"text":"QuantileSummaries::merge (cognitive 17): QuantileSummaries::merge has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (13 pts), loops 3, 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":"native/spark-expr/src/agg_funcs/quantile_summaries.rs"},"region":{"startLine":264}}}],"partialFingerprints":{"codehealthFindingId/v1":"910791cdd28fdcd9b93bbe1a9246f35eb3763e52a80c6c07e3d977911743bcca"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkArraysOverlap::invoke_with_args (cognitive 17): SparkArraysOverlap::invoke_with_args has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (12 pts), match/switch 3 (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":"native/spark-expr/src/array_funcs/arrays_overlap.rs"},"region":{"startLine":124}}}],"partialFingerprints":{"codehealthFindingId/v1":"8afc37ec3342374f44f570a070797380c05e461d606918618db44c76a8f44d5c"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::agg_funcs::hll_plus_plus::query (cognitive 17): datafusion_comet_spark_expr::agg_funcs::hll_plus_plus::query has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (10 pts), boolean chains 4, loops 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":"native/spark-expr/src/agg_funcs/hll_plus_plus.rs"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"63a3789082f4ef86cd62b27701920f65e76eb3399e5a18b11dd1ec87c04b8d12"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::unhex::spark_unhex_inner (cognitive 17): datafusion_comet_spark_expr::math_funcs::unhex::spark_unhex_inner has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (14 pts), loops 1 (2 pts), 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":"native/spark-expr/src/math_funcs/unhex.rs"},"region":{"startLine":88}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7f19336bc142738a138f1f0980da91b16da1786187ee772f265e25ee758c40e"}},{"ruleId":"D2","level":"warning","message":{"text":"GenerateDocs.writeCastMatrixForMode (cognitive 17): GenerateDocs.writeCastMatrixForMode has cognitive complexity 17 (threshold 15). Drivers by points: loops 5 (7 pts), if/else 4 (6 pts), match/switch 1 (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":"spark/src/main/scala/org/apache/comet/GenerateDocs.scala"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"765aa5dbcbaa9f207dfdaed9e317ebaf2e1e62bc8cbbc808ffed4a9955b5e39c"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExecRule.tryConvertToComet (cognitive 17): CometExecRule.tryConvertToComet has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 3, 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1288}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a75b5e1e3e7b891cb02a16d8204d7c7a6a2de9464ad62569072c2337e960a4e"}},{"ruleId":"D2","level":"warning","message":{"text":"CometScanRule.nativeScan (cognitive 17): CometScanRule.nativeScan has cognitive complexity 17 (threshold 15). Drivers by points: if/else 12, boolean chains 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"0620d5dfd1c97ff0a109f4664fae9053753cb551bf0bf444caab306444d23193"}},{"ruleId":"D2","level":"warning","message":{"text":"CometElementAt.convert (cognitive 17): CometElementAt.convert has cognitive complexity 17 (threshold 15). Drivers by points: loops 3 (9 pts), if/else 5 (6 pts), boolean chains 1, match/switch 1 (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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":922}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a34452aec8f1ff3d9fca59129a35e427add11d5d71c55a05cba61ab6d4ea963"}},{"ruleId":"D2","level":"warning","message":{"text":"CometWindowExec.convert (cognitive 17): CometWindowExec.convert 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"948c879160f6f5803a34126eea2a999a8e718c12346ad7c28d755bb10504fcff"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowFieldWriter.writeChildRuns (cognitive 17): ArrowFieldWriter.writeChildRuns has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (15 pts), boolean chains 1, 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"49a3aeae72b62aee655463a85e1214219a588b40ca3afeb9b6f7d684496b53c7"}},{"ruleId":"D2","level":"warning","message":{"text":"NativeBatchDecoderIterator.close (cognitive 17): NativeBatchDecoderIterator.close has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (15 pts), 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/NativeBatchDecoderIterator.scala"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7a7f0a40dc01a1200f705eb8038834269d1d8339f58baf985dfdf258e8a94b7"}},{"ruleId":"D2","level":"warning","message":{"text":"CometMergeRows.convert (cognitive 17): CometMergeRows.convert has cognitive complexity 17 (threshold 15). Drivers by points: if/else 14, boolean chains 2, match/switch 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":"spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"61d8e607c4886d7ca6558c4c36290efce6e3ddb722c347ddaa2c653ae14d31a6"}},{"ruleId":"D2","level":"warning","message":{"text":"Spark4xCometExprShim.sparkVersionSpecificExprToProtoInternal (cognitive 17): Spark4xCometExprShim.sparkVersionSpecificExprToProtoInternal has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (12 pts), 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":"spark/src/main/spark-4.x/org/apache/comet/shims/Spark4xCometExprShim.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ad2a9ed5fadc5b143201bb02bbb54c59ec27a4b830ec684f83d40604ed4d5d5"}},{"ruleId":"D2","level":"warning","message":{"text":"FactoryHook.invoke (cognitive 17): FactoryHook.invoke has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (12 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":729}}}],"partialFingerprints":{"codehealthFindingId/v1":"50ceda6bb4ac23b9cb9db765c1c1fab4d9f73bfe32e46ba134496beaf83a27e5"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_artifact_names (cognitive 17): check-ci-config.check_artifact_names has cognitive complexity 17 (threshold 15). Drivers by points: if/else 3 (9 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":"dev/ci/check-ci-config.py"},"region":{"startLine":956}}}],"partialFingerprints":{"codehealthFindingId/v1":"12226d5d252049db219d6f4086947908df996bb33181264b34ac94b78e2e7335"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_local_actions_have_checkout (cognitive 17): check-ci-config.check_local_actions_have_checkout has cognitive complexity 17 (threshold 15). Drivers by points: if/else 4 (12 pts), loops 3 (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":"dev/ci/check-ci-config.py"},"region":{"startLine":984}}}],"partialFingerprints":{"codehealthFindingId/v1":"4aa4f5d0d9952e1f41a81fc0c1f54ce67ff0ba2e7d4fbdef119482e227917762"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.ci_jobs_and_aggregator (cognitive 17): check-ci-config.ci_jobs_and_aggregator has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (14 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1019}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8de6947524e6a79823908913491515b1b8e81189213327b6476f78f929e277e"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config._cache_steps (cognitive 17): check-ci-config._cache_steps has cognitive complexity 17 (threshold 15). Drivers by points: if/else 3 (9 pts), loops 3 (5 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1508}}}],"partialFingerprints":{"codehealthFindingId/v1":"a6e83b2289ebab0f27ae9167c7d4a0d8b51eb28a404189de57bd188698484819"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_common::utf8::decode_string_arrays (cognitive 16): datafusion_comet_common::utf8::decode_string_arrays has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), loops 2 (4 pts), 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":"native/common/src/utf8.rs"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"141eb6a0a97d939677572bfa5377b9d70511eec9cca1250446311776cd7b6337"}},{"ruleId":"D2","level":"warning","message":{"text":"WindowBuilder::build (cognitive 16): WindowBuilder::build has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (12 pts), match/switch 1 (3 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":"native/core/src/execution/planner/window.rs"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"050622eb358345127b78ad8b0037e024a9675ba493a3f78e519d98b85be4bfcf"}},{"ruleId":"D2","level":"warning","message":{"text":"PhysicalPlanner::create_scalar_function_expr (cognitive 16): PhysicalPlanner::create_scalar_function_expr has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9, match/switch 4 (6 pts), boolean chains 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":"native/core/src/execution/planner.rs"},"region":{"startLine":2084}}}],"partialFingerprints":{"codehealthFindingId/v1":"c25ab901b2cf3739588145b2f7315e748c3e8ace4ea10edf57ed7d816db16ec7"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkPhysicalExprAdapter::wrap_all_type_mismatches (cognitive 16): SparkPhysicalExprAdapter::wrap_all_type_mismatches has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), match/switch 1 (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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":1314}}}],"partialFingerprints":{"codehealthFindingId/v1":"33c1b3c867244c3c9e8dd1bb482a4e28f33f5a97b20a4a9c75f19462180e5438"}},{"ruleId":"D2","level":"warning","message":{"text":"SparkPhysicalExprAdapter::replace_with_spark_cast (cognitive 16): SparkPhysicalExprAdapter::replace_with_spark_cast has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (14 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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":1421}}}],"partialFingerprints":{"codehealthFindingId/v1":"114a07d0ad6395a5720904e7530c3f1a57ca84d093ec8590791c20f70496abe6"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::execution::serde::to_arrow_datatype (cognitive 16): datafusion_comet::execution::serde::to_arrow_datatype has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 5 (9 pts), if/else 2 (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":"native/core/src/execution/serde.rs"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"1296be9e2bffbc62be39dcd25efb790f1ca560d04ecbf5541bd80940200adb2d"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet::parquet::parquet_exec::init_datasource_exec (cognitive 16): datafusion_comet::parquet::parquet_exec::init_datasource_exec has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (10 pts), boolean chains 3, match/switch 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":"native/core/src/parquet/parquet_exec.rs"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3340e8894f7477a4ec3ae555acd857372fdb35b59d66130a56d03ce023f4ef8"}},{"ruleId":"D2","level":"warning","message":{"text":"RssPartitionWriter::estimated_array_compaction_scratch (cognitive 16): RssPartitionWriter::estimated_array_compaction_scratch 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). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":798}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb554b6d7e77f8bf7efe9c17b1edaf9abf3f0cd236cdea2929cc9ef5c06977b9"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::bin::shuffle_bench::print_shuffle_metrics (cognitive 16): datafusion_comet_shuffle::bin::shuffle_bench::print_shuffle_metrics 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":"native/shuffle/src/bin/shuffle_bench.rs"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"12e0f5fb222254ee9e4c8d4bae30474ff714ad2c8406321304c83b6a0cb5188b"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_shuffle::ipc::read_single_batch (cognitive 16): datafusion_comet_shuffle::ipc::read_single_batch has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (10 pts), match/switch 3 (5 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":"native/shuffle/src/ipc.rs"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"de4fcfd3534d07d72acbcb5b4632838ec59b5706aaba6a40196057dab32937e7"}},{"ruleId":"D2","level":"warning","message":{"text":"SumIntegerAccumulatorTry::merge_batch (cognitive 16): SumIntegerAccumulatorTry::merge_batch has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (12 pts), match/switch 1 (2 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"f12d8669e16fcc4e46c3ee97d2a8a3a7cf33e90704b0efaa7572b5dc7872807f"}},{"ruleId":"D2","level":"warning","message":{"text":"SumIntGroupsAccumulatorTry::update_batch::update_groups_sum (cognitive 16): SumIntGroupsAccumulatorTry::update_batch::update_groups_sum has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (10 pts), match/switch 1 (3 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":900}}}],"partialFingerprints":{"codehealthFindingId/v1":"db97c44e109386b6dd7d59aab152e20dc811a6799ed91f00d202142aeba7492e"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_extrema::nested_extrema (cognitive 16): datafusion_comet_spark_expr::array_funcs::array_extrema::nested_extrema has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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":"native/spark-expr/src/array_funcs/array_extrema.rs"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"e375ac7dbf6902e72a6a2210d1cfe0f9fe2becf8413729bbf881d52d3baf14b3"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_remove::remove_floats (cognitive 16): datafusion_comet_spark_expr::array_funcs::array_remove::remove_floats has cognitive complexity 16 (threshold 15). Drivers by points: if/else 2 (7 pts), loops 2 (5 pts), match/switch 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":"native/spark-expr/src/array_funcs/array_remove.rs"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"158427c867d6c2d9e7a3795a8d778e5a985164d53088e545ad8de8a6dbcebcde"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::array_funcs::array_slice::slice_list (cognitive 16): datafusion_comet_spark_expr::array_funcs::array_slice::slice_list has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (12 pts), boolean chains 2, 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":"native/spark-expr/src/array_funcs/array_slice.rs"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"25979eea3ca755a158fab14c19f8c5d9fd01cd1a6b4e2b2b8c49d908e905bd8a"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::cast::cast_array_to_string (cognitive 16): datafusion_comet_spark_expr::conversion_funcs::cast::cast_array_to_string has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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. This shape REPEATS in the file: one other method here (datafusion_comet_spark_expr::conversion_funcs::cast::casts_struct_to_string) 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":687}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d12d6327abc8db37ffd4a58844ed13f423e4d8b014ee669ada7cc09aeca928c"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::cast::casts_struct_to_string (cognitive 16): datafusion_comet_spark_expr::conversion_funcs::cast::casts_struct_to_string has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (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. This shape REPEATS in the file: one other method here (datafusion_comet_spark_expr::conversion_funcs::cast::cast_array_to_string) 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":733}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6f2548c8c453da32c4e5959f9cd5d5aaa6f6185cfb142c81bae882960280430"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::conversion_funcs::numeric::decimal128_to_java_string (cognitive 16): datafusion_comet_spark_expr::conversion_funcs::numeric::decimal128_to_java_string has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (12 pts), loops 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":"native/spark-expr/src/conversion_funcs/numeric.rs"},"region":{"startLine":697}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9e1c725cabe9f7b2383fd3bf2774035777d5bf3c688e2e28f2fb8e46fe00393"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_by_row_format (cognitive 16): datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_by_row_format has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 3 (7 pts), if/else 4 (6 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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":1299}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb7a6e22dab20504347775928b1ef3e3d0d06995c7149ac05490af1082b917fc"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::math_funcs::checked_arithmetic::binary_overflow_error (cognitive 16): datafusion_comet_spark_expr::math_funcs::checked_arithmetic::binary_overflow_error has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (12 pts), match/switch 1 (2 pts), boolean chains 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":"native/spark-expr/src/math_funcs/checked_arithmetic.rs"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"2dbd41eb797db0240198691028b12fc4b0ca060a253abd928b8b2eefebab7933"}},{"ruleId":"D2","level":"warning","message":{"text":"datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2 (cognitive 16): datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2 has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (8 pts), match/switch 5 (8 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":"native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ec43056e809ee7ff1c2bd5a8c43b837e10d1bb5546ecefea408fd142d4a3fc0"}},{"ruleId":"D2","level":"warning","message":{"text":"EliminateRedundantTransitions._apply (cognitive 16): EliminateRedundantTransitions._apply has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (14 pts), match/switch 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":"spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac4340c50d2ff87748de9dd346b920aa2f6c29ea5b58adc7c97c8fcfbff78771"}},{"ruleId":"D2","level":"warning","message":{"text":"QueryPlanSerde.extractQueryContext (cognitive 16): QueryPlanSerde.extractQueryContext has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (9 pts), boolean chains 3, error handling 1 (2 pts), 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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":504}}}],"partialFingerprints":{"codehealthFindingId/v1":"8215f53ff644c7eb3a2d2d1419b3b299771c68af27910fc34f1ebcbee4ad457e"}},{"ruleId":"D2","level":"warning","message":{"text":"CometIntegralDivide.convert (cognitive 16): CometIntegralDivide.convert 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":"spark/src/main/scala/org/apache/comet/serde/arithmetic.scala"},"region":{"startLine":317}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceeacacf9c2484dddd410ed981957d9de1da058415356068c911ed32c8f2f340"}},{"ruleId":"D2","level":"warning","message":{"text":"CometShuffleExchangeExec.shuffleSupported (cognitive 16): CometShuffleExchangeExec.shuffleSupported 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":489}}}],"partialFingerprints":{"codehealthFindingId/v1":"a07524a2a957ff73f8bdd92580413bfa2fa20d24fa95bb3588fae054dae4cacf"}},{"ruleId":"D2","level":"warning","message":{"text":"PlanDataInjector.injectPlanData (cognitive 16): PlanDataInjector.injectPlanData has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (9 pts), match/switch 3 (6 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f771139dd1c63d59dd4d107b02f384624d7fa32b75f77c108c6c06922979730"}},{"ruleId":"D2","level":"warning","message":{"text":"CometExprShim.sparkVersionSpecificExprToProtoInternal (cognitive 16): CometExprShim.sparkVersionSpecificExprToProtoInternal has cognitive complexity 16 (threshold 15). Drivers by points: match/switch 4 (7 pts), boolean chains 5, if/else 4 (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":"spark/src/main/spark-4.1\u002B/org/apache/comet/shims/CometExprShim.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e954c58526be75e52665b79dcc734de2b60bd7ef29853761fce9734b675d0cf"}},{"ruleId":"D2","level":"warning","message":{"text":"CometArrowEvalPythonExec.getSupportLevel (cognitive 16): CometArrowEvalPythonExec.getSupportLevel has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9, boolean chains 5, 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":"spark/src/main/spark-4.1\u002B/org/apache/spark/sql/comet/CometArrowEvalPythonExec.scala"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a92e52ecbeb9a99cb9cf62135a4f102f33c4591eec5a615d0420530a14158f7"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornShufflePartitionPusher.finish (cognitive 16): CelebornShufflePartitionPusher.finish has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9, error handling 4, boolean chains 2, loops 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"b495ee3b3936c01f5233687bc4c080578cb5dda3967b1adb8bb18a73c40e2c3b"}},{"ruleId":"D2","level":"warning","message":{"text":"CelebornTransportCallbackTracker.installFactoryHook (cognitive 16): CelebornTransportCallbackTracker.installFactoryHook has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (11 pts), error handling 4, 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4cb0cbf608d21223f004bd19fbd788fc5ab5304737f9d1fe6fb9a45720af9fc"}},{"ruleId":"D2","level":"warning","message":{"text":"check-ci-config.check_cache_refresh_scope (cognitive 16): check-ci-config.check_cache_refresh_scope has cognitive complexity 16 (threshold 15). Drivers by points: if/else 3 (8 pts), loops 4 (6 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":"dev/ci/check-ci-config.py"},"region":{"startLine":1340}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd03869752c4e222f180caa8383c073d496932eb9288ba71163a118133882b79"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: comet/operators.scala: FileTooLong \u2014 2273 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1773 over it, 4.55\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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e61c316ce4a5422fadab45b69ac261af0e7dcfd9afa61f9a52eb4aaf1c4eefb5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/planner.rs: FileTooLong \u2014 2050 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), about 68% of them inside a single declaration: PhysicalPlanner (3 blocks, 185-2272). The bar is 500 significant lines; this is 1550 over it, 4.10\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":"native/core/src/execution/planner.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0aecf8e9f26030dc3db402abb363f5f2e15e653e43768b140a42e967b3b07678"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: IcebergReflection: TooManyMethods \u2014 119 methods. The bar is 30 methods; this is 89 over it, 3.97\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":"spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"93fb8f9e21d380783c5542480ca663336547ead48471285ffe068cdb2870b01c"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_expr: MethodTooLong \u2014 create_expr runs 370 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 270 over it, 3.70\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":"native/core/src/execution/planner.rs"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a67dba21f7a0a558044c91894b8ddbafcc447f520093e03492c3fd4cd53297a"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_agg_expr: MethodTooLong \u2014 create_agg_expr runs 364 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 264 over it, 3.64\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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"f190b47b1e6903a42699a160144c4c05042423903a399c484f176bc8da7d6b08"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: PhysicalPlanner: ClassTooLong \u2014 1404 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), 51 methods, 3 blocks, lines 185-2272. The bar is 400 significant lines; this is 1004 over it, 3.51\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":"native/core/src/execution/planner.rs"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"0735c74c0360634029d9251367a0d62a7bf2492d2b92b3cde0bd80a902f16ed3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: comet/CometConf.scala: FileTooLong \u2014 1661 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1161 over it, 3.32\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":"spark/src/main/scala/org/apache/comet/CometConf.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"356fe8e9be2186572e5550b1988b362af91a041f8e4a82bebb32342d0c08aa3e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: execution/jni_api.rs: FileTooLong \u2014 1586 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), declaring 77 free functions. The bar is 500 significant lines; this is 1086 over it, 3.17\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":"native/core/src/execution/jni_api.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa54186c2e4575a988e7cc282c319280f82f81c4c51b2e95790f874d63bb21cf"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_plan: MethodTooLong \u2014 create_plan runs 317 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 217 over it, 3.17\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":"native/core/src/execution/planner.rs"},"region":{"startLine":1643}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed86bf58c0f85435b66ad96ff5e03b569c6784d8fbd152aa3d1772c33e8b3bfb"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: conversion_funcs/string.rs: FileTooLong \u2014 1491 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), declaring 62 free functions. The bar is 500 significant lines; this is 991 over it, 2.98\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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"648cc04dec3db75f88468a5e155e140b879c17af975b58c308cff9c76147e251"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: iceberg/IcebergReflection.scala: FileTooLong \u2014 1384 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 884 over it, 2.77\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":"spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"30b6151803f56dc592449e9dbccd3801406f56b7315530c4d2ae12cc7ba24914"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: operators/iceberg_write.rs: FileTooLong \u2014 1329 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 829 over it, 2.66\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":"native/core/src/execution/operators/iceberg_write.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d4d75b1b900bfb2c4c4c4841fabf715fa72c2d12a7287f38e640ae791dddd85"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: arrow/ArrowWriters.scala: FileTooLong \u2014 1263 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 763 over it, 2.53\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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2eca0d4dd32a95dba078a2839219b1c8aa6ed25f1f44dda62288127a6f4e8487"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark_unsafe/row.rs: FileTooLong \u2014 1176 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 676 over it, 2.35\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d312c57d7add3f4d9d3507b67f5e5f71401d68211c6a30cf8af0cd9857e44241"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::execution::planner::parse_file_scan_tasks_from_common: FunctionTooLong \u2014 datafusion_comet::execution::planner::parse_file_scan_tasks_from_common runs 227 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 127 over it, 2.27\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":"native/core/src/execution/planner.rs"},"region":{"startLine":2419}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b008481ea3322ed8d28f874cb6b25a5ddaa7b0668ebe88c7db56a8c2ed464e7"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: serde/aggregates.scala: FileTooLong \u2014 1131 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 631 over it, 2.26\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":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6e262c36b12e598eb38122529c4f27561ddc2284cf6d0fc66baa84d6d672cec"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: ci/check-ci-config.py: FileTooLong \u2014 1129 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 629 over it, 2.26\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":"dev/ci/check-ci-config.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d83d73c674a6d0e35d96fe0898faec57b0b6fa97fcc350eab7a563c953e0a2f"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: CelebornTransportCallbackTracker: ClassTooLong \u2014 896 significant lines (blank, comment-only and punctuation-only lines excluded), 15 methods. The bar is 400 significant lines; this is 496 over it, 2.24\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":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9c8e88352ce47e23265b0ec42eae28ce4529d3e257bf8569d81fadd792901fe"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SparkError.params_as_json: MethodTooLong \u2014 params_as_json runs 221 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 121 over it, 2.21\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":"native/common/src/error.rs"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"be409d246c5b675ed224070cc33e4fbf4e8688c44950f2fc2c7fd5eca4fb5c8c"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: CelebornShufflePartitionPusher: ClassTooLong \u2014 869 significant lines (blank, comment-only and punctuation-only lines excluded), 50 methods. The bar is 400 significant lines; this is 469 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"05f841dbc7ef360ad64d11c3f2c8ff3a333666fbe7e2747ac27ca82e2423660c"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: rules/CometExecRule.scala: FileTooLong \u2014 1072 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 572 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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1c34c25b9b57210dbf58f7b59230bf1b4719570241555114b292fccf303940d"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DeltaScanSupport: 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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd09675d29228ebea9473a863503939c13dff3adefcd9c559ad26822626ea7ea"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: RssPartitionWriter: ClassTooLong \u2014 802 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), 17 methods, 3 blocks, lines 48-1133. The bar is 400 significant lines; this is 402 over it, 2.01\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"b60c4481a190eef54fab00668d916af53676c4c02d7e6ca2e096871e9cf6302d"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: rules/CometScanRule.scala: FileTooLong \u2014 990 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 490 over it, 1.98\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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"87b5ce3a72a6314ff214dab33b4df31c1ffc7cce262e6f2e597a3f16498aff5b"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/schema_adapter.rs: FileTooLong \u2014 979 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 479 over it, 1.96\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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"43d153c2c31a0b3fa1b8078811d545d0f166b09060005fdcc7464e0bee7f323f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: operator/CometIcebergNativeScan.scala: FileTooLong \u2014 962 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 462 over it, 1.92\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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"62fabeb8ccc7eaf296f431ff3eab3bcb46e3eb25b79da6c0f67c83a7e5c4414a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: serde/QueryPlanSerde.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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c842fe93b06d1d91c7ca8924b4505105cfe2e1a4015207abfb4a1e5285a3701a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/CelebornTransportCallbackTracker.java: FileTooLong \u2014 927 significant lines (blank, comment-only and punctuation-only lines excluded), about 97% of them inside a single declaration: CelebornTransportCallbackTracker (55-1409). The bar is 500 significant lines; this is 427 over it, 1.85\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":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f9cd90e5160e3378fc53fbc1294e0226d8d7ed9bb99b3109f539c61391c3cbc"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: delta/DeltaScanSupport.scala: FileTooLong \u2014 900 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 400 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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d8a877da0ed8f04a9b8bc0b3e7c3e64a69f6e4e4c744d4bc3841fae985a8744"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/CelebornShufflePartitionPusher.java: FileTooLong \u2014 889 significant lines (blank, comment-only and punctuation-only lines excluded), about 98% of them inside a single declaration: CelebornShufflePartitionPusher (43-1266). The bar is 500 significant lines; this is 389 over it, 1.78\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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0329568b8f1fbde6b7269c6699086925c1fe10e91eb4b035ac27e40689db609"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::conversion_funcs::cast::cast_array: FunctionTooLong \u2014 datafusion_comet_spark_expr::conversion_funcs::cast::cast_array runs 177 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 77 over it, 1.77\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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8c08eff87da40fd54940d7ab1e0287a95877bc4c45432ce2bc5254a34244351"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/CometCelebornShuffleManager.scala: FileTooLong \u2014 868 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 368 over it, 1.74\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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c47246e2e7c71d0713952f5c4d9a44aeb0b228c7bde70c2f5eb30b3c34b9541a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: rss/rss_partition_writer.rs: FileTooLong \u2014 867 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), about 93% of them inside a single declaration: RssPartitionWriter (3 blocks, 48-1133). The bar is 500 significant lines; this is 367 over it, 1.73\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"519720c6279f83bed537e991625998a730df440de1cab7613f603aa9c8865d71"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: HashAggBuilder.build: MethodTooLong \u2014 build runs 172 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 72 over it, 1.72\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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"2620bfdeec399549b5ffa54ce2697f0d7c3fd90412b17da533bce07ab912026e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: kernels/temporal.rs: FileTooLong \u2014 855 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), declaring 52 free functions. The bar is 500 significant lines; this is 355 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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b8e5497c1e926f042c2b473c9087566101f9007e012037f32be5822115d3f648"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: PhysicalPlanner: TooManyMethods \u2014 51 methods, declared across 5 files: execution/planner.rs (38), planner/join.rs (5), planner/aggregate.rs (4), planner/window.rs (3), \u002B1 more file(s). The bar is 30 methods; this is 21 over it, 1.70\u00D7 the bar. That list is where to read them, not a suggestion to split the file: the members belong to the type wherever they are declared, so moving them between files leaves the count unchanged. 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":"native/core/src/execution/planner.rs"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"bef0ba24659e1022a9306dee49e1b4cd8fd17010e369706c478ac39164af20d2"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::math_funcs::abs::abs: FunctionTooLong \u2014 datafusion_comet_spark_expr::math_funcs::abs::abs runs 169 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 69 over it, 1.69\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":"native/spark-expr/src/math_funcs/abs.rs"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"9905d3f165f4a589f2231badedee65c66064f14f6edfc6af7dc67a43d6a7b94e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: serde/arrays.scala: FileTooLong \u2014 839 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 339 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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"01c234c714971b308716032780188d4cbeb494a686c2135541b60f92951aa50f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: cast_column/variant.rs: FileTooLong \u2014 839 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 339 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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0555eea9ff2fe85af76baaffe8900db699c46b933786894716a6b1478cd0045"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: hash_funcs/utils.rs: FileTooLong \u2014 835 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 335 over it, 1.67\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":"native/spark-expr/src/hash_funcs/utils.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"570b8077c4185e32ecd38a7ef7b589016da12ee018fe157ceb40ba9ef7594d8e"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: CelebornShufflePartitionPusher: 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"ead3945943008a4fd322904d8f3ea71f6a1cc574b850b62d0f26c2736c1225b1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/eager_page_index_reader_factory.rs: FileTooLong \u2014 828 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 328 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":"native/core/src/parquet/eager_page_index_reader_factory.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c40873211a2b4e39e2e36205ae71f68d5c21047d2bdaf825b6c3b15f6430820"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major: FunctionTooLong \u2014 datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major runs 165 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 65 over it, 1.65\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":823}}}],"partialFingerprints":{"codehealthFindingId/v1":"21133ed387db9b5ec94b61626fd932dd5663fdf36db3ee0370d14eb4708a4886"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: RssPartitionWriter.estimated_ipc_metadata_scratch: MethodTooLong \u2014 estimated_ipc_metadata_scratch runs 164 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 64 over it, 1.64\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":390}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccc60349175e20b87cd785d359cf277b76d3f06b63c45748eb0de31e53964b09"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: conversion_funcs/numeric.rs: FileTooLong \u2014 818 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), declaring 36 free functions. The bar is 500 significant lines; this is 318 over it, 1.64\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":"native/spark-expr/src/conversion_funcs/numeric.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"39ad78501f172ccd0548848203c2416dda9052a79e25c35194c0e938dbfccd4e"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::comet_scalar_funcs::create_comet_physical_fun_with_eval_mode: FunctionTooLong \u2014 datafusion_comet_spark_expr::comet_scalar_funcs::create_comet_physical_fun_with_eval_mode runs 159 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/spark-expr/src/comet_scalar_funcs.rs"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"21dc5c88fea06d70a4c222e92b51f53ab7221afb4e137c23be59762089c175ed"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major: FunctionTooLong \u2014 datafusion_comet_shuffle::spark_unsafe::row::append_nested_struct_fields_field_major runs 158 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 58 over it, 1.58\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":373}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4be6667da4861601c142872e35eb163c88815fe7c8b2b9b858595be881d71c3"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: CelebornShufflePartitionPusher.\u003Cinit\u003E: MethodTooLong \u2014 \u003Cinit\u003E runs 156 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 56 over it, 1.56\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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e40205ade1decf5c472f25f4abd0f37679d374812a47644155dc369603bfab1"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_window_expr: MethodTooLong \u2014 create_window_expr runs 156 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 56 over it, 1.56\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":"native/core/src/execution/planner/window.rs"},"region":{"startLine":309}}}],"partialFingerprints":{"codehealthFindingId/v1":"ddba27ca32ff43e8bec0b9a447312e5937bdd800fdb0fd56a992d5604f1f1e10"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_shuffle::spark_unsafe::row::append_columns: FunctionTooLong \u2014 datafusion_comet_shuffle::spark_unsafe::row::append_columns runs 154 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 54 over it, 1.54\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1079}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff2c9be50e9be66f566591e3f3cc653c0110547e34de085b6357e7f275016731"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: operator/CometIcebergNativeWrite.scala: FileTooLong \u2014 763 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 263 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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeWrite.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"33fe329c45483c62c866d4406f76a619ccb18ded0b536e66ebb26ccc7173ee01"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::parquet::parquet_exec::init_datasource_exec: FunctionTooLong \u2014 datafusion_comet::parquet::parquet_exec::init_datasource_exec runs 147 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 47 over it, 1.47\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":"native/core/src/parquet/parquet_exec.rs"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f031ca126613f9343c1bf74b0afa1dcda3342887867ae68ac08745cf1df9654"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: RssPartitionWriter.push_batch_within_limit: MethodTooLong \u2014 push_batch_within_limit runs 147 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 47 over it, 1.47\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"450ae957ae73311f74ef02351019c9dd154bbc169c1bdbc7ec5245140779852a"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: SparkError: ClassTooLong \u2014 586 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), 7 methods, 3 blocks, lines 23-1040. The bar is 400 significant lines; this is 186 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":"native/common/src/error.rs"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb60508dc83010bd5084a6b0ff9d21b01a2ba47bf04f7298ffe9969d8a0a5035"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/CometShuffleExchangeExec.scala: 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"71bd24ae7fe96571ed28c6c0009b6ab064cc12884fd6c328e7dc2a89c810ebbb"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_common::bin::analyze_trace::main: FunctionTooLong \u2014 datafusion_comet_common::bin::analyze_trace::main runs 143 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 43 over it, 1.43\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":"native/common/src/bin/analyze_trace.rs"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"f98364a4f62d135333466b5d5c9ad0495ef30ac712228eddeb075e1011ffb45e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: agg_funcs/sum_int.rs: FileTooLong \u2014 708 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 208 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"70cb406a498a9bc132664ef0dd0fcbb366039cb3cbf0ea7826e0943145c29923"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: planner/aggregate.rs: FileTooLong \u2014 698 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). 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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1179e769a91e3088ce8f5111743634dae4e9a6a4315260da2d4dee505edbebd3"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/datetime_rebase.rs: FileTooLong \u2014 688 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 188 over it, 1.38\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":"native/core/src/parquet/datetime_rebase.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c402b17793cdc60942cd9356f2d3dcf99d256d803a67dd69296a1acb05455ee"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: serde/datetime.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":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf503a4364ffa8cb633130a910fd5ba161ba8adc4c78314f289ce693ccfaf1f5"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: conversion_funcs/cast.rs: FileTooLong \u2014 672 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 172 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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"aebe139d3ee0a7b0521d2060585304e7eb0669b32cb7243589cbd93ad3532d9e"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: parquet/parquet_support.rs: FileTooLong \u2014 660 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), declaring 33 free functions. The bar is 500 significant lines; this is 160 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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e910ee5aee21c5d3cbd093238d2598c6c9e5f1a2b436b2d7e7b0a95d639ba057"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::parquet::parquet_support::parquet_convert_array_impl: FunctionTooLong \u2014 datafusion_comet::parquet::parquet_support::parquet_convert_array_impl runs 131 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 31 over it, 1.31\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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d0ce093e851461d531ed519671c15577e19c820538f2aa030f006c912cef767"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: src/error.rs: FileTooLong \u2014 648 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted), about 90% of them inside a single declaration: SparkError (3 blocks, 23-1040). The bar is 500 significant lines; this is 148 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":"native/common/src/error.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ecab391c48a51a8a768628f1b83f242d0a5bab21c55ae0863ba4638fe87c856"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_binary_expr_with_options: MethodTooLong \u2014 create_binary_expr_with_options runs 128 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 28 over it, 1.28\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":"native/core/src/execution/planner.rs"},"region":{"startLine":1391}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c58b6162f6b81fb11e121dbdedb5ffedaa4b7f09747816bdba24330a4f29573"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: RssPartitionWriter.compact_array: MethodTooLong \u2014 compact_array runs 128 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 28 over it, 1.28\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":926}}}],"partialFingerprints":{"codehealthFindingId/v1":"57a7a2893f0130bac3f7864317514929ee54fdd664de04202f5edb044e78ac9a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: planner/join.rs: FileTooLong \u2014 639 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 139 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":"native/core/src/execution/planner/join.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b33bfd4f73cce04f5c2204ef70e252f4a2f6821406049bc02feda0c787eaaef"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: MultiPartitionShuffleRepartitioner.partitioning_batch: MethodTooLong \u2014 partitioning_batch runs 126 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 26 over it, 1.26\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":"native/shuffle/src/partitioners/multi_partition.rs"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"08445e93601673681fc13411f93349744d44832484b97924a071746e48488cbc"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: src/explode.rs: FileTooLong \u2014 613 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 113 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":"native/operators/src/explode.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2436b2c13576857bdd6e4fe212c86bbe567a75e80f1f1dc80c4c6893f777d1a5"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::execution::planner::literal_to_array_ref: FunctionTooLong \u2014 datafusion_comet::execution::planner::literal_to_array_ref runs 122 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/core/src/execution/planner.rs"},"region":{"startLine":2803}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ee67774955ecbfd68790ca562b929a3635519f2f4acccfda16a479a7c012a08"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner: FunctionTooLong \u2014 datafusion_comet_spark_expr::array_funcs::arrays_zip::arrays_zip_inner runs 119 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 19 over it, 1.19\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":"native/spark-expr/src/array_funcs/arrays_zip.rs"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8c22d002625f6cb036813121f8c8a3d7f49ce743ba47c1738691cd337848512"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: objectstore/s3.rs: FileTooLong \u2014 594 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 94 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":"native/core/src/parquet/objectstore/s3.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b88c5bb52eb6595b8fd2af409a3358f88eaa9621133bb6645bc611cd1ecefe1"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: MergeRowsBuilder.build: MethodTooLong \u2014 build runs 117 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 17 over it, 1.17\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":"native/core/src/execution/planner/merge_rows.rs"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"0de69952cf01b6bda0daf2843a96e9859458c266b42e71dcb3ec982995ae17ec"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::conversion_funcs::numeric::spark_cast_nonintegral_numeric_to_integral: FunctionTooLong \u2014 datafusion_comet_spark_expr::conversion_funcs::numeric::spark_cast_nonintegral_numeric_to_integral runs 116 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/spark-expr/src/conversion_funcs/numeric.rs"},"region":{"startLine":1179}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f9ebbfb4d5c9be3a96b6d1c6a2acefebd78b7ae77c475b03af8dde3d87b573a"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: comet/CometWindowExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fb708be058b880a49f8d636e014055f6586e40d9df68a45010af034e757b885"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: shuffle/CometCelebornShuffleReader.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c247958cb9fdcee419bb5e274706bda38fb66a2546c7bbb024680425f837584"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: src/errors.rs: FileTooLong \u2014 572 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). 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":"native/jni-bridge/src/errors.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"32a6c895b75942776ec203d545956f4f95feec0f88f56465059588c7802fa5be"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: conditional_funcs/case_when.rs: FileTooLong \u2014 568 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 68 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":"native/spark-expr/src/conditional_funcs/case_when.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7b9f4cde612a7ffe51d9085bb3534f822dc3691cad82ec34bbfca967f3b698b"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2: FunctionTooLong \u2014 datafusion_comet_spark_expr::static_invoke::char_varchar_utils::read_side_padding::spark_read_side_padding2 runs 113 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 13 over it, 1.13\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":"native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f608278adfe78579b98f2060ff037ca57a15fc95b476db303b46825e98685f8"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.create_scalar_function_expr: MethodTooLong \u2014 create_scalar_function_expr runs 111 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 11 over it, 1.11\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":"native/core/src/execution/planner.rs"},"region":{"startLine":2084}}}],"partialFingerprints":{"codehealthFindingId/v1":"df3b605bbcf6c34926ca22d7d16829282369703efe5347ff05d638686d42bc20"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: serde/strings.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":"spark/src/main/scala/org/apache/comet/serde/strings.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"310829d6bddc7f11cdaae8ac815c8a5d5f7628f7a0b5962d56184dac3bfcd67e"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: CelebornShufflePartitionPusher.pushClaimedPartitionData: MethodTooLong \u2014 pushClaimedPartitionData 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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":532}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3c7e3b697403ec02148c6ffb45f711310058368d788d24e76cd036145820232"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: ExplodeBuilder.build: MethodTooLong \u2014 build runs 108 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/core/src/execution/planner/explode.rs"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"00e8944f584f8c345ab6aa582fdb81bcc978607f5fe0eb6ada8e82602f7cc83e"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold: FunctionTooLong \u2014 datafusion_comet_spark_expr::string_funcs::levenshtein::levenshtein_distance_with_threshold runs 108 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"62bea6f2c684ea40bd2130e83cd7edd83b3cb5fc9ce0b5328d203dd745e043a2"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: QueryPlanSerde: 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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"0367af6857c9e3125301c3b7f88bfdd5eb6d3b6b8f15a8c4c57ac733c964600b"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: PhysicalPlanner.parse_join_parameters: MethodTooLong \u2014 parse_join_parameters runs 105 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 5 over it, 1.05\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":"native/core/src/execution/planner/join.rs"},"region":{"startLine":652}}}],"partialFingerprints":{"codehealthFindingId/v1":"743f903a4fd8023f5e5d812eae083165e775407d8035164bf83b7b4d85b95c31"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SparkPhysicalExprAdapter.replace_with_spark_cast: MethodTooLong \u2014 replace_with_spark_cast runs 105 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 5 over it, 1.05\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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":1421}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad05aa09a12406fae9cf4c76536190e73fa2f7c998e593c9d099163df33eea62"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: WideDecimalBinaryExpr.evaluate: MethodTooLong \u2014 evaluate runs 105 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 5 over it, 1.05\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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"de7bdcc3eee349c7751fbaeb457ced8fd43b610c5b1231f225b490d95e91edc8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: comet/CometExecIterator.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":"spark/src/main/scala/org/apache/comet/CometExecIterator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0345d7b76f00694b11e48e30af1c18849488be48576733f1fa7986732bc3f53b"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein: FunctionTooLong \u2014 datafusion_comet_spark_expr::string_funcs::levenshtein::spark_levenshtein runs 104 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 4 over it, 1.04\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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f5a223c5713b0cb40dda10d0056c21b930c4589148230177cbd3fd0f21798e3"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::execution::delta_dv::attach_access_plan: FunctionTooLong \u2014 datafusion_comet::execution::delta_dv::attach_access_plan runs 103 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/core/src/execution/delta_dv.rs"},"region":{"startLine":610}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7c75933a632d2a58597fa88a86aebc67c15223e947493f2e5533a5462a49cdf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: string_funcs/get_json_object.rs: FileTooLong \u2014 513 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted). The bar is 500 significant lines; this is 13 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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"34962bffc62bba20e3bd870edabedb2747c0430e8c649bcedbe8476ffe6b0a2f"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet::execution::operators::iceberg_write::run_write_task: FunctionTooLong \u2014 datafusion_comet::execution::operators::iceberg_write::run_write_task runs 102 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/core/src/execution/operators/iceberg_write.rs"},"region":{"startLine":975}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5a0781cd3fb58d89c4232be9aec316b3fd4c21485db051f57a03fbff64c084a"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: EagerPageIndexReader.get_metadata: MethodTooLong \u2014 get_metadata runs 102 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) 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":"native/core/src/parquet/eager_page_index_reader_factory.rs"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"002c708b5dd41b657c7cd0085ffe73a0ea19e866931f5bc61271b089fd96e48c"}},{"ruleId":"D3","level":"warning","message":{"text":"FunctionTooLong: datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string: FunctionTooLong \u2014 datafusion_comet_spark_expr::conversion_funcs::cast::cast_binary_to_string runs 101 significant lines (blank, comment-only and punctuation-only lines excluded, and inline test code \u2014 #[cfg(test)] modules and bare #[test] functions \u2014 not counted) in one body. The bar is 100 significant lines; this is 1 over it, 1.01\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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":898}}}],"partialFingerprints":{"codehealthFindingId/v1":"f532c5b193161a66ebb127b3302e2a44b130f47c1d8f49c2c9793d15ad287bab"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (159 shared lines): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:72-412 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:85-435 \u2014 These two members are variants of one another: 159 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"da5ca547f83d3928539d0be9619196f5a6cff1a8ac951d0e95750984600bd94a"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (72 shared lines): native/shuffle/src/spark_unsafe/row.rs:379-598 | native/shuffle/src/spark_unsafe/row.rs:832-1065 \u2014 These two members are variants of one another: 72 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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a9a400a4b6fc793fc77560553d672e8dba000ea508a626ef4134861ae16fa2c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): native/core/src/cloud/s3/credential_bridge.rs:228-264 | native/core/src/cloud/s3/credential_bridge.rs:310-341 \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":"native/core/src/cloud/s3/credential_bridge.rs"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"652f0b6b84f7cad22b43c739cb174ce92c72e6d0b89c1281140cbd0f3b414807"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): native/spark-expr/src/array_funcs/array_position.rs:136-159 | native/spark-expr/src/array_funcs/array_position.rs:170-196 | native/spark-expr/src/array_funcs/array_position.rs:204-233 | native/spark-expr/src/array_funcs/array_position.rs:241-264 | native/spark-expr/src/array_funcs/array_position.rs:272-301 \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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"b816f8e22da5eb597d471b76b9c02793934dacfde9af2ee462ff0b680a7666f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1134-1156 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1239-1261 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1295-1317 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1353-1379 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1651-1676 \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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":1134}}}],"partialFingerprints":{"codehealthFindingId/v1":"c66e94541447a2652cd344565faddb04efece8d2b0af78c590e7c5037e9f5203"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): native/spark-expr/src/agg_funcs/correlation.rs:220-244 | native/spark-expr/src/agg_funcs/correlation.rs:362-389 | native/spark-expr/src/agg_funcs/regr.rs:354-376 | native/spark-expr/src/agg_funcs/regr.rs:477-492 \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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"52cfdc9dd790acd1039a6161580390f05ba67ddc5a5993a9e66bd012c5b1e236"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): native/spark-expr/src/array_funcs/array_contains.rs:65-91 | native/spark-expr/src/array_funcs/array_remove.rs:67-90 | native/spark-expr/src/array_funcs/sort_array.rs:75-103 | native/spark-expr/src/array_funcs/sort_array.rs:141-170 \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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"17036e80974fc345813bbff689966cfa7ff8581c6dc6fc14136e416a0c7e0100"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): native/spark-expr/src/math_funcs/checked_arithmetic.rs:327-429 | native/spark-expr/src/math_funcs/div.rs:79-178 | native/spark-expr/src/math_funcs/modulo_expr.rs:90-119 | native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:181-336 \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":"native/spark-expr/src/math_funcs/checked_arithmetic.rs"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"452da13ab58c55b8387176840a305e62c8771f2997df13f48a3621141d4d1871"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): native/spark-expr/src/string_funcs/split.rs:319-341 | native/spark-expr/src/string_funcs/split.rs:346-364 | native/spark-expr/src/string_funcs/split.rs:369-387 | native/spark-expr/src/string_funcs/split.rs:392-414 \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":"native/spark-expr/src/string_funcs/split.rs"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"66abc14eeef31cd6aeff1e9a5acf436f0bbfe66c8db8ea8eb0507453320ee663"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:416-543 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:549-566 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:569-591 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:596-610 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"be88a6bcc20d013a731877f45550b2a7f536bb97e540c035cc0d231627b78620"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): spark/src/main/spark-3.5/org/apache/comet/iceberg/IcebergDeltaLogicalShim.scala:28-46 | spark/src/main/spark-4.0/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 | spark/src/main/spark-4.1/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 | spark/src/main/spark-4.2/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 \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":"spark/src/main/spark-3.5/org/apache/comet/iceberg/IcebergDeltaLogicalShim.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"91f889b24be28c6b6f6fde3dd4b49ff3cd3211bbc86003e1f0820b1683c61cc2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (78 corresponding lines): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:59-136 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:59-136 \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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d3d2562d05da796e3b001f868572c3111ea95c7dea8ec4a9a92ecfd5ac57112"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (48 corresponding lines): native/spark-expr/src/math_funcs/ceil.rs:34-81 | native/spark-expr/src/math_funcs/floor.rs:34-81 \u2014 These two members are one piece of code written twice and then edited apart: 48 consecutive lines correspond almost exactly, broken only by small local edits. Most of that correspondence is NOT reported as duplicated blocks below \u2014 the edits cut it into fragments and only the largest of them clear the block floor, so the rows below understate it. The repair is at the members\u0027 grain \u2014 factor the shared implementation into one the two call with their differences as parameters or as an injected step, or, where the difference is systematic (an extra return value, one transport against another), generate one from the other. Left alone, the next edit has to be made twice and the two will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/math_funcs/ceil.rs"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"8cf5051538b6f727ec33f6f61af764f6959be7c1eb8700ad0d6ac9e52e9bc38a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 64\u002B corresponding lines): native/spark-expr/src/agg_funcs/sum_int.rs:590-653 | native/spark-expr/src/agg_funcs/sum_int.rs:736-804 | native/spark-expr/src/agg_funcs/sum_int.rs:899-975 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 64 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":590}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1d459695c9c1d1f3e0ea7867dfc3b6e1e985c6f33d970b5c2d323bc6e78e2d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 59\u002B corresponding lines): native/spark-expr/src/datetime_funcs/make_date.rs:196-266 | native/spark-expr/src/datetime_funcs/make_time.rs:103-161 | native/spark-expr/src/datetime_funcs/next_day.rs:98-162 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 59 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":"native/spark-expr/src/datetime_funcs/make_date.rs"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"46e1bc0bcf2722c3eb7428e11986fc09fd1aac61de98e544b0a8e9b90493a25f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (63 corresponding lines): native/spark-expr/src/conversion_funcs/string.rs:372-434 | native/spark-expr/src/conversion_funcs/string.rs:443-507 \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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"05e59e3b328efa5a09b9cfa59ffbb84251d91edfca37f8cb171a83c744b12688"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): native/spark-expr/src/hash_funcs/murmur3.rs:28-69 | native/spark-expr/src/hash_funcs/xxhash64.rs:56-101 \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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9a78f92120150a6f71e2305d9f5f64964731ab1d08c04ab5798cb1c4c54d70b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (42 corresponding lines): native/core/src/execution/c_udf/mod.rs:77-119 | native/core/src/execution/c_udf/mod.rs:137-178 \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":"native/core/src/execution/c_udf/mod.rs"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea2dd9127f97d8a404747ce8b077ef7cc66f1d6bc01677b22a05a05a1540fa8f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (40 corresponding lines): native/spark-expr/src/agg_funcs/sum_int.rs:300-339 | native/spark-expr/src/agg_funcs/sum_int.rs:371-410 \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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":300}}}],"partialFingerprints":{"codehealthFindingId/v1":"66f540c1ea948e921d313b1050964d7722a5d619ede86bf4d71d4f48c6d3fc35"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (41 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:193-234 | native/spark-expr/src/agg_funcs/covariance.rs:236-276 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cdabf60ee53b0ab29830ed96e8bb7e5e9cf9686f214e557acfe626e09b516b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (29 corresponding lines): native/spark-expr/src/array_funcs/array_contains.rs:170-198 | native/spark-expr/src/array_funcs/array_contains.rs:205-233 \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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fc7299f52c0084f3b328cb2f7e8566b37ba8f07996f7978e369260e0e413de3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (50 corresponding lines): native/spark-expr/src/agg_funcs/sum_int.rs:521-570 | native/spark-expr/src/agg_funcs/sum_int.rs:1016-1067 \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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":521}}}],"partialFingerprints":{"codehealthFindingId/v1":"8cea61144282e45496b1814f8b9138a5de1f5c2c088d148cda583e35dfc6c6ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): native/spark-expr/src/hash_funcs/murmur3.rs:143-174 | native/spark-expr/src/hash_funcs/xxhash64.rs:172-203 \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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"63fcbd383ffc7a24e2661ea12b3760c6f5b4bbfde3b369510bf1d9dc59a9715a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): native/spark-expr/src/agg_funcs/avg.rs:240-275 | native/spark-expr/src/agg_funcs/avg_decimal.rs:455-484 \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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f19671d22c965851fed2e5229ed2dff460b9175dedf838bcf467b1060f6214b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:378-411 | native/spark-expr/src/agg_funcs/covariance.rs:418-447 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":378}}}],"partialFingerprints":{"codehealthFindingId/v1":"66b998d8910b26ceeb798a724590b5d09226f34b0d22b6546d304525c510f287"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (31 corresponding lines): spark/src/main/scala/org/apache/comet/serde/conditional.scala:65-97 | spark/src/main/scala/org/apache/comet/serde/conditional.scala:104-134 \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":"spark/src/main/scala/org/apache/comet/serde/conditional.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e68efd8105146736e4f477b5e2c152902d377aadbfac882bf4279e8a8da795b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (25 corresponding lines): spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala:40-64 | spark/src/main/spark-4.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala:40-69 \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":"spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"94fb9c1385db860e374ee89fbfb0b1563a6bbedcecf5e6b19e3e330b7a7e4d80"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): spark/src/main/java/org/apache/comet/vector/CometPlainVector.java:137-166 | spark/src/main/java/org/apache/comet/vector/CometPlainVector.java:169-192 \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":"spark/src/main/java/org/apache/comet/vector/CometPlainVector.java"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"160961ddf83b6c909484e8d9a9c1d53b3850e93218ef1f16aae2a193b082f89c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 30\u002B corresponding lines): native/spark-expr/src/conversion_funcs/string.rs:1184-1227 | native/spark-expr/src/conversion_funcs/string.rs:1233-1266 | native/spark-expr/src/conversion_funcs/string.rs:1271-1300 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 30 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1184}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e12fc21edaa627c1191eb895734838307008f42ee8e821b6105191a05376af5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (27 corresponding lines): native/spark-expr/src/math_funcs/signum.rs:26-52 | native/spark-expr/src/math_funcs/sqrt.rs:26-52 \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":"native/spark-expr/src/math_funcs/signum.rs"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"67e277ece1eb1ef0aca5a6688b0b3025a81b9db0e79369b5da19babc2dcd7656"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): native/spark-expr/src/agg_funcs/sum_int.rs:679-704 | native/spark-expr/src/agg_funcs/sum_int.rs:830-859 \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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":679}}}],"partialFingerprints":{"codehealthFindingId/v1":"46baa02335b31cd103191e531c173c4aa6ff10d82f35657ea9ed762d150164fd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/spark-expr/src/float_semantics/kernels.rs:205-223 | native/spark-expr/src/float_semantics/kernels.rs:227-247 \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":"native/spark-expr/src/float_semantics/kernels.rs"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"b20e1b8289353813a8feab50caeea97931e3a8c62893b3fb2da0a46466cb2826"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): spark/src/main/scala/org/apache/comet/serde/operator/CometSink.scala:56-92 | spark/src/main/scala/org/apache/comet/serde/operator/CometSink.scala:125-154 \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":"spark/src/main/scala/org/apache/comet/serde/operator/CometSink.scala"},"region":{"startLine":56}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4f509c05f608a9c4f1267c527847525d981156a60d13cef6c613728c8f76935"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): native/core/src/execution/operators/scan.rs:368-393 | native/core/src/execution/operators/shuffle_scan.rs:373-407 \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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":368}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ed028ca1a491c7ece651ee06e1aedcd23fd9a7281b7660cc4cbbc42c6ccd92e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala:1248-1268 | spark/src/main/scala/org/apache/comet/serde/arithmetic.scala:153-176 \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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":1248}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c0d624653bd77378db87614ac68ef32f4dd648aeff85a30426c4372b187a104"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (37 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala:529-565 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala:586-628 \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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a77bf6e7c59505857ed9a56feba447df118b64505af6d10a67c0c6cea9fc546"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): native/spark-expr/src/agg_funcs/correlation.rs:183-201 | native/spark-expr/src/agg_funcs/correlation.rs:203-218 \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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":183}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a1569488f9b03511dc74e7519f1b66aeacfd9fa121443e72f8a0bbf2a290382"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (30 corresponding lines): spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala:447-477 | spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala:483-512 \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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":447}}}],"partialFingerprints":{"codehealthFindingId/v1":"03fa57760257da617d57325b134cf544785b376c79420d19557dbeb2d89a3401"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (32 corresponding lines): native/jni-bridge/src/output_stream_sink.rs:116-152 | native/jni-bridge/src/shuffle_partition_pusher.rs:251-282 \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":"native/jni-bridge/src/output_stream_sink.rs"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"2974cfe9aa441564731e3253d7f619f5e6e8a79ded9e6c4bad0c913063604fee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): native/spark-expr/src/agg_funcs/collect.rs:307-326 | native/spark-expr/src/agg_funcs/collect.rs:653-672 \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":"native/spark-expr/src/agg_funcs/collect.rs"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fe11f76ef26e76611195de6fd82999764e5cb8fbb4aa77e68964b9baa25447d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/spark-expr/src/agg_funcs/approx_percentile.rs:360-378 | native/spark-expr/src/agg_funcs/approx_percentile.rs:385-412 \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":"native/spark-expr/src/agg_funcs/approx_percentile.rs"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3b1979ad10e39ef3970adf90ef5e7d98ada796580b02b3ce860de76102928a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): native/core/src/execution/operators/iceberg_partition_path.rs:278-299 | native/spark-expr/src/kernels/temporal.rs:407-423 \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":"native/core/src/execution/operators/iceberg_partition_path.rs"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"32c066eb79fb6c09f658926d09ebc37b0c29876e553e6f61be3f8f7479403d87"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:278-303 | native/spark-expr/src/agg_funcs/variance.rs:220-241 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":278}}}],"partialFingerprints":{"codehealthFindingId/v1":"a08374e0c937cc00ef31615cc21be27a5694f6faa2a211982c668342859576d9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): dev/ci/linux-test-profiles.py:69-88 | dev/ci/spark-sql-modules.py:149-164 \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":"dev/ci/linux-test-profiles.py"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fff103e817583ad711826e55800bab32c604a294a6ac6bc18f6a5960d7d219f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): spark/src/main/scala/org/apache/comet/serde/arithmetic.scala:188-213 | spark/src/main/scala/org/apache/comet/serde/arithmetic.scala:244-269 \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":"spark/src/main/scala/org/apache/comet/serde/arithmetic.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8194ec6cf1290cd5d2f1c82764f6c27b91587a79ef5c9ec099969611970bf1b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 16\u002B corresponding lines): native/core/src/execution/expressions/temporal.rs:46-62 | native/core/src/execution/expressions/temporal.rs:73-89 | native/core/src/execution/expressions/temporal.rs:100-116 | native/core/src/execution/expressions/temporal.rs:127-144 | native/core/src/execution/expressions/temporal.rs:178-193 \u2014 These 5 members are one piece of code written 5 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 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/expressions/temporal.rs"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"94b2fcb3dea3a7c5b67eb2e15ceb681ef4b0b80c2771b6ac5d4ebc08b21f8390"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): native/spark-expr/src/conditional_funcs/case_when.rs:695-713 | native/spark-expr/src/conditional_funcs/case_when.rs:716-732 \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":"native/spark-expr/src/conditional_funcs/case_when.rs"},"region":{"startLine":695}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba357f4277b8a9b1b3bc2859f76573ff6a3f38bdc9ecaa7bf52134044df3f17f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): native/core/src/execution/operators/scan.rs:131-151 | native/core/src/execution/operators/shuffle_scan.rs:133-158 \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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc8fe5786be1daff137fb0448c8461b9f837894d036f53fb9bac91d4baa764f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): native/spark-expr/src/agg_funcs/hll_plus_plus.rs:298-313 | native/spark-expr/src/agg_funcs/hll_plus_plus.rs:409-426 \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":"native/spark-expr/src/agg_funcs/hll_plus_plus.rs"},"region":{"startLine":298}}}],"partialFingerprints":{"codehealthFindingId/v1":"b4b29f5d8500f170f9b5bfe55df090518292462a51108df8fb07c50f7b2d109e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): native/spark-expr/src/agg_funcs/percentile.rs:580-593 | native/spark-expr/src/agg_funcs/percentile.rs:604-622 \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":"native/spark-expr/src/agg_funcs/percentile.rs"},"region":{"startLine":580}}}],"partialFingerprints":{"codehealthFindingId/v1":"d12e73504b0a8a30a35062ec082f83dc6de6180be736ffe69e05a833f4c417b7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/spark-expr/src/conversion_funcs/cast.rs:803-826 | native/spark-expr/src/math_funcs/checked_binary_expr.rs:96-114 \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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":803}}}],"partialFingerprints":{"codehealthFindingId/v1":"c97694c3a09ff19af140c6f646ca5126bf4f4719fe58d7a00888e1b5379c0d61"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): native/spark-expr/src/array_funcs/array_position.rs:39-62 | native/spark-expr/src/array_funcs/arrays_zip.rs:122-147 \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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"94ec0f41c9b023239d4c253b05c3a6dcd69619390f37b15fee18ff770acf541c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (24 corresponding lines): native/spark-expr/src/utils.rs:273-297 | native/spark-expr/src/utils.rs:300-323 \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":"native/spark-expr/src/utils.rs"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"09eacf394c217ebb678a68b3bed79ca04e6048287f3f3a66ba0b8b1eb4d2c20a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 22\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/aggregates.scala:550-572 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:899-920 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:936-964 \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":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":550}}}],"partialFingerprints":{"codehealthFindingId/v1":"285009ce80e80e3308b46349663858186d802f050320b0b9e8ad13a7b6d69ea8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): native/core/src/execution/planner/delta_scan.rs:79-106 | native/core/src/execution/planner/lance_scan.rs:47-66 \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":"native/core/src/execution/planner/delta_scan.rs"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"77bec6858cd692afa7764f2f5b93148a06aae1811df265a4cf2bc68890942290"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/common/src/utf8.rs:249-269 | native/shuffle/src/remote_schema.rs:167-185 \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":"native/common/src/utf8.rs"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"258cbcd8a096e599bfb33bdfcc3319225af1ed0a82fe60883c48f360b876e746"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:454-465 | native/spark-expr/src/agg_funcs/variance.rs:392-401 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":454}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d7964df9831f45c4b224489b170a0fa6fa1860f8af5cbdc8eb620a2996f2ad5"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/spark-expr/src/math_funcs/pow.rs:107-117 | native/spark-expr/src/math_funcs/pow.rs:119-129 \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":"native/spark-expr/src/math_funcs/pow.rs"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e0cf098e38335edf407e6cff77e20fa4bdbd691f6d24e292a219aa7dd88eb34"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/spark-expr/src/string_funcs/split.rs:553-570 | native/spark-expr/src/string_funcs/split.rs:572-584 \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":"native/spark-expr/src/string_funcs/split.rs"},"region":{"startLine":553}}}],"partialFingerprints":{"codehealthFindingId/v1":"424b85c46e19178365081737b01f88f36c46cb86d5b7c37ee6d956eb3d33e8d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (6 members, 21\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/aggregates.scala:55-76 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:96-117 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:438-458 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:479-499 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:520-540 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:1261-1282 \u2014 These 6 members are one piece of code written 6 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 6 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e06fcf6933e0c92dfbc44868f7a0b5f0a1b699f3c566f222fa4cbc502ea31c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/core/src/execution/spark_aggregate_state.rs:262-286 | native/core/src/execution/spark_aggregate_state.rs:294-312 \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":"native/core/src/execution/spark_aggregate_state.rs"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"14344374717c0025c8aca110bbc4930d9b4cb514689b6ab47f5fb39505cbc6bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (18 corresponding lines): spark/src/main/spark-4.x/org/apache/comet/serde/CometHllSketchAgg.scala:79-97 | spark/src/main/spark-4.x/org/apache/comet/serde/CometHllUnionAgg.scala:64-81 \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":"spark/src/main/spark-4.x/org/apache/comet/serde/CometHllSketchAgg.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"fed9dbc0bab0f124515bf6581243f8302647182061daa446506b5de971f109c0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/core/src/execution/operators/iceberg_write.rs:2002-2015 | native/core/src/execution/operators/iceberg_write.rs:2019-2031 \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":"native/core/src/execution/operators/iceberg_write.rs"},"region":{"startLine":2002}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ca4f45ee58e3495f47ed644e8e39814f48b35599915b2793c21f7c172d729f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (8 members, 17\u002B corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:174-190 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:192-208 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:210-226 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:228-244 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:246-262 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:264-280 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:282-298 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala:303-319 \u2014 These 8 members are one piece of code written 8 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 8 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowCachedBatchSerializer.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"e30b3dc8f90419c94bf3d492e9711c1bd7b792f82d77861b6bb4e498b03b8e9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/spark-expr/src/array_funcs/array_contains.rs:94-104 | native/spark-expr/src/array_funcs/array_remove.rs:93-103 \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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b90517dceb4608fd99aeaa17c13136302d8ba199012420241d78e1e81bfd02f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): native/spark-expr/src/bloom_filter/spark_bloom_filter.rs:178-197 | native/spark-expr/src/bloom_filter/spark_bloom_filter.rs:204-228 \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":"native/spark-expr/src/bloom_filter/spark_bloom_filter.rs"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"93ee18435e62f0e831e7f98b83b3f0bc4a82c388c546e8b865f77f9a9ce9dc0a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/string_funcs/regexp_extract_all.rs:179-185 | native/spark-expr/src/string_funcs/regexp_extract_all.rs:187-198 \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":"native/spark-expr/src/string_funcs/regexp_extract_all.rs"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"8272c9e098a681de873484ae5db6ef6dc557a684638d534deda04cce5e041dee"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 16\u002B corresponding lines): spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:442-457 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:460-475 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:478-494 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:497-513 \u2014 These 4 members are one piece of code written 4 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 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":442}}}],"partialFingerprints":{"codehealthFindingId/v1":"2581c7989a7759283750d1cfc0efb16329331160a20bf1644685737830c7b4ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 23\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/aggregates.scala:323-347 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:360-382 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:395-417 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:1427-1449 \u2014 These 4 members are one piece of code written 4 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 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"51f3abb53746aab3e945f8b436eda1d78d4d74f9bcf163a862527527810f4df2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/spark-expr/src/agg_funcs/avg.rs:323-335 | native/spark-expr/src/agg_funcs/avg_decimal.rs:580-595 \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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf3acad95f485531618fabe1ef1723470ab1da1cf7b6eba3779ef4971acc8f19"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:711-723 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1865-1876 \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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":711}}}],"partialFingerprints":{"codehealthFindingId/v1":"e87ec367f499cd8932b28f6f7fb7e73a7e3747b0370ff696b6cb93c51c2b9523"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): spark/src/main/scala/org/apache/comet/serde/aggregates.scala:603-622 | spark/src/main/scala/org/apache/comet/serde/aggregates.scala:654-674 \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":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":603}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa309d5b5c0d43e46bbcc578288c8a6d1cf185793886c0fc9eebe38df4e78feb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/comet-udf-sdk/src/c_abi.rs:460-474 | native/comet-udf-sdk/src/c_abi.rs:655-670 \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":"native/comet-udf-sdk/src/c_abi.rs"},"region":{"startLine":460}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d3c3e46b2f40c00ffce5fb868de1ceaee8c0e08e82155649fb8f6aaaa7a950e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (20 corresponding lines): native/spark-expr/src/agg_funcs/avg_decimal.rs:111-130 | native/spark-expr/src/agg_funcs/avg_decimal.rs:162-184 \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":"native/spark-expr/src/agg_funcs/avg_decimal.rs"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed0a58c8abfcf4a33319bd6953d69fc08b16161fefbc8143cb4e18738f09a3a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/spark-expr/src/agg_funcs/hll_plus_plus.rs:384-402 | native/spark-expr/src/agg_funcs/list_agg.rs:288-302 \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":"native/spark-expr/src/agg_funcs/hll_plus_plus.rs"},"region":{"startLine":384}}}],"partialFingerprints":{"codehealthFindingId/v1":"741afe1cca87b8621df3052ffc799b1c572e05204de7c3cfac3572f2a5887140"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/spark-expr/src/string_funcs/levenshtein.rs:355-365 | native/spark-expr/src/string_funcs/levenshtein.rs:372-386 \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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":355}}}],"partialFingerprints":{"codehealthFindingId/v1":"8140aa9e8d19822f5e11f0ccbecf911fc19432c9b00112a01fffeabb0dbe37d6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): native/core/src/execution/operators/iceberg_location_scoped.rs:318-337 | native/core/src/parquet/objectstore/location_scoped.rs:113-129 \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":"native/core/src/execution/operators/iceberg_location_scoped.rs"},"region":{"startLine":318}}}],"partialFingerprints":{"codehealthFindingId/v1":"153e44f85721c3717a1354d8978e2b1256a4fdd28e99a75177f76072c9030fc4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 19\u002B corresponding lines): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:138-156 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:138-156 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"d96157619a88e7838ce8c6e203636fb20398bf2e5d2a4626182b0d6d71915eab"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (22 corresponding lines): native/spark-expr/src/datetime_funcs/to_time.rs:244-265 | native/spark-expr/src/datetime_funcs/to_time.rs:270-298 \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":"native/spark-expr/src/datetime_funcs/to_time.rs"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf28e38ca31e869d66ecc8206dc378cc1dd2259b183792ec121d686d15a13811"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (21 corresponding lines): spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:1057-1078 | spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:1104-1124 \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":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":1057}}}],"partialFingerprints":{"codehealthFindingId/v1":"c14f3acf36c446ee3db7c9227b9c863e89e7f8264b063981d081f1bc4d7da4c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 18\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/datetime.scala:178-195 | spark/src/main/scala/org/apache/comet/serde/datetime.scala:206-223 | spark/src/main/scala/org/apache/comet/serde/datetime.scala:234-251 | spark/src/main/scala/org/apache/comet/serde/datetime.scala:294-312 | spark/src/main/scala/org/apache/comet/serde/datetime.scala:727-750 \u2014 These 5 members are one piece of code written 5 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 5 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"3866f38f58ee66c70089589c193b4d78fa9944ecae3a969a6999afbee5aaea81"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala:307-318 | spark/src/main/scala/org/apache/spark/sql/comet/CometWriteFilesExec.scala:521-534 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"9340dc11dd52ee0686b64b666572f9d71fcbc3db652eabd571b5964b7fb1ca3f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/core/src/execution/operators/scan.rs:260-275 | native/core/src/execution/operators/shuffle_scan.rs:332-346 \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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"aef89cf7bc651231b97db18f1c29a199c1c0bbc4f7680371a3e0a2d68e0aa789"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/spark-expr/src/agg_funcs/mode.rs:297-311 | native/spark-expr/src/agg_funcs/mode.rs:382-397 \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":"native/spark-expr/src/agg_funcs/mode.rs"},"region":{"startLine":297}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa9eeeeecd6b1abc5437fe896f7f6810be5226d9ed74890be3c55f97f2100edd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): spark/src/main/scala/org/apache/comet/serde/arrays.scala:46-59 | spark/src/main/scala/org/apache/comet/serde/arrays.scala:246-260 \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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"81051a32df41704cb8b7beeb6c5aee7a1059785f47b15fca71a5edf883cadc51"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/spark-expr/src/agg_funcs/variance.rs:192-204 | native/spark-expr/src/agg_funcs/variance.rs:206-218 \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":"native/spark-expr/src/agg_funcs/variance.rs"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"efbb3bc294e82381bf74d2bc25233eab1f528fdbadd3d4d2f28d197e3c475d73"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): spark/src/main/scala/org/apache/comet/serde/hash.scala:37-46 | spark/src/main/scala/org/apache/comet/serde/hash.scala:59-72 \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":"spark/src/main/scala/org/apache/comet/serde/hash.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff308cb484808b3739fefe2632488f846aa4e2fa0a523c6d8c8eadd959539f34"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.scala:180-191 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:1895-1911 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:2772-2787 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.scala"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"1453ca3951de22a2bd9c025525149e53449ea511f6272c8dcd3aa01c4f8ae97d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): spark/src/main/scala/org/apache/spark/Plugins.scala:380-394 | spark/src/main/scala/org/apache/spark/Plugins.scala:396-411 \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":"spark/src/main/scala/org/apache/spark/Plugins.scala"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"c52a4cab65d4bc83ff2ee2db55cab6431c3486d341b6bfa4762d9a7a8d86800e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/core/src/execution/expressions/strings.rs:45-51 | native/core/src/execution/expressions/temporal.rs:155-167 \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":"native/core/src/execution/expressions/strings.rs"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"d383ca0fdc537bf450986b8136dcd52f98b3f2c5c16150403b6eea116e057fc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 14\u002B corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3172-3185 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3465-3480 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3619-3635 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3850-3864 \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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":3172}}}],"partialFingerprints":{"codehealthFindingId/v1":"188caa926fb080d0a6555a1308a703344216ce43898044e57ffa68cc74901e63"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala:36-46 | spark/src/main/spark-4.1\u002B/org/apache/comet/shims/CometExprShim.scala:40-49 \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":"spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e31e49d7781520b7521eb34d4a47d044cd0a717d58e6a0f6eb9c13f8b3468e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/spark-expr/src/array_funcs/size.rs:30-45 | native/spark-expr/src/json_funcs/json_array_length.rs: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":"native/spark-expr/src/array_funcs/size.rs"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e582b08500c41702f6f9d2782b57fab62786e32bcdef5a561cb69800c01e8c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): native/core/src/parquet/datetime_rebase.rs:162-170 | native/spark-expr/src/conversion_funcs/string.rs:1465-1472 \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":"native/core/src/parquet/datetime_rebase.rs"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4bc6da7108ef8a199b4e1f7ac0bd6b3a771bb3fd75c552078ca00edb26c76d8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): native/core/src/parquet/objectstore/location_scoped.rs:234-243 | native/core/src/parquet/objectstore/location_scoped.rs:245-254 \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":"native/core/src/parquet/objectstore/location_scoped.rs"},"region":{"startLine":234}}}],"partialFingerprints":{"codehealthFindingId/v1":"a17bc472f29d827485a1a0deaac14fcf4fa37453fe41a46d9871c74032639b2c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 7\u002B corresponding lines): native/spark-expr/src/agg_funcs/min_max.rs:79-85 | native/spark-expr/src/agg_funcs/min_max.rs:102-112 | native/spark-expr/src/agg_funcs/min_max.rs:114-124 \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":"native/spark-expr/src/agg_funcs/min_max.rs"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3ae0dea3dbc4bd54880fb8b597fef6ed4ce5ff204d0cec0069d934404e9e0eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): native/spark-expr/src/conversion_funcs/numeric.rs:945-961 | native/spark-expr/src/conversion_funcs/numeric.rs:969-983 \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":"native/spark-expr/src/conversion_funcs/numeric.rs"},"region":{"startLine":945}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c57626b672b816ba85c0c609a364155ed66a8b3417b7d9713a9fae142d7a470"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometBroadcastExchangeExec.scala:251-263 | spark/src/main/scala/org/apache/spark/sql/comet/CometColumnarToRowExec.scala:171-189 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometBroadcastExchangeExec.scala"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f4ffe79b6938ac2ab4196e10e1304a125a3b1c94f5d2d5b62f66494ddf0a3b2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 8\u002B corresponding lines): native/spark-expr/src/kernels/temporal.rs:200-208 | native/spark-expr/src/kernels/temporal.rs:217-225 | native/spark-expr/src/kernels/temporal.rs:228-235 \u2014 These 3 members are one piece of code written 3 times and then edited apart: every two of them correspond over at least 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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfff43811d50f826cd7f133715e30308779a4ae770be70a141fa8962959b431e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): native/spark-expr/src/string_funcs/contains.rs:139-148 | native/spark-expr/src/string_funcs/contains.rs:154-163 \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":"native/spark-expr/src/string_funcs/contains.rs"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"d94d10f5edd8419fc4e5cd7bdc7b5f670f7526d57f1a36779e9c23ee5c23feec"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala:171-179 | spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleInputRDD.scala:128-136 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed56f3e9a145cd3efacf4f1b6ed4df59f46f72e4976c754f7351632c85ec2ff8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): native/core/src/execution/expressions/arithmetic.rs:35-83 | native/core/src/execution/expressions/arithmetic.rs:95-111 \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":"native/core/src/execution/expressions/arithmetic.rs"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f6bde69fe712760a72f4c93f6f3ca6413d3d6b77f43017b7efae2a281fc9245"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): spark/src/main/scala/org/apache/comet/rules/CometSpark34AqeDppFallbackRule.scala:206-219 | spark/src/main/scala/org/apache/comet/rules/CometSpark34AqeDppFallbackRule.scala:230-246 \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":"spark/src/main/scala/org/apache/comet/rules/CometSpark34AqeDppFallbackRule.scala"},"region":{"startLine":206}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d9c33e9e731575f548db7a5c6516ef88c795c424c6172fc740d6cbfbbcc554f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (19 corresponding lines): native/core/src/parquet/parquet_support.rs:187-206 | native/spark-expr/src/conversion_funcs/cast.rs:234-252 \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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"e989784909d655840befa6e46c7f8396121e234dcc80b8a2ae2d10c2ee6261ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 14\u002B corresponding lines): native/shuffle/src/spark_unsafe/list.rs:198-213 | native/shuffle/src/spark_unsafe/row.rs:138-151 | native/shuffle/src/spark_unsafe/row.rs:154-167 \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":"native/shuffle/src/spark_unsafe/list.rs"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"982c3a99442bb1d725e5d93f0b4db18704218687256214cb5205b09ce181c02c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala:1446-1457 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3806-3814 \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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":1446}}}],"partialFingerprints":{"codehealthFindingId/v1":"719b81bbe39726961df0d05e1bf0c8087e5e56651a43e1403e6b08ae13a7bda6"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/jni-bridge/src/arrow_array_stream.rs:39-51 | native/jni-bridge/src/comet_udf_bridge.rs:38-51 \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":"native/jni-bridge/src/arrow_array_stream.rs"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a8b6065888eab65f8f63f60f92bf6f38e7a7884a23fc1609416bab4bf710a70"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/shuffle/src/spark_unsafe/unsafe_object.rs:93-103 | native/shuffle/src/spark_unsafe/unsafe_object.rs:106-117 \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":"native/shuffle/src/spark_unsafe/unsafe_object.rs"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"df0f8255cf23ccdaed8b1dc7a5e9d6f845ad3c58a50a018d26d43b047f1af47e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/agg_funcs/correlation.rs:272-278 | native/spark-expr/src/agg_funcs/regr.rs:414-420 \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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"84a3f7c5823018cb351820cf8c7d9ad7cceca141c8304f1f7d5619f8d8a7e78e"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): native/spark-expr/src/agg_funcs/min_max.rs:352-360 | native/spark-expr/src/agg_funcs/min_max_struct.rs: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":"native/spark-expr/src/agg_funcs/min_max.rs"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"c62fde3b8be5ebb519e3ab002e40cd1e2f5b06a1b0768baa1cbdac995abdf4eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (17 corresponding lines): native/core/src/parquet/parquet_support.rs:143-159 | native/core/src/parquet/parquet_support.rs:161-177 \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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e258cd2898b91b38beb5fa2f69a08aa197cc1a1e49fec9b2f6f540fce517586"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/spark-expr/src/float_semantics/normalize.rs:185-197 | native/spark-expr/src/iceberg_funcs/mod.rs:55-65 \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":"native/spark-expr/src/float_semantics/normalize.rs"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"41375229c7d3cfa6c46c584a6709486e95db8b0b250003b85d1b9c7f77b4a049"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 5\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/SparkFixes.scala:44-49 | spark/src/main/scala/org/apache/comet/serde/SparkFixes.scala:60-65 | spark/src/main/scala/org/apache/comet/serde/SparkFixes.scala:79-83 | spark/src/main/scala/org/apache/comet/serde/SparkFixes.scala:102-107 \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":"spark/src/main/scala/org/apache/comet/serde/SparkFixes.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"2bd8cc4942161eb4a86f8a84aea66f4d51f47dac467264ffd070c1ed541ae499"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (15 corresponding lines): spark/src/main/scala/org/apache/comet/serde/arithmetic.scala:477-491 | spark/src/main/scala/org/apache/comet/serde/structs.scala:96-114 \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":"spark/src/main/scala/org/apache/comet/serde/arithmetic.scala"},"region":{"startLine":477}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1700c86f54c74e0254ca1ff408fde4b4a036880c37c818df41d98b2b6c446b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): native/spark-expr/src/agg_funcs/avg.rs:82-95 | native/spark-expr/src/agg_funcs/avg_decimal.rs:132-145 \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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff7927d69ae394863ab6e579eb4d5d8111222ef7dbebc324f0f41b08b95a2a8c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala:1579-1588 | spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala:1595-1604 \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":"spark/src/main/scala/org/apache/comet/iceberg/IcebergReflection.scala"},"region":{"startLine":1579}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab8877316147e1f040e53dff56a76b1a0cbf05d904b25f5fac758f8d125f7d3f"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): native/core/src/execution/operators/scan.rs:196-208 | native/core/src/execution/operators/shuffle_scan.rs: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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9bfb633def0a871e432978199af42febeb9d70f00b9ce6e7f7f278be74e9530"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 9\u002B corresponding lines): native/spark-expr/src/agg_funcs/avg_decimal.rs:257-265 | native/spark-expr/src/agg_funcs/avg_decimal.rs:415-423 | native/spark-expr/src/agg_funcs/sum_decimal.rs:231-239 | native/spark-expr/src/agg_funcs/sum_decimal.rs:401-409 | native/spark-expr/src/array_funcs/list_extract.rs:107-115 \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":"native/spark-expr/src/agg_funcs/avg_decimal.rs"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"85b97931162e8b536ce3b9d1880c4f68480751453ff2eccd6e47d7086b119111"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): native/spark-expr/src/array_funcs/array_insert.rs:190-200 | native/spark-expr/src/array_funcs/list_extract.rs:216-229 \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":"native/spark-expr/src/array_funcs/array_insert.rs"},"region":{"startLine":190}}}],"partialFingerprints":{"codehealthFindingId/v1":"de7fdcee3420782caaec4b3b6b920e42ebfa2dccfe5fc628c0ed39a86b509d92"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): spark/src/main/java/org/apache/spark/shuffle/sort/SpillSorter.java:332-340 | spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometDiskBlockWriter.java:331-344 \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":"spark/src/main/java/org/apache/spark/shuffle/sort/SpillSorter.java"},"region":{"startLine":332}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9e4fc1a4a2d32be03a5f2d126c0451a5554ead3307b536509ab26b4010b5f3c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala:81-93 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:631-640 \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":"contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"83c2886e16c9a0374cf758a7b1aa41670ae1839cca8e62a194de7518abec02a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:515-523 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:525-532 \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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":515}}}],"partialFingerprints":{"codehealthFindingId/v1":"202a1faebcb6ccc277625ef7a3ac1f32b0b6dbc617488e8a4565748a5d3a4abd"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 12\u002B corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometSampleExec.scala:105-117 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:1764-1775 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:2027-2039 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometSampleExec.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6df39c37043ba8ebe6acc18ab402c42bfe2280b2e1d924fa293e5f15f6e03bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:362-368 | native/spark-expr/src/agg_funcs/variance.rs:308-313 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b5a41a527035f936dd46107ee2c8f1181bd3a37cdf63872b996e3410a7c68a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): native/spark-expr/src/agg_funcs/welford.rs:154-162 | native/spark-expr/src/agg_funcs/welford.rs:172-180 \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":"native/spark-expr/src/agg_funcs/welford.rs"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"e8b0abb394c88640bec2b8f44a30a37a9d2e7ec19792928d3de8276c15d40b63"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:1267-1279 | spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:1282-1294 \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":"spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java"},"region":{"startLine":1267}}}],"partialFingerprints":{"codehealthFindingId/v1":"2277938e57a7919e0b15825cfb688bbbf9023fc5968f5d1d6648ffb9030dbab2"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (16 corresponding lines): spark/src/main/scala/org/apache/comet/CometConf.scala:1788-1803 | spark/src/main/scala/org/apache/comet/CometConf.scala:1819-1834 \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":"spark/src/main/scala/org/apache/comet/CometConf.scala"},"region":{"startLine":1788}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5228dbbfd21cb213305ba75ed248d9420c6da92a923d3e91b30227e21415a80"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (5 members, 11\u002B corresponding lines): spark/src/main/scala/org/apache/comet/serde/bitwise.scala:31-44 | spark/src/main/scala/org/apache/comet/serde/bitwise.scala:63-73 | spark/src/main/scala/org/apache/comet/serde/bitwise.scala:80-90 | spark/src/main/scala/org/apache/comet/serde/predicates.scala:84-97 | spark/src/main/scala/org/apache/comet/serde/predicates.scala:104-114 \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":"spark/src/main/scala/org/apache/comet/serde/bitwise.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"efd518189a3ab56adf2306af531d0d508869916325b3e6edaa8ebfa72a2e6461"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala:811-815 | spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala:1076-1085 \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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala"},"region":{"startLine":811}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e32ba51503e938c814b039cbed9d89a4569b7df645ef5483348d81dfdde71cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): native/core/src/parquet/objectstore/location_scoped.rs:272-277 | native/core/src/parquet/objectstore/location_scoped.rs:283-288 \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":"native/core/src/parquet/objectstore/location_scoped.rs"},"region":{"startLine":272}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1c1ef616b7b9a0a8dfd7e6aac3d3caccb2616a93acb35c7f1e4d53099a46311"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): native/spark-expr/src/agg_funcs/max_min_by.rs:100-108 | native/spark-expr/src/agg_funcs/max_min_by.rs:134-142 \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":"native/spark-expr/src/agg_funcs/max_min_by.rs"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"900f2b922164bfacd7d0a8d477a6bda9202bca2c9cb2eb6a8d0b89de9437be78"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): native/spark-expr/src/iceberg_funcs/bucket.rs:172-176 | native/spark-expr/src/iceberg_funcs/truncate.rs:161-165 \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":"native/spark-expr/src/iceberg_funcs/bucket.rs"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7b17fc9d5fc08e871648d3d187c45f545b87ce26df7d5d3d221856a35b3980a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (14 corresponding lines): contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala:227-240 | spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala:287-306 \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":"contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala"},"region":{"startLine":227}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4a35a269f9c9dfc2ec972d43121eb4247d477300c28e8f7d43a6c396e334b5c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java:416-425 | spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:298-309 \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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7f95c6736c4a94d188c21335f4a0bcc14810cc9327a43fe3b1940d5197915d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (10 corresponding lines): native/core/src/execution/planner/delta_scan.rs:62-71 | native/core/src/execution/planner/lance_scan.rs:35-45 \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":"native/core/src/execution/planner/delta_scan.rs"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"6d397f1093a371d38c701c2ff36daf54a602aa85336d4cfc21aa16e9cea007eb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (12 corresponding lines): native/core/src/execution/operators/dynamic_filter/join.rs:265-276 | native/core/src/execution/operators/dynamic_filter/topk.rs:218-229 \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":"native/core/src/execution/operators/dynamic_filter/join.rs"},"region":{"startLine":265}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0b23f599ba4c538e4c25364e85fb82f3a4c81c2f86a44913ca1ddc989408136"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (13 corresponding lines): native/spark-expr/src/agg_funcs/correlation.rs:58-70 | native/spark-expr/src/agg_funcs/covariance.rs:64-76 \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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f8d377c037fbaa87ba5e02cd6a754da91c21b5c0174152a763de701743bf50c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (1 corresponding lines): native/core/src/execution/expressions/logical.rs:30-30 | native/core/src/execution/expressions/nullcheck.rs:27-27 \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":"native/core/src/execution/expressions/logical.rs"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"f20e84aa4af24611edd210f1c2f64a481a7a78b21c820e64e47bf09fe1d13326"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): native/spark-expr/src/agg_funcs/hll_sketch_agg.rs:205-214 | native/spark-expr/src/agg_funcs/hll_union_agg.rs:153-161 \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":"native/spark-expr/src/agg_funcs/hll_sketch_agg.rs"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa793b8014e52fd14ea354267e6a8bd9423b1779298018cde2808a3201360047"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:1261-1274 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:1280-1290 \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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1261}}}],"partialFingerprints":{"codehealthFindingId/v1":"d290ad58ad021852eef8600ca2f21632b00a78c1be4592814c306f37a9cdda22"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala:244-251 | spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala:310-320 \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":"contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"4247b7df224c362ce79d900168d01c0996af4dd6f143deaad2680806aa27dffb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): native/spark-expr/src/datetime_funcs/extract_date_part.rs:121-128 | native/spark-expr/src/datetime_funcs/unix_timestamp.rs:56-63 \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":"native/spark-expr/src/datetime_funcs/extract_date_part.rs"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"15ea72b08a0ce7cf9d0a772cda58fa6762ce60c725fb57105b710a951853f328"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): native/spark-expr/src/array_funcs/get_array_struct_fields.rs:57-64 | native/spark-expr/src/array_funcs/list_extract.rs:97-104 \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":"native/spark-expr/src/array_funcs/get_array_struct_fields.rs"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"61afc07afca76878de852c33ee7e3c19fcf74202c0ef0d9154e0f9e2a4eacc9d"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (11 corresponding lines): spark/src/main/scala/org/apache/comet/serde/statics.scala:298-308 | spark/src/main/scala/org/apache/comet/serde/strings.scala:870-881 \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":"spark/src/main/scala/org/apache/comet/serde/statics.scala"},"region":{"startLine":298}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e34a0121ff0ab8806a941083f3d3e7f7ec8130d1974ddc1f99d9960707dbc69"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): native/spark-expr/src/json_funcs/from_json.rs:117-124 | native/spark-expr/src/json_funcs/to_json.rs:120-127 \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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"a13901de7053e425d6617fe8bdb2a6c4362b85c3fa55e44e40011d9e37338947"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/math_funcs/internal/decimal_rescale_check.rs:50-56 | native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:70-77 \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":"native/spark-expr/src/math_funcs/internal/decimal_rescale_check.rs"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"bad82469e3c8a4ae648bebbc14d490464fe12ce2d628df92798b7994028fd60b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/json_funcs/from_json.rs:102-108 | native/spark-expr/src/json_funcs/to_json.rs:104-111 \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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecf831fc8f9ae694b56e9084610a3b4741c2c404e039c5c6b37d3900f6f95ed1"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): native/spark-expr/src/agg_funcs/avg.rs:345-348 | native/spark-expr/src/agg_funcs/avg_decimal.rs:605-608 \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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":345}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dbdfd605b3a5fc2246d7770c0af1c6ee45e0179293808d72b0300868476b863"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:449-452 | native/spark-expr/src/agg_funcs/variance.rs:387-390 \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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":449}}}],"partialFingerprints":{"codehealthFindingId/v1":"2cf34e8a3b73393ea580b8ccd43f79c0e7e77a2edb5801e2ae283f25820b52e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.scala:105-112 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:431-438 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"73bf5d7b2583562a17911b4d16814ea30385489c85892fdbda1c37596c3d6217"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): native/spark-expr/src/agg_funcs/avg_decimal.rs:82-87 | native/spark-expr/src/agg_funcs/sum_decimal.rs:66-72 \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":"native/spark-expr/src/agg_funcs/avg_decimal.rs"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"d247c0f147c57daad9f69a7e5e689e06d806676e4c91f7c6ff1f0f6f12b454dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): native/spark-expr/src/csv_funcs/to_csv.rs:47-51 | native/spark-expr/src/json_funcs/to_json.rs:54-58 \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":"native/spark-expr/src/csv_funcs/to_csv.rs"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f9f4bff58b785b1f173828fd13a5b74d11d4018d9c83c87d3c0817997497045"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/agg_funcs/covariance.rs:184-191 | native/spark-expr/src/agg_funcs/variance.rs: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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"69b62803d84d2de9946beeabd5b0d0350451b1a473cfb6b65510efed558663cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): native/core/src/execution/operators/iceberg_scan.rs:117-124 | native/core/src/execution/operators/iceberg_write.rs:788-795 \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":"native/core/src/execution/operators/iceberg_scan.rs"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"ea5cd3aea6d08f4a1229b45cf8b7fdf2284c68e0fa9603526f5812c768f11108"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (3 corresponding lines): native/spark-expr/src/array_funcs/nested_comparison.rs:356-361 | native/spark-expr/src/conditional_funcs/lazy_logical.rs:207-209 \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":"native/spark-expr/src/array_funcs/nested_comparison.rs"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"c632e0d8244a5230b1758af004670427ed751379cf68d61f338d428a7efa741c"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): spark/src/main/scala/org/apache/comet/serde/datetime.scala:341-345 | spark/src/main/scala/org/apache/comet/serde/strings.scala:148-153 \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":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":341}}}],"partialFingerprints":{"codehealthFindingId/v1":"41fb1cbe2d12602fbd4bef648c580027c2dd3444c0de05066338f224526e653b"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): spark/src/main/scala/org/apache/comet/serde/datetime.scala:361-365 | spark/src/main/scala/org/apache/comet/serde/url.scala:31-36 \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":"spark/src/main/scala/org/apache/comet/serde/datetime.scala"},"region":{"startLine":361}}}],"partialFingerprints":{"codehealthFindingId/v1":"6be108d06aebe04129f89ec7e10f7f6f5a8615a4b02c5ff5ac995ef4667c339a"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (4 corresponding lines): spark/src/main/scala/org/apache/spark/sql/comet/CometSubqueryAdaptiveBroadcastExec.scala:66-69 | spark/src/main/scala/org/apache/spark/sql/comet/CometSubqueryBroadcastExec.scala:81-84 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometSubqueryAdaptiveBroadcastExec.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b1c40dfe2b39384fdc608e28b3a7dd21475b5025881387aa87c1730fab819fe"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): native/core/src/debug/debug_batch_stream.rs:102-107 | native/spark-expr/src/float_semantics/normalize.rs:117-122 \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":"native/core/src/debug/debug_batch_stream.rs"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"b650ce2140878b73a8deefb7b2dc5680a8948eebe33de26f499b7bfb123999fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (3 members, 4\u002B corresponding lines): native/core/src/parquet/name_fold.rs:176-179 | native/core/src/parquet/objectstore/s3.rs:279-282 | native/core/src/parquet/parquet_support.rs:926-929 \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":"native/core/src/parquet/name_fold.rs"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"f38ff5fc8063a415a7fb255f7a75aea6631d5fa9c1500fe03d375377cca5da12"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): native/spark-expr/src/agg_funcs/approx_percentile.rs:120-126 | native/spark-expr/src/agg_funcs/mode.rs:144-150 \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":"native/spark-expr/src/agg_funcs/approx_percentile.rs"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"2733834d050452b23280cf7c7dab789a18ff16fb48f53705b2bae60a000546d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (9 corresponding lines): spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java:1238-1246 | spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java:246-254 \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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":1238}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e56486f2b86cdd7840ea295dc9b6cbe43d9189a70f0a8ee20ecc5e6facc0027"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (5 corresponding lines): native/spark-expr/src/agg_funcs/min_max.rs:362-366 | native/spark-expr/src/agg_funcs/pivot_first.rs:572-576 \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":"native/spark-expr/src/agg_funcs/min_max.rs"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"5aa2e9f074899b118ec343c6520c17f184f901b38c591c8cf9becfc71731afcc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (6 corresponding lines): native/spark-expr/src/bloom_filter/spark_bloom_filter.rs:267-272 | native/spark-expr/src/predicate_funcs/rlike.rs: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":"native/spark-expr/src/bloom_filter/spark_bloom_filter.rs"},"region":{"startLine":267}}}],"partialFingerprints":{"codehealthFindingId/v1":"27f9835862800d295e40b77447e8c9516dfcab6379eba3a41270b1386830a506"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copies of one member (4 members, 4\u002B corresponding lines): dev/ci/check-benchmark-runner.py:42-45 | dev/ci/check-ci-config.py:636-639 | dev/ci/check-mermaid.py:85-95 | dev/ci/local-ci-config.py:88-93 \u2014 These 4 members are one piece of code written 4 times and then edited apart: every two of them correspond over at least 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 4 times and the copies will drift further apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"dev/ci/check-benchmark-runner.py"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"f30129df5c30fce938d53a9d05e88939066cdfcb20bd1975018d461c209d19dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (8 corresponding lines): spark/src/main/scala/org/apache/comet/serde/predicates.scala:121-128 | spark/src/main/scala/org/apache/comet/serde/strings.scala:461-468 \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":"spark/src/main/scala/org/apache/comet/serde/predicates.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"bca7fa283490ba0fc274c1cd485ab48a725366b9078f2cc6558a17caeabfb1e0"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (7 corresponding lines): spark/src/main/spark-4.x/org/apache/comet/serde/CometHllUnion.scala:47-53 | spark/src/main/spark-4.x/org/apache/comet/serde/CometHllUnionAgg.scala: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":"spark/src/main/spark-4.x/org/apache/comet/serde/CometHllUnion.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad19e55568a9cd4caf2bcd6ef911723fae98ca778af599571d557a7bbe06d130"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (50\u201352 lines \u00D7 2): native/spark-expr/src/string_funcs/levenshtein.rs:216-265 | native/spark-expr/src/string_funcs/levenshtein.rs:297-348 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"127deb023f3333c07fca3a783fb09094404144a6fc5993e289f72dc4cef8179a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (33 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:614-646 | native/spark-expr/src/agg_funcs/sum_int.rs:765-797 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:614\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":614}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc3c4c9f5d91077ea55b4e8bf21de0b1284d7d43c289323b6937cb1ff3eb98fd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30 lines \u00D7 2): native/spark-expr/src/conversion_funcs/string.rs:405-434 | native/spark-expr/src/conversion_funcs/string.rs:478-507 \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 \u0060native/spark-expr/src/conversion_funcs/string.rs:405\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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e5ffba21b23c965fb179b18958bcc36e4b86e01cb4be6644e0aad5d6c7f2b0d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (28 lines \u00D7 2): native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs:65-92 | native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs:112-139 \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 \u0060native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs:65\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":"native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"134ebf75d114d1ac6867a9e7e8668122083611130ed2078396c7bd723b21b4d1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25\u201328 lines \u00D7 2): native/spark-expr/src/string_funcs/levenshtein.rs:186-213 | native/spark-expr/src/string_funcs/levenshtein.rs:271-295 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"fa691ceba58e69b2013c112f4addd2ebcbc5c147fdbc7aacd673689bbf95454b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25\u201326 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:542-566 | native/shuffle/src/spark_unsafe/row.rs:1009-1034 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/shuffle/src/spark_unsafe/row.rs:542\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":542}}}],"partialFingerprints":{"codehealthFindingId/v1":"765f709adf08e515189beb07286f95fbbe0d7e9381ec541d507c084cfb549b81"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25\u201326 lines \u00D7 2): native/spark-expr/src/string_funcs/levenshtein.rs:94-119 | native/spark-expr/src/string_funcs/levenshtein.rs:146-170 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/string_funcs/levenshtein.rs:146\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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a90866cce728f85089ad086c8e8b61f71333b7ce58f8466a4c5e97edd00c8a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201322 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:591-610 | native/spark-expr/src/agg_funcs/sum_int.rs:737-758 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs: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. 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2186551eb66e4ac34a4c10650f7fd77cc3c18fcf24c620bc8f6435e422b0b38"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201322 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:680-699 | native/spark-expr/src/agg_funcs/sum_int.rs:831-852 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:680\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":680}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc48ca3dc7f10ccf0cecc7a21b0a8d87bdfcfb426cd4cfbe09d09e7e6da6ed0c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): native/core/src/execution/c_udf/imported_c.rs:191-211 | native/core/src/execution/c_udf/imported_c.rs:254-274 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/c_udf/imported_c.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/c_udf/imported_c.rs"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5ecdc68566e47dd45162d9f2ecb8ddd4a5b1f011133bf46e6b9a5fa7c245016"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): native/core/src/execution/operators/dynamic_filter/join.rs:168-188 | native/core/src/execution/operators/dynamic_filter/topk.rs:122-142 \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 both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/core/src/execution/operators/dynamic_filter/join.rs:168\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":"native/core/src/execution/operators/dynamic_filter/join.rs"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"89655ef3af69bd589859c03cc4f00402453a66adb25f33cb7a27371ca5073939"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19\u201320 lines \u00D7 2): native/core/src/cloud/s3/credential_bridge.rs:231-250 | native/core/src/cloud/s3/credential_bridge.rs:311-329 \u2014 both copies are in the same file, so extract the block 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":"native/core/src/cloud/s3/credential_bridge.rs"},"region":{"startLine":231}}}],"partialFingerprints":{"codehealthFindingId/v1":"b07ad1a6ac44a6ac28f2ba3cceaff3f4b65a3355742151ee4d008088e283e11c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): native/spark-expr/src/agg_funcs/covariance.rs:197-217 | native/spark-expr/src/agg_funcs/covariance.rs:239-259 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/agg_funcs/covariance.rs:197\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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"3986d2ffd8558ee23c227ceb7917f6fd562ece190fa3169708351ab234881189"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201319 lines \u00D7 2): native/core/src/execution/planner/join.rs:186-204 | native/core/src/execution/planner/join.rs:397-410 \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 \u0060native/core/src/execution/planner/join.rs:186\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":"native/core/src/execution/planner/join.rs"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"582878f7d9375ed6713870fc13dfb254d4125fb2bb5beef2a7246896dd71c9e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): native/jni-bridge/src/shuffle_partition_pusher.rs:113-131 | native/jni-bridge/src/shuffle_partition_pusher.rs:141-159 \u2014 both copies are in the same file, so extract the block 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 \u0060native/jni-bridge/src/shuffle_partition_pusher.rs:113\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":"native/jni-bridge/src/shuffle_partition_pusher.rs"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b8c62d2864d20fa2a5cf4a6ea8ced0d25f7b5509e2c8a90205049c6066a8b01"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18\u201319 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:511-528 | native/shuffle/src/spark_unsafe/row.rs:978-996 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/spark_unsafe/row.rs:511\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3802d994d870fc162f547e0dcad45c07523c9d7a9be00b5ce339df9f1e1d52f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 3): native/shuffle/src/partitioners/multi_partition.rs:313-330 | native/shuffle/src/partitioners/multi_partition.rs:366-383 | native/shuffle/src/partitioners/multi_partition.rs:446-463 \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 \u0060native/shuffle/src/partitioners/multi_partition.rs:313\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":"native/shuffle/src/partitioners/multi_partition.rs"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c9eb10d1bf186f4ae2d9e3ab6784bba3fb0fe588a8fb9ba9b40e35250afedf6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): native/spark-expr/src/agg_funcs/stddev.rs:111-128 | native/spark-expr/src/agg_funcs/variance.rs:103-120 \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. 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":"native/spark-expr/src/agg_funcs/stddev.rs"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"e71c8a50c8699fc3ec1aabd3dda17bd2a15947940f88e4c3e4d34c1a8a00fe1c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201317 lines \u00D7 3): native/spark-expr/src/utils.rs:75-91 | native/spark-expr/src/utils.rs:94-108 | native/spark-expr/src/utils.rs:111-125 \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 \u0060native/spark-expr/src/utils.rs:75\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":"native/spark-expr/src/utils.rs"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"64ec99f1d755ae00614ffd198f71e4a14563ab074758e74124624d0675afdd67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): native/spark-expr/src/datetime_funcs/unix_timestamp.rs:92-108 | native/spark-expr/src/datetime_funcs/unix_timestamp.rs:114-130 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/datetime_funcs/unix_timestamp.rs:92\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":"native/spark-expr/src/datetime_funcs/unix_timestamp.rs"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6709da16edf682a57f8da7f3fc5f0df8afd7edfc835f14aa00d1446e27ac663"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201317 lines \u00D7 2): native/spark-expr/src/string_funcs/levenshtein.rs:77-91 | native/spark-expr/src/string_funcs/levenshtein.rs:126-142 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"b852348c3982a8a374f7275c87f748564acaca8fbaccb7cc1b64b59945c15a32"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): native/shuffle/src/writers/rss/rss_partition_writer.rs:835-850 | native/shuffle/src/writers/rss/rss_partition_writer.rs:853-868 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:835\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":835}}}],"partialFingerprints":{"codehealthFindingId/v1":"974d403b1cd353cda91e535fef995e617f415a7d78f0646ded4126877a3536dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 3): native/shuffle/src/writers/rss/rss_partition_writer.rs:952-966 | native/shuffle/src/writers/rss/rss_partition_writer.rs:978-991 | native/shuffle/src/writers/rss/rss_partition_writer.rs:1046-1059 \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 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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":952}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4063ee512e3841e34e3d04dfdd8fefaf8ad5d89c545e1ff3ebab6f160d1df3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 3): native/spark-expr/src/array_funcs/array_position.rs:145-159 | native/spark-expr/src/array_funcs/array_position.rs:219-233 | native/spark-expr/src/array_funcs/array_position.rs:250-264 \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 \u0060native/spark-expr/src/array_funcs/array_position.rs:145\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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d5048fb2621829ce9cab111232ec497a93f15ee1d0617f238966c66c20b2e8a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201315 lines \u00D7 2): native/core/src/execution/planner/window.rs:426-437 | native/core/src/execution/planner/window.rs:486-500 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/planner/window.rs:426\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":"native/core/src/execution/planner/window.rs"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8c847dc2265ebd640751da1acd5375cb7195153ac01ac0fd15e2eee3b958f10"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): native/jni-bridge/src/output_stream_sink.rs:138-152 | native/jni-bridge/src/shuffle_partition_pusher.rs:268-282 \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 \u0060native/jni-bridge/src/output_stream_sink.rs:138\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":"native/jni-bridge/src/output_stream_sink.rs"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"b66041fb5be8addaf177924715786a3b31f06e568c4733717289f3615b2299d8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): native/spark-expr/src/agg_funcs/collect.rs:429-443 | native/spark-expr/src/agg_funcs/collect.rs:744-757 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/collect.rs:429\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":"native/spark-expr/src/agg_funcs/collect.rs"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"7eee5dda52184558c6cba5691a3233b803e2054a8ade786fcadbc6a07643286f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): native/spark-expr/src/hash_funcs/murmur3.rs:160-174 | native/spark-expr/src/hash_funcs/xxhash64.rs:189-203 \u2014 before extracting anything, compare \u0060native/spark-expr/src/hash_funcs/murmur3.rs\u0060 and \u0060native/spark-expr/src/hash_funcs/xxhash64.rs\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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/hash_funcs/murmur3.rs:160\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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":160}}}],"partialFingerprints":{"codehealthFindingId/v1":"f06da11e85d1d60084622789779b02eb7747173691ef16b5ef78fce2081c2abc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:233-246 | native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs: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 \u0060native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:233\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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":233}}}],"partialFingerprints":{"codehealthFindingId/v1":"10668f23c3d4bf3423b993f8925601fe0df675888057aa7e4a24fa79989e87a7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): native/spark-expr/src/string_funcs/split.rs:86-99 | native/spark-expr/src/string_funcs/split.rs:151-164 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/string_funcs/split.rs:86\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":"native/spark-expr/src/string_funcs/split.rs"},"region":{"startLine":86}}}],"partialFingerprints":{"codehealthFindingId/v1":"d28954a1f280e6bf8214bc9ac1004a5553d51b346e5b7e36ec41f4ebef29058d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): native/spark-expr/src/agg_funcs/sum_int.rs:595-607 | native/spark-expr/src/agg_funcs/sum_int.rs:741-753 | native/spark-expr/src/agg_funcs/sum_int.rs:905-917 \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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:595\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, \u0060native/spark-expr/src/agg_funcs/sum_int.rs:919\u0060 calls \u0060is_none\u0060 and \u0060native/spark-expr/src/agg_funcs/sum_int.rs:608\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":595}}}],"partialFingerprints":{"codehealthFindingId/v1":"79f6f3048dd590ab2588ae7a2f4a5907e3e91d255fb5ae922afc9316f3f1b09d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): native/core/src/parquet/schema_adapter.rs:1451-1462 | native/core/src/parquet/schema_adapter.rs:1566-1578 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/parquet/schema_adapter.rs:1566\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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":1451}}}],"partialFingerprints":{"codehealthFindingId/v1":"b842320a10cbb44e5c99ff2f6ca8f9e0064350dc72a2c64d09ca942bade4b159"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): native/spark-expr/src/conversion_funcs/string.rs:380-392 | native/spark-expr/src/conversion_funcs/string.rs:451-463 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/conversion_funcs/string.rs:380\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, \u0060native/spark-expr/src/conversion_funcs/string.rs:465\u0060 calls \u0060from_i128\u0060 and \u0060native/spark-expr/src/conversion_funcs/string.rs:393\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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"7008de20ac8996fd816c7abaa660017058aea3c10bdd0930859169c5a461ac19"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): native/spark-expr/src/conversion_funcs/string.rs:1205-1217 | native/spark-expr/src/conversion_funcs/string.rs:1285-1297 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/conversion_funcs/string.rs:1205\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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1205}}}],"partialFingerprints":{"codehealthFindingId/v1":"75b7c7f48d48bb87016689eedfb6eb989ce32ba7ebf386257e19436ade74bcf9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): native/spark-expr/src/math_funcs/abs.rs:73-85 | native/spark-expr/src/math_funcs/unhex.rs:151-163 \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":"native/spark-expr/src/math_funcs/abs.rs"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7f3f96759cc6dc737f67c1b225a6c46a6e572ccaea53ab2a4c43b987b96cca7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 4): native/spark-expr/src/array_funcs/array_position.rs:139-150 | native/spark-expr/src/array_funcs/array_position.rs:173-184 | native/spark-expr/src/array_funcs/array_position.rs:213-224 | native/spark-expr/src/array_funcs/array_position.rs:244-255 \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 \u0060native/spark-expr/src/array_funcs/array_position.rs:139\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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cfd300f67c66e5346ce541e058a2ae34511f6a30b9a72114e60d16cc302ef99"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/core/src/execution/operators/scan.rs:82-95 | native/core/src/execution/operators/shuffle_scan.rs:100-111 \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 \u0060native/core/src/execution/operators/scan.rs:82\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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"915d77497b028aa1a10e60899a17d4dcfad2a55a2affd5ce4f930f5881293f1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): native/core/src/execution/operators/scan.rs:132-143 | native/core/src/execution/operators/shuffle_scan.rs:134-144 \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":"native/core/src/execution/operators/scan.rs"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"02e8e2189de94062fab35698b4f0f011b69ec8cf46bde8d7f7debfbd4a11ac89"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/core/src/execution/planner.rs:1475-1486 | native/core/src/execution/planner.rs:1547-1558 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/planner.rs:1475\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":"native/core/src/execution/planner.rs"},"region":{"startLine":1475}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb6a8e41623d53e296c90c64dab4cf254a6e02aad58a3cce1f170d2446ac4ccd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/core/src/parquet/cast_column/variant.rs:289-301 | native/core/src/parquet/cast_column/variant.rs:500-511 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/parquet/cast_column/variant.rs:289\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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"9dcfea5e78ff6ba2a42310543e096325b34ddcdd5132780b890782af8e2ab80a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:490-501 | native/shuffle/src/spark_unsafe/row.rs:958-969 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/spark_unsafe/row.rs:490\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":490}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab3e82943439add01a89fe37c338498068ca6bd8e1f654f20e1395bb55f60c29"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:301-312 | native/spark-expr/src/agg_funcs/sum_int.rs:372-383 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:301\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7d0f8fe4dbbf26a9295d2d2e6644acbd3ec4600b28498a64b13c8bb97741b4b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:656-667 | native/spark-expr/src/agg_funcs/sum_int.rs:807-818 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":656}}}],"partialFingerprints":{"codehealthFindingId/v1":"0738453710a7270a62e472ea9c372e3abd1d6b94f324e9f95c461b8d81ea178b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201312 lines \u00D7 2): native/spark-expr/src/datetime_funcs/date_diff.rs:71-82 | native/spark-expr/src/datetime_funcs/make_time.rs:107-115 \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 \u0060native/spark-expr/src/datetime_funcs/date_diff.rs: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. 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":"native/spark-expr/src/datetime_funcs/date_diff.rs"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"19a21e8140e613e3f6662f30a683ea9163d71024531c4ed5ba8bfcad6cb681b7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): native/spark-expr/src/string_funcs/regexp_extract.rs:46-57 | native/spark-expr/src/string_funcs/regexp_extract_all.rs:49-60 \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 \u0060native/spark-expr/src/string_funcs/regexp_extract.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/string_funcs/regexp_extract.rs"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"a132c424419076fff5ad5a129cf97eed61c59948684ab09a637bbec8175a39e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 4): native/spark-expr/src/agg_funcs/correlation.rs:221-231 | native/spark-expr/src/agg_funcs/correlation.rs:365-375 | native/spark-expr/src/agg_funcs/regr.rs:356-366 | native/spark-expr/src/agg_funcs/regr.rs:478-488 \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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ebe7072a768ae53c8a07a2a65459bb87ef1984e0ace8c721a0844f4afebe646"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 3): native/shuffle/src/spark_unsafe/row.rs:463-473 | native/shuffle/src/spark_unsafe/row.rs:482-492 | native/shuffle/src/spark_unsafe/row.rs:503-513 \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 \u0060native/shuffle/src/spark_unsafe/row.rs:463\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":463}}}],"partialFingerprints":{"codehealthFindingId/v1":"fadb28180897d298305147f5e3a81e02c2812638df61b809b0ed662e0f020339"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 3): native/spark-expr/src/agg_funcs/sum_int.rs:302-312 | native/spark-expr/src/agg_funcs/sum_int.rs:373-383 | native/spark-expr/src/agg_funcs/sum_int.rs:454-464 \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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:302\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"822113a628c92b241b22d378d961f420e96ccc605ce2e430a1cc8ae2e4cf1567"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): native/core/src/parquet/cast_column/variant.rs:266-276 | native/core/src/parquet/cast_column/variant.rs:289-299 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/core/src/parquet/cast_column/variant.rs:266\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":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":266}}}],"partialFingerprints":{"codehealthFindingId/v1":"f144b0bcb84370f0781609de3438756d050733d2a63eeaa75aaedd6ed92fd680"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): native/shuffle/src/spark_unsafe/list.rs:398-408 | native/shuffle/src/spark_unsafe/row.rs:307-317 \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 \u0060native/shuffle/src/spark_unsafe/list.rs: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":"native/shuffle/src/spark_unsafe/list.rs"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"5adc8a71c829c14966bb4c4c6aa0ab0763254db3f19b6a569c5b47eb74bf6ff0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): native/spark-expr/src/agg_funcs/correlation.rs:97-107 | native/spark-expr/src/agg_funcs/covariance.rs:103-113 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/agg_funcs/correlation.rs:97\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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"9fbdaa369d8a6d11726de8e2ace7d6f4f22b1635a8d6bf5828c9162ef87f6b8e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): native/spark-expr/src/agg_funcs/covariance.rs:401-411 | native/spark-expr/src/agg_funcs/covariance.rs:437-447 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/covariance.rs:401\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, \u0060native/spark-expr/src/agg_funcs/covariance.rs:436\u0060 calls \u0060value\u0060 and \u0060native/spark-expr/src/agg_funcs/covariance.rs:400\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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf8e4749f7f23c5f12d462b8dfe64cf08ef4d39cd3a34930e8e5123b68eb8daa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:316-339 | native/spark-expr/src/agg_funcs/sum_int.rs:387-410 \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 \u0060native/spark-expr/src/agg_funcs/sum_int.rs:316\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":316}}}],"partialFingerprints":{"codehealthFindingId/v1":"ae423e1627231a3bd3138fb1726bbd86250998677ca0dee09a26117d79c5f761"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): native/spark-expr/src/conversion_funcs/cast.rs:816-826 | native/spark-expr/src/math_funcs/checked_binary_expr.rs:104-114 \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 \u0060native/spark-expr/src/conversion_funcs/cast.rs:816\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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":816}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a502e8be9fe83e510499722dfafe7cd1c5bbfcce30567f30313ec84e5be4bef"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26\u201330 lines \u00D7 2): native/spark-expr/src/datetime_funcs/make_date.rs:197-226 | native/spark-expr/src/datetime_funcs/make_time.rs:104-129 \u2014 before extracting anything, compare \u0060native/spark-expr/src/datetime_funcs/make_date.rs\u0060 and \u0060native/spark-expr/src/datetime_funcs/make_time.rs\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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/datetime_funcs/make_date.rs"},"region":{"startLine":197}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b9ba282941a64926dc86a7a9173119faf3a933fcd9eb0a9b7981d2767526719"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): native/shuffle/src/spark_unsafe/row.rs:933-942 | native/shuffle/src/spark_unsafe/row.rs:951-960 | native/shuffle/src/spark_unsafe/row.rs:971-980 \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 \u0060native/shuffle/src/spark_unsafe/row.rs:933\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"9797b1ae3bcd4f41fa4706ab59e7b1997f3b9630f9c73aa8cbcd09c389ef0740"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): native/spark-expr/src/agg_funcs/avg.rs:257-266 | native/spark-expr/src/agg_funcs/avg_decimal.rs:470-479 | native/spark-expr/src/agg_funcs/sum_decimal.rs:454-463 \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 \u0060native/spark-expr/src/agg_funcs/avg.rs:257\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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f6af0e50abce06bc5541733f8749491ecd429b521afbaa50a0dcbbb73a1678c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/common/src/utf8.rs:62-71 | native/common/src/utf8.rs:103-112 \u2014 both copies are in the same file, so extract the block 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 before the matched lines, \u0060native/common/src/utf8.rs:102\u0060 calls \u0060entries\u0060 and \u0060native/common/src/utf8.rs:61\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":"native/common/src/utf8.rs"},"region":{"startLine":62}}}],"partialFingerprints":{"codehealthFindingId/v1":"66defb237b783e418f3e7dd7ce8e4a656f842dbbf83070922b5f1f254b4c33ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/shuffle/src/remote_schema.rs:90-99 | native/shuffle/src/remote_schema.rs:169-178 \u2014 both copies are in the same file, so extract the block 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":"native/shuffle/src/remote_schema.rs"},"region":{"startLine":90}}}],"partialFingerprints":{"codehealthFindingId/v1":"76c38c7917c296500e091ccbc73bf066edf9fecf190f0fba06dcc0a488fe8779"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): native/spark-expr/src/array_funcs/array_contains.rs:66-75 | native/spark-expr/src/array_funcs/array_remove.rs:68-76 \u2014 before extracting anything, compare \u0060native/spark-expr/src/array_funcs/array_contains.rs\u0060 and \u0060native/spark-expr/src/array_funcs/array_remove.rs\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 \u0060native/spark-expr/src/array_funcs/array_contains.rs: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. 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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"9032da3f7f6b768678be30a91cfd5fed2d8c0619c9fcdd4f3e8911281ef04300"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/spark-expr/src/array_funcs/array_contains.rs:127-136 | native/spark-expr/src/array_funcs/array_remove.rs:124-133 \u2014 before extracting anything, compare \u0060native/spark-expr/src/array_funcs/array_contains.rs\u0060 and \u0060native/spark-expr/src/array_funcs/array_remove.rs\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 \u0060native/spark-expr/src/array_funcs/array_contains.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":127}}}],"partialFingerprints":{"codehealthFindingId/v1":"c13cb142ff3a7e2e76afdd3c44b5d3c154507153bb7491127e4b6c202333e4ed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): native/spark-expr/src/array_funcs/array_position.rs:44-52 | native/spark-expr/src/array_funcs/arrays_zip.rs:126-135 \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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5b430c922787e602123caff4fbf6ed04261359cbfbefded9f8382ecc37660b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): native/spark-expr/src/array_funcs/array_set_ops.rs:75-83 | native/spark-expr/src/float_semantics/normalize.rs:187-196 \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 \u0060native/spark-expr/src/float_semantics/normalize.rs: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":"native/spark-expr/src/array_funcs/array_set_ops.rs"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"462ef27517490f083981de90f54b42733d95d640dba7a3c2dfa1f7b06e9bf60a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/spark-expr/src/array_funcs/list_extract.rs:342-351 | native/spark-expr/src/array_funcs/list_extract.rs:375-384 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/array_funcs/list_extract.rs:342\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":"native/spark-expr/src/array_funcs/list_extract.rs"},"region":{"startLine":342}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d95d469ee1082e8d1255116dbdea63e1cb6c7f271737a8e39ff90fa1a279ef5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/spark-expr/src/conversion_funcs/string.rs:1185-1194 | native/spark-expr/src/conversion_funcs/string.rs:1272-1281 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1185}}}],"partialFingerprints":{"codehealthFindingId/v1":"d17764a559506df9116622086b8b6ea9d862da286e4fc60ec4a3dc5ce7e02dfe"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 2): native/spark-expr/src/datetime_funcs/make_date.rs:201-210 | native/spark-expr/src/datetime_funcs/next_day.rs:102-110 \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 \u0060native/spark-expr/src/datetime_funcs/make_date.rs: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":"native/spark-expr/src/datetime_funcs/make_date.rs"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad248407c7ef11e37d9be47c5bac1df385c9cfe54cff3a261c39a14b89c15a96"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/spark-expr/src/hash_funcs/murmur3.rs:149-158 | native/spark-expr/src/hash_funcs/xxhash64.rs:177-186 \u2014 before extracting anything, compare \u0060native/spark-expr/src/hash_funcs/murmur3.rs\u0060 and \u0060native/spark-expr/src/hash_funcs/xxhash64.rs\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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/hash_funcs/murmur3.rs:149\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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef4f5425d02b9f3c625f5e5eb9938d3792889e079f678c91b4ed2816acce9b69"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): native/spark-expr/src/math_funcs/ceil.rs:44-53 | native/spark-expr/src/math_funcs/floor.rs:44-53 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/math_funcs/ceil.rs: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":"native/spark-expr/src/math_funcs/ceil.rs"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"9301d255b351553b48b398fe3077027ff023673605cb338ef86df2f3fb866e5c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): native/spark-expr/src/agg_funcs/hll_plus_plus.rs:389-397 | native/spark-expr/src/agg_funcs/max_min_by.rs:355-363 | native/spark-expr/src/agg_funcs/percentile.rs:366-374 \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 \u0060native/spark-expr/src/agg_funcs/hll_plus_plus.rs:389\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":"native/spark-expr/src/agg_funcs/hll_plus_plus.rs"},"region":{"startLine":389}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b4a72d3cb19a73bcda7ae8f7232dcedbe284bf79c5bf32205a20ab900a0ac13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 3): native/spark-expr/src/agg_funcs/sum_int.rs:319-336 | native/spark-expr/src/agg_funcs/sum_int.rs:390-407 | native/spark-expr/src/agg_funcs/sum_int.rs:479-496 \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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"d8bf337ba91a1ba39f8b8e5403bccf621f859e0378cf296c8b80efc88fbc28e1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:401-409 | native/shuffle/src/spark_unsafe/row.rs:871-879 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/spark_unsafe/row.rs:401\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":401}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8c8b7e181a7b77cdc3c054d6dc7b53cfafadc3b5cb1534eb19d9983acf90542"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:1767-1775 | native/shuffle/src/spark_unsafe/row.rs:1786-1794 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/spark_unsafe/row.rs:1767\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":1767}}}],"partialFingerprints":{"codehealthFindingId/v1":"1071a3d634a7e4bfe893b8041695acec730a81266e39d852c5dfae96f9f17f40"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20139 lines \u00D7 4): native/shuffle/src/writers/rss/rss_partition_writer.rs:670-678 | native/shuffle/src/writers/rss/rss_partition_writer.rs:681-689 | native/shuffle/src/writers/rss/rss_partition_writer.rs:946-949 | native/shuffle/src/writers/rss/rss_partition_writer.rs:972-975 \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 \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:670\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":670}}}],"partialFingerprints":{"codehealthFindingId/v1":"b161f7b0c06d2f60fb26d19a206d3f0ed145a93a27bbd772a34afbbaafdff4c9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/agg_funcs/collect.rs:313-321 | native/spark-expr/src/agg_funcs/collect.rs:659-667 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/collect.rs:313\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":"native/spark-expr/src/agg_funcs/collect.rs"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"4cb04fe9062b01b7bd31a9a9d10403da0b4683456dbbd1602b31f056d8d9d36d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_decimal.rs:563-571 | native/spark-expr/src/agg_funcs/sum_int.rs:1029-1037 \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 \u0060native/spark-expr/src/agg_funcs/sum_decimal.rs:563\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, \u0060native/spark-expr/src/agg_funcs/sum_int.rs:1026\u0060 calls \u0060resize\u0060, \u0060Some\u0060 and \u0060native/spark-expr/src/agg_funcs/sum_decimal.rs:561\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":"native/spark-expr/src/agg_funcs/sum_decimal.rs"},"region":{"startLine":563}}}],"partialFingerprints":{"codehealthFindingId/v1":"df9a8ccaa8de13a76c9ef92ddbd68dbc7a294108b0331867332e3d40e91fe6c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/utils.rs:129-137 | native/spark-expr/src/utils.rs:141-149 \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 \u0060native/spark-expr/src/utils.rs:129\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":"native/spark-expr/src/utils.rs"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"998ba64ea142a22fa390b65f176cc79c240905a47f2e834c67f0433fc7af90b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): native/shuffle/src/partitioners/multi_partition.rs:282-288 | native/shuffle/src/partitioners/multi_partition.rs:336-343 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/shuffle/src/partitioners/multi_partition.rs:282\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":"native/shuffle/src/partitioners/multi_partition.rs"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"609646914e110c696d991341bba7b62375a1ab88db2e34472c94e387eb7836d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/shuffle/src/spark_unsafe/row.rs:383-390 | native/shuffle/src/spark_unsafe/row.rs:854-861 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/spark_unsafe/row.rs:383\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":383}}}],"partialFingerprints":{"codehealthFindingId/v1":"00f7d0e3806483c4d9845e9e70b51cc0b10f0dedf71bf9a99ee9833d416431e5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/agg_funcs/avg_decimal.rs:258-265 | native/spark-expr/src/agg_funcs/avg_decimal.rs:416-423 \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. 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":"native/spark-expr/src/agg_funcs/avg_decimal.rs"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"a68a6ac3e0ea2ddad6b115099d6f7d52afaba2e7f2bcbdfd0552ff1e541f6552"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/agg_funcs/covariance.rs:421-428 | native/spark-expr/src/agg_funcs/variance.rs:362-369 \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 \u0060native/spark-expr/src/agg_funcs/covariance.rs:421\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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":421}}}],"partialFingerprints":{"codehealthFindingId/v1":"c343ff0c69da1267f6fc157d412bd2aa1244e823fd4a372190b235d4042cca42"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/agg_funcs/min_max.rs:353-360 | native/spark-expr/src/agg_funcs/min_max_struct.rs:364-371 \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":"native/spark-expr/src/agg_funcs/min_max.rs"},"region":{"startLine":353}}}],"partialFingerprints":{"codehealthFindingId/v1":"95b527c6d68989ccc25e2a5074b0e6df2778413e99e15ba7484160c351dd6f3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_decimal.rs:232-239 | native/spark-expr/src/agg_funcs/sum_decimal.rs:402-409 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/agg_funcs/sum_decimal.rs"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"c22b26714bb766e102866a7b737d5b1f217633ad21b76e3b66b48a9e98fbec30"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_int.rs:522-530 | native/spark-expr/src/agg_funcs/sum_int.rs:1017-1024 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":522}}}],"partialFingerprints":{"codehealthFindingId/v1":"3dd759326118b98c6da2084e417d18af8aa8d4c914cf6ce239d0fdf50e761409"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/array_funcs/arrays_overlap.rs:352-359 | native/spark-expr/src/array_funcs/arrays_overlap.rs:558-565 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/array_funcs/arrays_overlap.rs: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. 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":"native/spark-expr/src/array_funcs/arrays_overlap.rs"},"region":{"startLine":352}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f8c45663ed0d613f061d63d0e75cc778d1f65bf1ec5b7892f18d95351d30398"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/array_funcs/flatten.rs:118-125 | native/spark-expr/src/array_funcs/flatten.rs:147-154 \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 \u0060native/spark-expr/src/array_funcs/flatten.rs:118\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":"native/spark-expr/src/array_funcs/flatten.rs"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee845c7153c9ce3e010b565e0635baff4bb1ee7513a24687f1099003c6d7f2f8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/conversion_funcs/cast.rs:753-761 | native/spark-expr/src/json_funcs/to_json.rs:228-236 \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 \u0060native/spark-expr/src/conversion_funcs/cast.rs:753\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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":753}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf9d312fb6ae2451a31759e4d846d655ec36b4c432fe915c9d79895819f270df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/json_funcs/from_json.rs:240-247 | native/spark-expr/src/json_funcs/from_json.rs:270-277 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/json_funcs/from_json.rs:240\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":"native/spark-expr/src/json_funcs/from_json.rs"},"region":{"startLine":240}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1985c19c7c502645aad255747fe15d088874a8b00fe42cb1646f6f7b32577b5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/math_funcs/log.rs:76-83 | native/spark-expr/src/math_funcs/log.rs:104-111 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/math_funcs/log.rs: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":"native/spark-expr/src/math_funcs/log.rs"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fb8389ce4d5d3e8155113e43b410043bea503eab50c62686d2eabe8c189ddd2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/math_funcs/log.rs:95-102 | native/spark-expr/src/math_funcs/log.rs:123-130 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/math_funcs/log.rs:95\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":"native/spark-expr/src/math_funcs/log.rs"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"13e8660bef590c9234646e89f36b0814d1eb280763271d58eddab15c8315c1d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): native/spark-expr/src/array_funcs/arrays_zip.rs:179-186 | native/spark-expr/src/array_funcs/arrays_zip.rs:191-198 | native/spark-expr/src/array_funcs/arrays_zip.rs:203-210 \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 \u0060native/spark-expr/src/array_funcs/arrays_zip.rs:179\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":"native/spark-expr/src/array_funcs/arrays_zip.rs"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cbeafdf51dca753e7837cc5fa5aac15a916465cd083c02b8297123aa8866302"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/agg_funcs/avg.rs:286-292 | native/spark-expr/src/agg_funcs/avg_decimal.rs:498-504 \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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"488009a1ae7f9389217861d673380c91e28b1f566b834ea30577e3060167949f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/agg_funcs/correlation.rs:184-192 | native/spark-expr/src/agg_funcs/correlation.rs:204-212 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"b138fc913b6d0a389d8784781474c2d90dde1901d66834a06f63a0b3193813c4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/datetime_funcs/make_date.rs:242-248 | native/spark-expr/src/datetime_funcs/make_time.rs:147-153 \u2014 before extracting anything, compare \u0060native/spark-expr/src/datetime_funcs/make_date.rs\u0060 and \u0060native/spark-expr/src/datetime_funcs/make_time.rs\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 \u0060native/spark-expr/src/datetime_funcs/make_date.rs:242\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":"native/spark-expr/src/datetime_funcs/make_date.rs"},"region":{"startLine":242}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb9a6f4150f6b0de9c265c61871a48929cc958415a7f39317f68678c60a6b04b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/hash_funcs/murmur3.rs:45-51 | native/spark-expr/src/hash_funcs/xxhash64.rs:77-83 \u2014 before extracting anything, compare \u0060native/spark-expr/src/hash_funcs/murmur3.rs\u0060 and \u0060native/spark-expr/src/hash_funcs/xxhash64.rs\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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/hash_funcs/murmur3.rs:45\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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"529e450a902bd898076057e5bd484589a12f7eb758e08df0ada77ab1f249ceef"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6\u20137 lines \u00D7 2): native/spark-expr/src/utils.rs:224-229 | native/spark-expr/src/utils.rs:306-312 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/utils.rs:224\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":"native/spark-expr/src/utils.rs"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"f609fd774d5960a852ce6e6605ac6fdce9ca1a2c7c13fad746cfe12c4844b968"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 5): native/spark-expr/src/array_funcs/array_position.rs:143-148 | native/spark-expr/src/array_funcs/array_position.rs:177-182 | native/spark-expr/src/array_funcs/array_position.rs:217-222 | native/spark-expr/src/array_funcs/array_position.rs:248-253 | native/spark-expr/src/array_funcs/array_position.rs:286-291 \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 \u0060native/spark-expr/src/array_funcs/array_position.rs:143\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":"native/spark-expr/src/array_funcs/array_position.rs"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"508a13db0a6749c0530003ddbb575e0a2ae167a5a9ea3eb321d9ca738cdb4f8e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): native/shuffle/src/spark_unsafe/row.rs:863-869 | native/shuffle/src/spark_unsafe/row.rs:933-938 | native/shuffle/src/spark_unsafe/row.rs:951-956 | native/shuffle/src/spark_unsafe/row.rs:971-976 \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 \u0060native/shuffle/src/spark_unsafe/row.rs:863\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":863}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfd37ccb0ca2c2e16d5a44f68e6cea2176fb0539533fc9f14609bedc9e332a15"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): native/spark-expr/src/string_funcs/split.rs:320-328 | native/spark-expr/src/string_funcs/split.rs:347-352 | native/spark-expr/src/string_funcs/split.rs:370-375 | native/spark-expr/src/string_funcs/split.rs:393-398 \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 \u0060native/spark-expr/src/string_funcs/split.rs:320\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":"native/spark-expr/src/string_funcs/split.rs"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"245b07c91254f23337eb5dfc5e146cee61af57ba9211d6266bde579ee2fd2dff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/core/src/execution/operators/iceberg_write.rs:2004-2009 | native/core/src/execution/operators/iceberg_write.rs:2022-2027 \u2014 both copies are in the same file, so extract the block 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":"native/core/src/execution/operators/iceberg_write.rs"},"region":{"startLine":2004}}}],"partialFingerprints":{"codehealthFindingId/v1":"37db1274627c808e2fc0cc616179bd7b7bfe1811a83f49f25dad5296b9591446"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/agg_funcs/covariance.rs:280-285 | native/spark-expr/src/agg_funcs/variance.rs:221-226 \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 \u0060native/spark-expr/src/agg_funcs/covariance.rs:280\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":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"b72914e519ebd074a8b1bcbeca5aba2cd35f794e3aa0eec39835cc1462853a53"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/agg_funcs/sum_decimal.rs:419-425 | native/spark-expr/src/agg_funcs/sum_decimal.rs:592-597 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/agg_funcs/sum_decimal.rs:419\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":"native/spark-expr/src/agg_funcs/sum_decimal.rs"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"854a701dbc1bbac0d3dc3d54bdee15cb46637d2ab0891b5db1a57fe86eb6d3d7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/array_funcs/flatten.rs:130-135 | native/spark-expr/src/array_funcs/flatten.rs:159-164 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/array_funcs/flatten.rs:130\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":"native/spark-expr/src/array_funcs/flatten.rs"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0e9c67e0723c7508063a31587d0d2b450449fa90804286497599d9176eb885d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/datetime_funcs/date_diff.rs:67-73 | native/spark-expr/src/datetime_funcs/next_day.rs:99-104 \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 \u0060native/spark-expr/src/datetime_funcs/date_diff.rs:67\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":"native/spark-expr/src/datetime_funcs/date_diff.rs"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2b0231996201d0dfcfa14e30af30d5f4dc63c1069a736f98da8093f1d517d67"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/math_funcs/pow.rs:108-113 | native/spark-expr/src/math_funcs/pow.rs:120-125 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/math_funcs/pow.rs: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. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060base\u0060 to \u0060f64\u0060 in one and \u0060\u0026Float64Array\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":"native/spark-expr/src/math_funcs/pow.rs"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"14a31244405c4d14a1a56f07867548402a117ccf06cd6e359d08efdf076a799d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 4): native/spark-expr/src/math_funcs/checked_arithmetic.rs:349-357 | native/spark-expr/src/math_funcs/div.rs:88-96 | native/spark-expr/src/math_funcs/modulo_expr.rs:92-100 | native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:197-205 \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. 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":"native/spark-expr/src/math_funcs/checked_arithmetic.rs"},"region":{"startLine":349}}}],"partialFingerprints":{"codehealthFindingId/v1":"45bc3db28366e8f7dd2b1e5571bcbc189da693756557ac32311a86bd67734b96"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): native/spark-expr/src/kernels/temporal.rs:201-205 | native/spark-expr/src/kernels/temporal.rs:218-222 | native/spark-expr/src/kernels/temporal.rs:229-233 \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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6cb51e785a07c167e7ff91d375ec2a6998d4d29fd614e273bb5cf657197882e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (4\u20135 lines \u00D7 3): native/shuffle/src/writers/rss/rss_partition_writer.rs:667-671 | native/shuffle/src/writers/rss/rss_partition_writer.rs:832-836 | native/shuffle/src/writers/rss/rss_partition_writer.rs:945-948 \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 \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:667\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: the declarations holding them bind \u0060array\u0060 to \u0060\u0026dyn Array\u0060 in one and \u0060\u0026ArrayRef\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. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:944\u0060 calls \u0060List\u0060, \u0060as_any\u0060, \u0060unwrap\u0060 and \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:832\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":667}}}],"partialFingerprints":{"codehealthFindingId/v1":"4571875e9c7ed108daf7bea7104662bc5b5521990a390c01c8632fbf25b1782d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/iceberg_funcs/temporal.rs:135-140 | native/spark-expr/src/kernels/temporal.rs:409-414 \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":"native/spark-expr/src/iceberg_funcs/temporal.rs"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"1568f4298ea0ebe08ae0cc10a24acd71a9a2914b4a2470485f54890164cd4429"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/spark-expr/src/math_funcs/div.rs:96-100 | native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs:205-210 \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 \u0060native/spark-expr/src/math_funcs/div.rs: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":"native/spark-expr/src/math_funcs/div.rs"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"f35b3cdf23b28dcfff39508e72996f666c13fb94a82e28d455d82ad08c064e69"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/spark-expr/src/string_funcs/levenshtein.rs:415-419 | native/spark-expr/src/string_funcs/levenshtein.rs:487-491 \u2014 both copies are in the same file, so extract the block 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 \u0060native/spark-expr/src/string_funcs/levenshtein.rs:415\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":"native/spark-expr/src/string_funcs/levenshtein.rs"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"171cc545bb6209ad78cbb8a742466ed378099b0fc431fec22f7860313418275e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): native/spark-expr/src/agg_funcs/covariance.rs:49-54 | native/spark-expr/src/agg_funcs/stddev.rs:48-53 | native/spark-expr/src/agg_funcs/variance.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/agg_funcs/covariance.rs"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd729730ae1f8f4afe00d6cce6813095e2c3e27ec62ebd5efd174ffc5ad138e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/agg_funcs/min_max.rs:87-93 | native/spark-expr/src/agg_funcs/min_max_struct.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/agg_funcs/min_max.rs"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"c57f89ae8b7900ca9a08648f080b037cd42a0250dbe63d5c5300f1b3bbaead13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/spark-expr/src/datetime_funcs/make_date.rs:167-174 | native/spark-expr/src/datetime_funcs/make_time.rs:164-171 \u2014 before extracting anything, compare \u0060native/spark-expr/src/datetime_funcs/make_date.rs\u0060 and \u0060native/spark-expr/src/datetime_funcs/make_time.rs\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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/datetime_funcs/make_date.rs"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5d10d213a062f888ee4d2ea6708a8763ed2d43db1cec255c53a345951b0b5ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/spark-expr/src/conversion_funcs/cast.rs:92-96 | native/spark-expr/src/math_funcs/internal/checkoverflow.rs:57-61 \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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"f524642b626cfa78fc7462b6ce12c25a092483086450dbd4e745378e55c3cb6c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/conversion_funcs/string.rs:1356-1362 | native/spark-expr/src/conversion_funcs/utils.rs:132-138 \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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1356}}}],"partialFingerprints":{"codehealthFindingId/v1":"b48ea48648a53e9d7c1a43caacef17585c918571870731ed3c4e59116401dca2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/math_funcs/ceil.rs:95-100 | native/spark-expr/src/math_funcs/floor.rs:95-100 \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":"native/spark-expr/src/math_funcs/ceil.rs"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca215157eca9c5eb5cc7e2c6947da0288e9aa03c473a9ea86d2748566ec649bd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/spark-expr/src/math_funcs/negative.rs:179-184 | native/spark-expr/src/nondetermenistic_funcs/shuffle.rs:129-134 \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 \u0060native/spark-expr/src/math_funcs/negative.rs: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":"native/spark-expr/src/math_funcs/negative.rs"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe67aba2c4677a933c425d180d4a0bc8a465384de7b5f11abf94edb09cd54860"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/string_funcs/get_json_object.rs:70-79 | native/spark-expr/src/string_funcs/split.rs:120-128 \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 \u0060native/spark-expr/src/string_funcs/get_json_object.rs:70\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":"native/spark-expr/src/string_funcs/get_json_object.rs"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"fda44c3d7e694c7b4dcf465dceaab0e4de3adc10409d1b9681b856fb48823d62"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 4): native/spark-expr/src/array_funcs/array_contains.rs:70-79 | native/spark-expr/src/array_funcs/array_remove.rs:72-78 | native/spark-expr/src/array_funcs/sort_array.rs:89-94 | native/spark-expr/src/array_funcs/sort_array.rs:144-148 \u2014 before extracting anything, compare \u0060native/spark-expr/src/array_funcs/array_contains.rs\u0060 and \u0060native/spark-expr/src/array_funcs/array_remove.rs\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 \u0060native/spark-expr/src/array_funcs/array_contains.rs:70\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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"6fb7d7497f97390ce5a942069baaad2fac1f64f5d1e97af610c0379503ceb9d2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/spark-expr/src/math_funcs/signum.rs:28-36 | native/spark-expr/src/math_funcs/sqrt.rs: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 both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/spark-expr/src/math_funcs/signum.rs:28\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":"native/spark-expr/src/math_funcs/signum.rs"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ddbdff38d2beb171dd1d4a77731a3350ed7fc420fde5b583a0534ceeb80f336"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): native/core/src/execution/operators/arrow_python_udf.rs:157-165 | native/core/src/execution/operators/arrow_python_udf.rs:171-179 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/operators/arrow_python_udf.rs:157\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":"native/core/src/execution/operators/arrow_python_udf.rs"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc36de78207a1d2ce3e7d4363cba856b456f262b2f3ebfb8091e9eb04b9a32a8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/core/src/execution/planner/aggregate.rs:404-411 | native/core/src/execution/planner/aggregate.rs:418-425 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/planner/aggregate.rs:404\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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":404}}}],"partialFingerprints":{"codehealthFindingId/v1":"959a2f4bf7560f643b211d60f9b270bce5be2494bffcaebc8d1a4651cf9e6232"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): native/core/src/execution/planner/aggregate.rs:501-508 | native/core/src/execution/planner/aggregate.rs:513-520 \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 \u0060native/core/src/execution/planner/aggregate.rs:501\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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":501}}}],"partialFingerprints":{"codehealthFindingId/v1":"39ec237f84e543f9d4a0c0a77a71530afb05405fe12e0bad1712fe0a7b810413"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/agg_funcs/collect.rs:335-341 | native/spark-expr/src/agg_funcs/collect.rs:681-687 \u2014 both copies are in the same file, so extract the block 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":"native/spark-expr/src/agg_funcs/collect.rs"},"region":{"startLine":335}}}],"partialFingerprints":{"codehealthFindingId/v1":"ffd53ec17d412392ea21e283b01dede3c6b31d77b10a778134622b6f8134a641"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/shuffle/src/spark_unsafe/list.rs:169-175 | native/shuffle/src/spark_unsafe/map.rs:37-43 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060native/shuffle/src/spark_unsafe/list.rs:169\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":"native/shuffle/src/spark_unsafe/list.rs"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"548cf7181222a1915b588ea15a11eb317a6880ac6efc62bc3b94339b0363d103"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/comet-udf-sdk/src/c_abi.rs:505-509 | native/comet-udf-sdk/src/c_abi.rs:562-566 \u2014 both copies are in the same file, so extract the block 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":"native/comet-udf-sdk/src/c_abi.rs"},"region":{"startLine":505}}}],"partialFingerprints":{"codehealthFindingId/v1":"325baca3dffa7ab525675b7aba961d6d4748bbbdd2a22f316dc22bc8db2baf55"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): native/core/src/execution/c_udf/mod.rs:109-114 | native/core/src/execution/c_udf/mod.rs:166-171 \u2014 both copies are in the same file, so extract the block 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 \u0060native/core/src/execution/c_udf/mod.rs: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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/c_udf/mod.rs"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d72543b109e356a6379524079d01b25a6dbd9203283483c38e71e5da0b9aa70"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/core/src/execution/planner.rs:549-553 | native/core/src/parquet/parquet_exec.rs:199-203 \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 \u0060native/core/src/execution/planner.rs:549\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":"native/core/src/execution/planner.rs"},"region":{"startLine":549}}}],"partialFingerprints":{"codehealthFindingId/v1":"aaec56714df6cd2eeb5f8d258741e675b4e1a10f8c100e982b7edf7bc2bbbf31"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/core/src/execution/planner/aggregate.rs:555-559 | native/core/src/execution/planner/aggregate.rs:655-659 \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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":555}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1fb3b762c0b7298e1b88d4f45bce2dd114999253b01fb323b4b035edc0b3188"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): native/shuffle/src/writers/rss/rss_partition_writer.rs:711-715 | native/shuffle/src/writers/rss/rss_partition_writer.rs:886-890 \u2014 both copies are in the same file, so extract the block 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 \u0060native/shuffle/src/writers/rss/rss_partition_writer.rs:711\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":711}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cb66a8b86535bc7d0712fdd5806894f1e9f439e8eec521f8886177eecfeb8cd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): native/spark-expr/src/array_funcs/array_contains.rs:174-180 | native/spark-expr/src/array_funcs/array_contains.rs:207-213 \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 \u0060native/spark-expr/src/array_funcs/array_contains.rs:174\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":"native/spark-expr/src/array_funcs/array_contains.rs"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"103ca82c8843786ddc766f9abd9b6cd0cad791436e8f2d4693b6ab8a11d33a9b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (33\u201336 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:239-271 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:262-297 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:239\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"092c94a8fcc2713f52975fd0a2722ce0c92299ff53ae589b0a5529184e655608"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:60-94 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:60-94 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1922221bd83a98a953f3e1a86b2ad89d8070f18a7bf28c2da64d294ac7d9d04"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:415-449 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:438-472 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f417ca18949b2bdde11e681da36e455664c840b6a0d2a5f7c44d18b14192bf4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27\u201328 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:174-200 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:203-230 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:174\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"0725754474f60f82378aed5a1694bba12a2b9e0bf9134e538dc229f925fe566e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (36\u201337 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:84-120 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:84-120 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:101-136 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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 \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:84\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, \u0060spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:137\u0060 calls \u0060setSemanticMetricsRequired\u0060 and \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:121\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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f1ed4d905cda2d201229584f17a17598d55d03b390fca0f8287d99a90e59ab4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22\u201323 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:142-164 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:168-189 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:142\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, \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:190\u0060 calls \u0060getOrElse\u0060 and \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:165\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"a71e759f7bce014a8fc7c0f593e2cb5b62fee512fd40ef3523a1a7521a7ae509"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala:94-118 | spark/src/main/scala/org/apache/spark/sql/comet/CometScanExec.scala:189-213 \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":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6a8aa58db75ca81bd213161731e089abb01bf944393177b3c5042606a7d53e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201321 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:2904-2924 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3712-3731 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:2904\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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":2904}}}],"partialFingerprints":{"codehealthFindingId/v1":"c91548120a28c47f0437411e7ae3e1aa073daac801fc89fe9b2e431eee29e79a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala:41-60 | spark/src/main/spark-4.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala:41-60 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala\u0060 as WHOLE FILES: 89% 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 \u0060spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.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":"spark/src/main/spark-3.x/org/apache/comet/iceberg/IcebergDeltaWriterShim.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b47a2dfacff052af2c8689d56b011301b42ed8ce5da8f90d0bcdc4dd8c5d15d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 4): spark/src/main/spark-3.5/org/apache/comet/iceberg/IcebergDeltaLogicalShim.scala:28-46 | spark/src/main/spark-4.0/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 | spark/src/main/spark-4.1/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 | spark/src/main/spark-4.2/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala:28-46 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/iceberg/IcebergDeltaLogicalShim.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/iceberg/IcebergDeltaLogicalFieldsShim.scala\u0060 as WHOLE FILES: 95% 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-3.5/org/apache/comet/iceberg/IcebergDeltaLogicalShim.scala"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"673b52b6c4089a63832f9e3053399b0f03dcda9ee0f2686e0393074ad8507c98"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (19 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:287-305 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:315-333 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:287\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":287}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fbf27ca94f1f9a7d69e1086f7559ee0e5489d2e393f0969b4ef81d4e1418052"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201319 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:381-399 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:407-418 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:381\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, \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:419\u0060 calls \u0060Some\u0060, \u0060CometPythonException\u0060, \u0060params\u0060 and \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:405\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":381}}}],"partialFingerprints":{"codehealthFindingId/v1":"1fcc137477ea2b6053d9f8da07dbfa794b66926a1dcf5fbb0c08f16fc57dfdb8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:211-228 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:211-228 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:247-264 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"da14513590b9b83fa6b92d88f7690bdfefbbf5f0fd0326f0a235cb942e7f507a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): spark/src/main/scala/org/apache/comet/serde/strings.scala:641-658 | spark/src/main/scala/org/apache/comet/serde/strings.scala:679-696 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/comet/serde/strings.scala"},"region":{"startLine":641}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ad8a88e0953578d1f729a1bcc8b770565fe95f27ba88383468b095ab5af39e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:121-136 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:121-136 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:138-153 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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 \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:121\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, \u0060spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:137\u0060 calls \u0060setSemanticMetricsRequired\u0060 and \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:120\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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"76c5d8f41cf9ba96ba86dbb50380e973d46c32217f690508aa4b21a6adf1825c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometWindowGroupLimit.scala:37-52 | spark/src/main/spark-4.x/org/apache/comet/shims/ShimCometWindowGroupLimit.scala:38-53 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometWindowGroupLimit.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/comet/shims/ShimCometWindowGroupLimit.scala\u0060 as WHOLE FILES: 95% 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometWindowGroupLimit.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"f033deeccb44a379fa10e7976c7428ca9cb74746b7fd939f3347c61495088367"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u201315 lines \u00D7 3): spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:491-505 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:557-564 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:598-605 \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 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, \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:490\u0060 calls \u0060createSizeMetric\u0060 and \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:556\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":"spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala"},"region":{"startLine":491}}}],"partialFingerprints":{"codehealthFindingId/v1":"a04e94aaf460cc5331aff1061b04df8e9704d37d6ba5f7417952155234702d30"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201315 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:399-412 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:421-435 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:399\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, \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:419\u0060 calls \u0060Some\u0060, \u0060CometPythonException\u0060, \u0060params\u0060 and \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:397\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":399}}}],"partialFingerprints":{"codehealthFindingId/v1":"8968a69aa3762c58a3363214ccf2741a3f5dcd190662e1424754934c4e32d9e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:143-156 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:143-156 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:160-173 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":143}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f885b936d055a0f17350a55f83fa05c8a57bb7da379099a89fff2d8b8047160"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimCometShuffleMaterialization.scala:33-46 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimCometShuffleMaterialization.scala:36-49 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimCometShuffleMaterialization.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimCometShuffleMaterialization.scala\u0060 as WHOLE FILES: 94% 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. Note first that the copies are not typed on the same thing: \u0060SparkSession\u0060 names \u0060org.apache.spark.sql.SparkSession\u0060 in one and \u0060org.apache.spark.sql.classic.SparkSession\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimCometShuffleMaterialization.scala"},"region":{"startLine":33}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e748ec4376f4c8bbf9b9490bc834d38d80f1852836c07caf3525b39cf82144d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201314 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:351-363 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:381-394 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala: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. 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":351}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d503f182d5eccac5569b1eefee322b3f88c1e4cd868c1b0dc547ff16b9ccf3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): spark/src/main/scala/org/apache/comet/serde/arrays.scala:502-513 | spark/src/main/scala/org/apache/comet/serde/arrays.scala:1192-1204 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":502}}}],"partialFingerprints":{"codehealthFindingId/v1":"342c04e93f3cfd8f3fb839ca089d5c75215c58aa06c358d5c432fcbfce2264ea"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala:34-46 | spark/src/main/spark-4.x/org/apache/comet/serde/CometToPrettyString.scala:34-46 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/comet/serde/CometToPrettyString.scala\u0060 as WHOLE FILES: 100% 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":"spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"7d89609ec5fd86fd88a0f37b77a64ee3025d8c200fca5751e3030fb6719553b4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala:52-64 | spark/src/main/spark-4.x/org/apache/comet/serde/CometToPrettyString.scala:52-64 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/comet/serde/CometToPrettyString.scala\u0060 as WHOLE FILES: 100% 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":"spark/src/main/spark-3.5/org/apache/comet/serde/CometToPrettyString.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"12f5ad931295695036fd3c58618e4a8890286bdb9e2a4eb42c7b3f54b28ec4f6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:118-129 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:143-155 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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 \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:118\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc2f27ff62623828b2e7f13068118c56ed93f338acf95298ce9186f46ff41401"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:482-492 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:501-511 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"65623584555cd5dbb9f7b337f6926c0bc1e694f81ffcc04ad363c8c491e26e54"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala:555-565 | spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala:618-628 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala:555\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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala"},"region":{"startLine":555}}}],"partialFingerprints":{"codehealthFindingId/v1":"5743615b145ff719ecfed91a21bbed5b1bcf0819363b10d9e719c65c52ebb334"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 5): contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1135-1147 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1240-1249 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1296-1305 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1354-1363 | contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1652-1661 \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 \u0060contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala:1135\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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":1135}}}],"partialFingerprints":{"codehealthFindingId/v1":"6cda4c36aca8008e0fbc9fa2525e364adf1f92868bb5029893a29eac794f3c1b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:446-455 | spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:464-473 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":446}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdbdd175e24757df89bb5a4460ce4640db057ce03406c2870d454afceb7f3d9e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3176-3185 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3471-3480 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3176\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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":3176}}}],"partialFingerprints":{"codehealthFindingId/v1":"a48b713f083a271a5056554b785d57c4a94ed8b980f9d12e2787414a87827d92"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3443-3452 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3833-3842 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":3443}}}],"partialFingerprints":{"codehealthFindingId/v1":"4363ecbffb5a7e31a88d643c56fe8a3441ee7e83e3af2b2f69c498bc1608ec05"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:60-68 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:60-68 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:70-78 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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 \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.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. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:79\u0060 calls \u0060mergeActionContext\u0060 and \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:69\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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"88ff81f04c990be0d460ff4046dd2e626e36de6b23ded4efe510bc7bf06bd5dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/src/main/scala/org/apache/comet/serde/arrays.scala:51-59 | spark/src/main/scala/org/apache/comet/serde/arrays.scala:252-260 \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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/src/main/scala/org/apache/comet/serde/arrays.scala:51\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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":51}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ffb6fdf42a20ed792c0efa01d6f384b005f2c09e967d604553877a60cce7428"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala:970-978 | spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala:987-996 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala:970\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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeScan.scala"},"region":{"startLine":970}}}],"partialFingerprints":{"codehealthFindingId/v1":"cab016bf6c92d71821211972c79ef361b5040e54308b6c9df0595d76c3f7d0c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:111-119 | spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:143-151 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:111\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":"spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"e78a9a9718a11eb3c9197b902592876ec2caa4041e0183fde3099737faa8756d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:69-76 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:69-76 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:80-87 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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, \u0060spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:79\u0060 calls \u0060mergeActionContext\u0060 and \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala: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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"6827c2f304b93039fa821f067e797eaac941eba387d3606da010508772e0f1df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 5): spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:497-507 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:515-523 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:559-564 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:581-589 | spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:600-605 \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. 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, \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:558\u0060 calls \u0060createSizeMetric\u0060 and \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala:496\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":"spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"a562d597b4e9c962536d054277aac0940166fe943d02bd7e8408a1259467567b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/src/main/scala/org/apache/comet/serde/conditional.scala:73-79 | spark/src/main/scala/org/apache/comet/serde/conditional.scala:113-119 \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 \u0060spark/src/main/scala/org/apache/comet/serde/conditional.scala:73\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":"spark/src/main/scala/org/apache/comet/serde/conditional.scala"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"117d8b4a6e18ccd435bbe38222a6e0fed1982bea12188e00d8b30a0650a3c022"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3468-3473 | spark/src/main/scala/org/apache/spark/sql/comet/operators.scala:3622-3627 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":3468}}}],"partialFingerprints":{"codehealthFindingId/v1":"a24adeb4617699531a0546623cec808007478349f7da24a3f310417d17e2c9ca"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala:40-46 | spark/src/main/spark-4.1\u002B/org/apache/comet/shims/CometExprShim.scala:43-49 \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 \u0060spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala:40\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":"spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"e95d0c26950613452d0d9721bbb250353b0e2bcb40acdc951dad5152b68c367e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometBroadcastExchangeExec.scala:31-43 | spark/src/main/spark-4.x/org/apache/comet/shims/ShimCometBroadcastExchangeExec.scala:31-43 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometBroadcastExchangeExec.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/comet/shims/ShimCometBroadcastExchangeExec.scala\u0060 as WHOLE FILES: 100% 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-3.5/org/apache/comet/shims/ShimCometBroadcastExchangeExec.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"66f9dc1cf7fa9d3440210726bef4eb6a20479bf987872145b67f04bca6eda33d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala:1034-1043 | spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala:66-75 | spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala:68-77 \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 all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala:1034\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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1034}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed004b392e11687f876b0b878140eeca1dea55bd84b9abf7098bc6e6f3c155e9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): spark/src/main/scala/org/apache/comet/serde/json.scala:45-50 | spark/src/main/scala/org/apache/comet/serde/strings.scala:165-170 | spark/src/main/scala/org/apache/comet/serde/strings.scala:764-769 | spark/src/main/scala/org/apache/comet/serde/strings.scala:824-829 \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. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060expr\u0060 to \u0060LengthOfJsonArray): SupportLevel = if (!CometConf.isExprAllowIncompat(getExprConfigName(expr))\u0060 in one and \u0060InitCap): SupportLevel = if (!CometConf.isExprAllowIncompat(getExprConfigName(expr))\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":"spark/src/main/scala/org/apache/comet/serde/json.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"864019d0011ccf10503f5c36dc4b331a4d601b8eb534402b0ee450c140fb18e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): spark/src/main/scala/org/apache/comet/serde/strings.scala:716-721 | spark/src/main/scala/org/apache/comet/serde/structs.scala:137-142 | spark/src/main/scala/org/apache/comet/serde/structs.scala:206-211 \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. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060expr\u0060 to \u0060RegExpReplace): SupportLevel = if (!CometConf.isExprAllowIncompat(getExprConfigName(expr)) \u0026\u0026 nativeSupported(expr)\u0060 in one and \u0060StructsToJson): SupportLevel = if (!CometConf.isExprAllowIncompat(getExprConfigName(expr)) \u0026\u0026 nativeSupported(expr)\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":"spark/src/main/scala/org/apache/comet/serde/strings.scala"},"region":{"startLine":716}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbb8e139ff1b97783beff62f01684607ae6e1b8306bbb7d501875e1e093462f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:46-54 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:46-54 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"a2787940bfad0ee7220ef68b6cfa43c4c25d9a89ab368a1e97913dbe1d686d93"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:186-191 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:186-191 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:203-208 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"69932b3f87abc3eee391ce74f858bfa1ad12d997a30940975d2cf13137560e7c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:201-207 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:201-207 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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 \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:201\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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":201}}}],"partialFingerprints":{"codehealthFindingId/v1":"92eaba2cd1933b48e546e35a6a09ac8c46d312f2ec09e38da931e9a6264b4c7a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala:236-241 | spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala:236-241 | spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.scala:272-277 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala\u0060 and \u0060spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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. 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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":236}}}],"partialFingerprints":{"codehealthFindingId/v1":"03509688999c966da2316f819782b2bc930c5691965f528eb597a349c8c365ab"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): spark/src/main/spark-3.5/org/apache/comet/shims/CometExprShim.scala:59-63 | spark/src/main/spark-4.0/org/apache/comet/shims/CometExprShim.scala:50-54 | spark/src/main/spark-4.1\u002B/org/apache/comet/shims/CometExprShim.scala:122-126 \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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-3.5/org/apache/comet/shims/CometExprShim.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac807e76f3b7f37e6490d294dfdbdd2f21ecb02a73aaa2ec372e3ff44f008efa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:48-55 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:44-51 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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, \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:45\u0060 calls \u0060sqlCtx\u0060, \u0060getOrElse\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:42\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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c74a2019e2a64249734fb9516613e62c5e4eab7ead337ba72dcfebf6674b39d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:57-65 | spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala:53-61 \u2014 before extracting anything, compare \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 as WHOLE FILES: this scan already matched 11 separate duplicated blocks between them, totalling at least 219 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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"da312b1fae455a5e06a98e655d445381ba02c3bd2021793c13fb653ff65ea34c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): spark/src/main/spark-4.1/org/apache/spark/sql/comet/shims/ShimCometMapInBatch.scala:39-50 | spark/src/main/spark-4.2/org/apache/spark/sql/comet/shims/ShimCometMapInBatch.scala:39-50 \u2014 before extracting anything, compare \u0060spark/src/main/spark-4.1/org/apache/spark/sql/comet/shims/ShimCometMapInBatch.scala\u0060 and \u0060spark/src/main/spark-4.2/org/apache/spark/sql/comet/shims/ShimCometMapInBatch.scala\u0060 as WHOLE FILES: 100% 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-4.1/org/apache/spark/sql/comet/shims/ShimCometMapInBatch.scala"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"40a410ba8c5850d60c391a312b0a8e58b485a65ab61200f928f382d06bc6cba5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): spark/src/main/spark-4.1/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala:63-67 | spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala:71-75 \u2014 before extracting anything, compare \u0060spark/src/main/spark-4.1/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala\u0060 and \u0060spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala\u0060 as WHOLE FILES: 88% 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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/spark-4.1/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9c326da9e8aca011f29bd2929f9b1233957516fb92676431eb354e3db02baed"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.java:475-485 | spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.java:544-554 \u2014 both copies are in the same file, so extract the block 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 \u0060spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.java:475\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":"spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.java"},"region":{"startLine":475}}}],"partialFingerprints":{"codehealthFindingId/v1":"087623bb7423a03ca34fee29535403f203afcf4d265c137b3de958e7bd99ce80"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java:194-200 | spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java:334-340 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java"},"region":{"startLine":194}}}],"partialFingerprints":{"codehealthFindingId/v1":"01a9adaab7b96dd880f2f2237b99393f89075e7a10fc7ebc282c77f178f14f08"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 9): spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:392-396 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:402-406 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:412-416 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:422-426 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:432-436 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:442-446 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:453-457 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:465-469 | spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java:474-478 \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 \u0060spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.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":"spark/src/main/java/org/apache/comet/DirectColumnarToRowConverter.java"},"region":{"startLine":392}}}],"partialFingerprints":{"codehealthFindingId/v1":"dca0c4b1758cf96dee2dd6d62efbf9dd1aaaaa2e5ab525c33ac96a132a8728fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): spark/src/main/java/org/apache/comet/vector/CometListVector.java:58-63 | spark/src/main/java/org/apache/comet/vector/CometMapVector.java:79-84 | spark/src/main/java/org/apache/comet/vector/CometStructVector.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 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":"spark/src/main/java/org/apache/comet/vector/CometListVector.java"},"region":{"startLine":58}}}],"partialFingerprints":{"codehealthFindingId/v1":"f194dd5f30611dd44c7c39f0a63c9b7f49930d9b13086712c222655c3a9a1600"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/src/main/java/org/apache/comet/vector/CometPlainVector.java:142-148 | spark/src/main/java/org/apache/comet/vector/CometPlainVector.java:174-180 \u2014 both copies are in the same file, so extract the block 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":"spark/src/main/java/org/apache/comet/vector/CometPlainVector.java"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"052e6df5c43e3c95ba59f3c594431e648cff3a2dea81b24e0705320dad49b4de"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometBypassMergeSortShuffleWriter.java:46-50 | spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.java:56-60 \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."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometBypassMergeSortShuffleWriter.java"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c9f0e0ebd351baf441192671a40b426931b321eee1beeee4c23b9eb805b328e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201316 lines \u00D7 2): dev/ci/check-ci-config.py:698-709 | dev/ci/check-ci-config.py:726-741 \u2014 both copies are in the same file, so extract the block 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":"dev/ci/check-ci-config.py"},"region":{"startLine":698}}}],"partialFingerprints":{"codehealthFindingId/v1":"a39e9244a45e2b79bcdc455ff730a34def4c92e4037c89c4b388bb47b59dc3c3"}},{"ruleId":"D5","level":"warning","message":{"text":"Unstable project datafusion-comet: datafusion-comet has instability 0.90 with 1 dependents."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"e475a811e405bd3047a852c0afd7f0f9d82bb2c239d18027888204776b1d1073"}},{"ruleId":"D5","level":"warning","message":{"text":"Off the main sequence: comet-udf-sdk: comet-udf-sdk: abstractness 0.17, instability 0.00, distance 0.83 \u2014 zone of pain \u2014 concrete and depended on by 1 project(s), so it\u0027s rigid to change."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"d8e99c5a550ab65ec3f7e16648496da2eb324afbc8513d5b27004fa8fe6c98b5"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/execution/planner.rs: native/core/src/execution/planner.rs changed 104 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 44 in PhysicalPlanner::create_expr at line 766. 38 of those changes were fix/bug commits, and the other 66 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/planner.rs\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":"native/core/src/execution/planner.rs"},"region":{"startLine":766}}}],"partialFingerprints":{"codehealthFindingId/v1":"06e23be15dbae87cb4a28fcd43594648762b799b0d23261201f5739cedd59581"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala: spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala changed 29 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 103 in CometScanRule.transformV2Scan at line 387. 17 of those changes were fix/bug commits, so the churn is repair rather than feature work. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/rules/CometScanRule.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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":387}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d6c2748121e9459cb808e96f1c9cae77939b9afb37e2f1c38050593311c7280"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala: spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala changed 53 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 55 in CometExecRule.transform at line 441. 23 of those changes were fix/bug commits, and the other 30 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/rules/CometExecRule.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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":441}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f660cb7290806240597ac2d3b4caf82ecead08b095c5af486005c1cbb8b0de0"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/operators.scala: spark/src/main/scala/org/apache/spark/sql/comet/operators.scala changed 52 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 41 in CometNativeExec.buildNativeContext at line 991. 26 of those changes were fix/bug commits, and the other 26 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/operators.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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":991}}}],"partialFingerprints":{"codehealthFindingId/v1":"89cfda83e9c0be4bc9bc20dd2a1466802acf8fafb436411a59ec1f38b4883130"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala: spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala changed 35 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 35 in QueryPlanSerde.serializeDataType at line 646. 15 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":646}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a8599d11f11b399790ea30f20492a46bb078bffee22a99e53876ce66a1f6b89"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala changed 10 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 70 in CometWindowExec.windowExprToProto at line 261. 7 of those changes were fix/bug commits, so the churn is repair rather than feature work. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowExec.scala"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"222cd0e925c733c459df3fc65a249f42dc7e54e2a5e64fd91a767c404fccd375"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala changed 22 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 31 in CometShuffleExchangeExec.nativeShuffleFailureReasons at line 600. 11 of those changes were fix/bug commits, and the other 11 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"20316511f6e2ff1c74e0e9f52cd62b27bb010a3b6dc7a69cedf90de51fcb990a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/parquet/parquet_support.rs: native/core/src/parquet/parquet_support.rs changed 27 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 24 in datafusion_comet::parquet::parquet_support::parquet_convert_array_impl at line 220. 18 of those changes were fix/bug commits, so the churn is repair rather than feature work. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/parquet_support.rs\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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e4e5bd2f6224ffb8cac517e7666588588366bdecc479a7dc415e1ff3bedc01c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/conversion_funcs/cast.rs: native/spark-expr/src/conversion_funcs/cast.rs changed 12 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 53 in datafusion_comet_spark_expr::conversion_funcs::cast::cast_array at line 254. 8 of those changes were fix/bug commits, so the churn is repair rather than feature work. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/conversion_funcs/cast.rs\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":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"51b9c98de67242bc9eef27fc0db3341aa5fc894764bff1d56eefac73804f0e42"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/shuffle/src/spark_unsafe/row.rs: native/shuffle/src/spark_unsafe/row.rs changed 9 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 68 in datafusion_comet_shuffle::spark_unsafe::row::append_struct_fields_field_major at line 823. 1 of those changes was a fix/bug commit, and the other 8 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/shuffle/src/spark_unsafe/row.rs\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":"native/shuffle/src/spark_unsafe/row.rs"},"region":{"startLine":823}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc4eb4a970395cf7c33ff64847d07d5f60c400970d762580f5fa2eeff911b415"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala: spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala changed 9 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 65 in ShimSparkErrorConverter.convertErrorType at line 80. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.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":"spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"385f55aef7a873c6cde0036622ffc5eed839953f561307ed8d1c095a451222b8"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/expressions/CometCast.scala: spark/src/main/scala/org/apache/comet/expressions/CometCast.scala changed 15 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 37 in CometCast.isSupported at line 225. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/expressions/CometCast.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":"spark/src/main/scala/org/apache/comet/expressions/CometCast.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2a38bffe194f088a32e22b9689f62eeb8da00224b8ac7bcd7fbb989b91f2b35"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: dev/ci/check-ci-config.py: dev/ci/check-ci-config.py changed 25 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in check-ci-config.check_event_policy at line 785. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- dev/ci/check-ci-config.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/ci/check-ci-config.py"},"region":{"startLine":785}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6d7c2c0503a4c817385ab88625f89749ec6a90fcabe1f6466e7b0b0f7c87607"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala: spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 62 in ShimSparkErrorConverter.convertErrorType at line 67. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.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":"spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab5490d8648b59e8c832e46543591c8ad4c051d9057055683e255baaccbe47fe"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/parquet/schema_adapter.rs: native/core/src/parquet/schema_adapter.rs changed 19 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 21 in datafusion_comet::parquet::schema_adapter::spark_has_updater at line 543. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/schema_adapter.rs\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":"native/core/src/parquet/schema_adapter.rs"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3b679725325e3ba9db9c267f02df6c183f53c39ecba748acaf50a26e15f2703"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/conversion_funcs/string.rs: native/spark-expr/src/conversion_funcs/string.rs changed 13 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in datafusion_comet_spark_expr::conversion_funcs::string::parse_sign_offset at line 1691. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/conversion_funcs/string.rs\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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":1691}}}],"partialFingerprints":{"codehealthFindingId/v1":"4bd535fae2179522ed0b4d273b54d8470d7eb282a6cf85b10b0fe7e2e23c0104"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala: spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala changed 15 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in CometNativeScan.isSupported 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.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":"spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"792f8c0d9bd83fe39952c79f7d07322535cfb9d46ee7a5b337ef9dbbc4330b8b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 35 in FixedWidthArrowFieldWriter.copyValues at line 815. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":815}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb66eea03c7b2dd618347b2244e1750869c17249c6f8a98c1ff1fc2b6044c39e"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/parquet/eager_page_index_reader_factory.rs: native/core/src/parquet/eager_page_index_reader_factory.rs changed 11 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 21 in EagerPageIndexReader::get_metadata at line 661. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/eager_page_index_reader_factory.rs\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":"native/core/src/parquet/eager_page_index_reader_factory.rs"},"region":{"startLine":661}}}],"partialFingerprints":{"codehealthFindingId/v1":"955e1eb6f4228eefbffde9ca7bff79e4d8d5e6059fa551c41de82eaf269e729f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.scala changed 14 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in CometNativeShuffleWriter.writeInternal at line 114. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleWriter.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"340aba55914ce5a24581562648d81ae70c7109939597fc035c56f48df1db0532"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.scala: spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.scala changed 9 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in CometBatchKernelCodegen.canHandle at line 174. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.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":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.scala"},"region":{"startLine":174}}}],"partialFingerprints":{"codehealthFindingId/v1":"81e6201d3e43ec9d51a983f6456322a440408f1e008ea70a6352c994c7879681"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala: spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in EliminateRedundantTransitions._apply at line 79. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.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":"spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"109e28f869c2d73c2185b72caf49a022c8c23d797ed95544b53f64181c1737c6"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/comet/serde/literals.scala: spark/src/main/scala/org/apache/comet/serde/literals.scala changed 7 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in CometLiteral.makeListLiteral at line 147. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/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":"spark/src/main/scala/org/apache/comet/serde/literals.scala"},"region":{"startLine":147}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba87d4fcebe25f741637a77931c67cbb36241c70c61fe91f694e5dac64a4962f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/execution/planner/aggregate.rs: native/core/src/execution/planner/aggregate.rs changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 44 in PhysicalPlanner::create_agg_expr at line 374. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/planner/aggregate.rs\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":"native/core/src/execution/planner/aggregate.rs"},"region":{"startLine":374}}}],"partialFingerprints":{"codehealthFindingId/v1":"141f7a6c99f408f4c5b1630b1eae7c0815a2f9dd75e9b29b0f2e51c8d9bd7b12"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala changed 8 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 16 in CelebornShuffleGenerationCoordinator.claimMapAttempt at line 851. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleManager.scala"},"region":{"startLine":851}}}],"partialFingerprints":{"codehealthFindingId/v1":"5365560a7155c6f5931d757efc32f3e62d74016760cd571c27c8ff940d012b87"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java: spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 32 in CelebornShufflePartitionPusher.\u003Cinit\u003E at line 199. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.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":"spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java"},"region":{"startLine":199}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc108dd699aacc1882c331ff29ec0197e1f394e4d17f7e95becb12158b7bc0b7"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/execution/operators/dynamic_filter/parquet_reader.rs: native/core/src/execution/operators/dynamic_filter/parquet_reader.rs changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 20 in datafusion_comet::execution::operators::dynamic_filter::parquet_reader::try_attach_parquet_reader_filter 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/operators/dynamic_filter/parquet_reader.rs\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":"native/core/src/execution/operators/dynamic_filter/parquet_reader.rs"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"34cda24609af526a1c1c7b8de4d6c1d024635c0a9b9e8a949da79f3fbb2e2ab3"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/common/src/bin/analyze_trace.rs: native/common/src/bin/analyze_trace.rs changed 4 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 29 in datafusion_comet_common::bin::analyze_trace::main at line 116. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/common/src/bin/analyze_trace.rs\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":"native/common/src/bin/analyze_trace.rs"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"645b4771f528c3e536187a57f484a2dc58ef9a6dc7f2865c09cdf1a05ef0faaa"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/shuffle/src/writers/rss/rss_partition_writer.rs: native/shuffle/src/writers/rss/rss_partition_writer.rs changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in RssPartitionWriter::push_batch_within_limit at line 154. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/shuffle/src/writers/rss/rss_partition_writer.rs\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":"native/shuffle/src/writers/rss/rss_partition_writer.rs"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"8da9d857ecb2ede4b0cd1e32bb87c26833964e2d1d65749441840d141d847d2f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/array_funcs/arrays_overlap.rs: native/spark-expr/src/array_funcs/arrays_overlap.rs changed 5 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in datafusion_comet_spark_expr::array_funcs::arrays_overlap::arrays_overlap_list_generic at line 545. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/array_funcs/arrays_overlap.rs\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":"native/spark-expr/src/array_funcs/arrays_overlap.rs"},"region":{"startLine":545}}}],"partialFingerprints":{"codehealthFindingId/v1":"10bd183bb595f06e0f0bb27db3e1a72a6871efa9bdb6d3a00e83952375fbee96"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/kernels/temporal.rs: native/spark-expr/src/kernels/temporal.rs changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 21 in datafusion_comet_spark_expr::kernels::temporal::timestamp_trunc_upstream at line 1109. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/kernels/temporal.rs\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":"native/spark-expr/src/kernels/temporal.rs"},"region":{"startLine":1109}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5a070fc0d99a9d6c21b6b658fb1ef084672936dd53dcd295b74b1b55da45c5b"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/core/src/execution/serde.rs: native/core/src/execution/serde.rs changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 28 in datafusion_comet::execution::serde::to_arrow_datatype at line 71. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/serde.rs\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":"native/core/src/execution/serde.rs"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"6024ba0800eb574ff81305b4c26bb9400e1ba525b24f1ec975cc8afdad32d84c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs: native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 17 in WideDecimalBinaryExpr::evaluate 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs\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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c482d49f51d32cb49f4b72f44e35c2216bf645299501ee0c9da593b5791ac2a"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: native/spark-expr/src/math_funcs/div.rs: native/spark-expr/src/math_funcs/div.rs changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 19 in datafusion_comet_spark_expr::math_funcs::div::spark_decimal_div_internal at line 72. 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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/math_funcs/div.rs\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":"native/spark-expr/src/math_funcs/div.rs"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3313967b53c9a6bafd2aa05c194381960940c93617cb26cdd41a84758f8bd8d"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/comet_scalar_funcs.rs: native/spark-expr/src/comet_scalar_funcs.rs changed 23 times in last 90 days and 12 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 2 (its worst body is CometScalarFunction::eq at line 414), 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: \u201Cfix: match SPARK-58821 and SPARK-60118 in sequence and string to decimal cast (#7171)\u201D; \u201Cfix: preserve Spark nested null ordering in native sort (#6968)\u201D; \u201Cfix: treat -0.0 and 0.0 as one value in arrays_overlap on Spark 4.0.5, 4.1.4 and 4.2.1 (#6989)\u201D; \u201Cfix: order nulls inside nested values first in least (#6761)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/comet_scalar_funcs.rs\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":"native/spark-expr/src/comet_scalar_funcs.rs"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"221193ad9afafce4ad395f82a4fc1e91c591ca1f91b617e18848756863cb9c5d"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeWrite.scala: spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeWrite.scala changed 20 times in last 90 days and 12 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 CometIcebergNativeWrite.effectiveHadoopConf at line 356), 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: \u201Cfix: fall back for brotli Iceberg writes when Hadoop\u0027s BrotliCodec cannot be loaded (#6996)\u201D; \u201Cfix: don\u0027t let S3A committer, delete and read defaults block native Iceberg writes (#6808)\u201D; \u201Cfix: load the Iceberg storage scheme lists from the native factory (#6065)\u201D; \u201Cfix: restore Spark write execs when reverting transition-heavy stages (#5957)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeWrite.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":"spark/src/main/scala/org/apache/comet/serde/operator/CometIcebergNativeWrite.scala"},"region":{"startLine":356}}}],"partialFingerprints":{"codehealthFindingId/v1":"08a6577a45fbb805f07dcd84a8d3cbcf5e06e4a52bc34e1f6314334f6ebee4f9"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/serde/aggregates.scala: spark/src/main/scala/org/apache/comet/serde/aggregates.scala changed 21 times in last 90 days and 11 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 9 (its worst body is CometCollectBuffer.canDecode at line 1299), 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: \u201Cfix: preserve float collect_set semantics in distinct aggregate chains (#7220)\u201D; \u201Cfix: pick the signed zero Spark ranks first in native percentile (#6928)\u201D; \u201Cfix: preserve Spark AVG buffer and overflow semantics (#5420)\u201D; \u201Cfix: fall back to Spark for decimal AVG cases that return wrong results (#7017)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/aggregates.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":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":1299}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab81fa43af44372ed97f22ed6e886540347536569738c9f624ea02568096eb89"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/parquet/parquet_exec.rs: native/core/src/parquet/parquet_exec.rs changed 20 times in last 90 days and 11 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 14 (its worst body is datafusion_comet::parquet::parquet_exec::init_datasource_exec at line 87), 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: \u201Cfix: decode invalid UTF-8 in nested Parquet BINARY values read as strings (#7106)\u201D; \u201Cfix: preserve Spark errors for Parquet timestamp overflow (#5891)\u201D; \u201Cfix: normalize float operands in the native comparison builder (#6447)\u201D; \u201Cfix: initialize dispatched kernels with the partition the native plan computes (#6700)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/parquet_exec.rs\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":"native/core/src/parquet/parquet_exec.rs"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b65fd1f3011bd967542974a98994185b19fe889284dbd354717dddb82f93324"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/operators/iceberg_write.rs: native/core/src/execution/operators/iceberg_write.rs changed 17 times in last 90 days and 11 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 9 (its worst body is datafusion_comet::execution::operators::iceberg_write::drop_unwritten at line 2070), 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: \u201Cfix: make fair_unified\u0027s per-consumer limit bind when tasks run concurrently (#7096)\u201D; \u201Cfix: drop values under NULL parents before the native Iceberg writer counts NaNs (#6658)\u201D; \u201Cfix: compact already-sliced batches before the native Iceberg writer counts NaNs (#6238)\u201D; \u201Cfix Iceberg cleanup handoff (#6582)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/operators/iceberg_write.rs\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":"native/core/src/execution/operators/iceberg_write.rs"},"region":{"startLine":2070}}}],"partialFingerprints":{"codehealthFindingId/v1":"f94e9e27bd31ea7ab2ff4d9f7ed320b77bfd7b414d508497d1fe06da38424be4"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/serde/arrays.scala: spark/src/main/scala/org/apache/comet/serde/arrays.scala changed 19 times in last 90 days and 10 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 CometArrayJoin.convert at line 581), 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: \u201Cfix: match SPARK-58821 and SPARK-60118 in sequence and string to decimal cast (#7171)\u201D; \u201Cfix: evaluate the array_append item on rows whose array is NULL (#7025)\u201D; \u201Cfix: preserve Spark nested null ordering in native sort (#6968)\u201D; \u201Cfix: treat -0.0 and 0.0 as one value in arrays_overlap on Spark 4.0.5, 4.1.4 and 4.2.1 (#6989)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/arrays.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":"spark/src/main/scala/org/apache/comet/serde/arrays.scala"},"region":{"startLine":581}}}],"partialFingerprints":{"codehealthFindingId/v1":"3bc9aee868778ca25d723a0f635043674b9f6a34b20e00be61b93057740e74fd"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/array_funcs/mod.rs: native/spark-expr/src/array_funcs/mod.rs changed 14 times in last 90 days and 8 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 2 (its worst body is datafusion_comet_spark_expr::array_funcs::set_bits_before at line 61), 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: \u201Cfix: match SPARK-58821 and SPARK-60118 in sequence and string to decimal cast (#7171)\u201D; \u201Cfix: preserve Spark nested null ordering in native sort (#6968)\u201D; \u201Cfix: normalize float operands in the native comparison builder (#6447)\u201D; \u201Cfix: match Spark\u0027s float ordering in min, max, greatest and least (#6457)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/array_funcs/mod.rs\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":"native/spark-expr/src/array_funcs/mod.rs"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"40e7b7a1717b98dc31c46867429a1992dc89f90a2b0f08f5f3b27e33383deb1c"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/util/Utils.scala: spark/src/main/scala/org/apache/spark/sql/comet/util/Utils.scala changed 12 times in last 90 days and 7 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 14 (its worst body is Utils.coalesceBroadcastBatches at line 426), 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: \u201Cfix: write a sliced batch to the in-memory cache without the rows before it (#7225)\u201D; \u201Cfix: preserve make_date argument and parent evaluation (#7261)\u201D; \u201Cfix: split a coalesced broadcast before a string or binary vector passes 1 GiB (#7193)\u201D; \u201Cfix: serialize large-offset string and binary vectors with 32-bit offsets (#6371)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/util/Utils.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":"spark/src/main/scala/org/apache/spark/sql/comet/util/Utils.scala"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"b715699c8f4fc7c23fbd67fc96cbf1a3635fc8011d9c4d2ebd52419f1ca449f0"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/conditional_funcs/case_when.rs: native/spark-expr/src/conditional_funcs/case_when.rs changed 11 times in last 90 days and 7 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 CaseWhenExpr::evaluate_eagerly at line 284), 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: \u201Cfix: evaluate the right operand of AND, OR and IN only for rows the left side has not decided (#7326)\u201D; \u201Cfix: evaluate the array_append item on rows whose array is NULL (#7025)\u201D; \u201Cfix: compare greatest and least struct arguments by position (#6760)\u201D; \u201Cfix: return an empty array from CASE WHEN for an empty batch (#6763)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/conditional_funcs/case_when.rs\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":"native/spark-expr/src/conditional_funcs/case_when.rs"},"region":{"startLine":284}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe3b8f5c686b1778c8f3614dab628defed16af15e3889f963c14d74c64365992"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/jni-bridge/src/errors.rs: native/jni-bridge/src/errors.rs changed 10 times in last 90 days and 7 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 13 (its worst body is CometError::to_exception at line 341), 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: \u201Cfix: point the external sort OOM error at Comet\u0027s memory settings (#7104)\u201D; \u201Cfix: point the spill limit error at spark.comet.maxTempDirectorySize (#7098)\u201D; \u201Cfix: log native panic backtraces instead of attaching them to the exception (#7042)\u201D; \u201Cfix: convert native ReadAncientDatetime errors to SparkUpgradeException (#6559)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/jni-bridge/src/errors.rs\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":"native/jni-bridge/src/errors.rs"},"region":{"startLine":341}}}],"partialFingerprints":{"codehealthFindingId/v1":"e7e57ea2048281223e378646736802cb767b673f83fb0dfb1ca0e3bc7cbea070"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/objectstore/NativeConfig.scala: spark/src/main/scala/org/apache/comet/objectstore/NativeConfig.scala changed 8 times in last 90 days and 7 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 10 (its worst body is NativeConfig.objectStoreOptionsAndAliasOptions at line 358), 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: \u201Cfix: keep URL passwords and SAS queries out of Azure and object store errors, keys and logs (#7127)\u201D; \u201Cfix: fall back to Spark when the driver cannot use the ABFS authentication (#7221)\u201D; \u201Cchore: fix stddev accumulator size and resolve session libhdfs schemes once per scan rule (#7120)\u201D; \u201Cfix: read fs.comet.libhdfs.schemes for the scan rule from the Hadoop conf (#6838)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/objectstore/NativeConfig.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":"spark/src/main/scala/org/apache/comet/objectstore/NativeConfig.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d3c5a95b04d2e4f7ae4e12edff483499f51da73150ccbaeea5bf573d2cb65f9"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.scala changed 9 times in last 90 days and 6 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 5 (its worst body is CometIcebergNativeScanExec.stringArgs at line 368), 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: \u201Cfix: report SinglePartition from a native Iceberg scan that replaces one (#7424)\u201D; \u201Cfix: do not resolve DPP subqueries when AQE reads a native scan\u0027s partitioning (#6268)\u201D; \u201Cfix: restore Spark write execs when reverting transition-heavy stages (#5957)\u201D; \u201Cfix: key each scan\u0027s planning data by its plan node in a native block (#6297)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.scala"},"region":{"startLine":368}}}],"partialFingerprints":{"codehealthFindingId/v1":"728064da446145f18b7ef943f0176b2f39977b319aabc1ea9ec0e78b4b884abd"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/memory_pools/mod.rs: native/core/src/execution/memory_pools/mod.rs changed 8 times in last 90 days and 6 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 3 (its worst body is datafusion_comet::execution::memory_pools::create_pool at line 75), 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: \u201Cfix: make fair_unified\u0027s per-consumer limit bind when tasks run concurrently (#7096)\u201D; \u201Cfix: let a spilled final aggregate read its spill files back past its memory share (#6544)\u201D; \u201Cfix: count pool overcommit as untracked memory in the native memory usage log (#6271)\u201D; \u201Cfix: return a native plan\u0027s memory before its Spark task ends (#6261)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/memory_pools/mod.rs\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":"native/core/src/execution/memory_pools/mod.rs"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a864080ac3413a68f8b7b99d9dcedb3fa338d5762a12dadf96288435d78a5ed"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala changed 8 times in last 90 days and 6 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 7 (its worst body is CometNativeScanExec.verboseStringWithOperatorId at line 93), 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: \u201Cfix: keep unconverted DPP filters in a scan\u0027s canonical form (#6270)\u201D; \u201Cfix: do not resolve DPP subqueries when AQE reads a native scan\u0027s partitioning (#6268)\u201D; \u201Cfix: restore Spark write execs when reverting transition-heavy stages (#5957)\u201D; \u201Cfix: key each scan\u0027s planning data by its plan node in a native block (#6297)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0b1913f17296f8c7af165b55c552d9179e5be5c0f2c505b6373ec4400732133"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/java/org/apache/spark/CometTaskMemoryManager.java: spark/src/main/java/org/apache/spark/CometTaskMemoryManager.java changed 7 times in last 90 days and 6 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 4 (its worst body is CometTaskMemoryManager.acquireMemory at line 75), 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: \u201Cfix: share the missing task entry retry and stop retrying it after the task has ended (#6813)\u201D; \u201Cfix: retry a native acquire that Spark failed after dropping the task\u0027s entry (#6310)\u201D; \u201Cfix: warn about unreleased native memory only after a task\u0027s last native plan closes (#6374)\u201D; \u201Cfix: log partial memory grants at DEBUG and drop the memory usage dump (#6269)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/java/org/apache/spark/CometTaskMemoryManager.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":"spark/src/main/java/org/apache/spark/CometTaskMemoryManager.java"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"51499aa78301b1104890a91fa3a51f683588872217506589d82bbfba73e3d7f2"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometInMemoryTableScanExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometInMemoryTableScanExec.scala changed 7 times in last 90 days and 6 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 CometInMemoryTableScanExec.doExecuteColumnar at line 138), 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: \u201Cfix: draw the cached plan below CometInMemoryTableScan in the SQL tab and event log (#6577)\u201D; \u201Cfix: draw the cached plan below CometInMemoryTableScan in EXPLAIN (#6574)\u201D; \u201Cfix: keep Spark\u0027s cache scan for a relation whose cached plan records observed metrics (#6421)\u201D; \u201Cfix: describe CometInMemoryTableScan by the scan it replaces in EXPLAIN (#6453)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometInMemoryTableScanExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometInMemoryTableScanExec.scala"},"region":{"startLine":138}}}],"partialFingerprints":{"codehealthFindingId/v1":"1446fdfe32836163c6e4ce925ed98b6dce4f5404ccd2d2023e1db3babb4e2962"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.scala changed 9 times in last 90 days and 5 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 4 (its worst body is CometIcebergWriteExec.doExecuteColumnar at line 232), 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: \u201Cfix: restore Spark write execs when reverting transition-heavy stages (#5957)\u201D; \u201Cfix Iceberg cleanup handoff (#6582)\u201D; \u201Cchore: Fix Scala code warnings (#5876)\u201D; \u201Cfix: Delete completed tasks\u0027 data files when an Iceberg write job fails (#5663)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergWriteExec.scala"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"771816064b045484d9d27c30de01f80394c82646f5f59b324d711e95127d2ae7"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/conversion_funcs/numeric.rs: native/spark-expr/src/conversion_funcs/numeric.rs changed 9 times in last 90 days and 5 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 13 (its worst body is datafusion_comet_spark_expr::conversion_funcs::numeric::spark_cast_nonintegral_numeric_to_integral at line 1179), 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: \u201Cfix: build with Rust 1.99, which deprecates the legacy f64 constants and fetch_update (#6507)\u201D; \u201Cfix: native ansi-errors raised as spark error (#5169)\u201D; \u201Cfix: render float and double Iceberg partition values like iceberg-java (#5840)\u201D; \u201Cfix: correctly rounded decimal to double/float cast matching BigDecimal.doubleValue/floatValue (#5684)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/conversion_funcs/numeric.rs\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":"native/spark-expr/src/conversion_funcs/numeric.rs"},"region":{"startLine":1179}}}],"partialFingerprints":{"codehealthFindingId/v1":"842446fbef16ecf7a1d087a806bb2ed41ceae25821e1d881bb03e95bc1aff784"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/java/org/apache/comet/NativeBase.java: spark/src/main/java/org/apache/comet/NativeBase.java changed 8 times in last 90 days and 5 of those changes were fix/bug commits, so repair is the majority of this file\u0027s churn. Its max cyclomatic complexity is 7 (its worst body is NativeBase.checkArch at line 282), 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: \u201Cfix: fall back to Spark when the driver cannot use the ABFS authentication (#7221)\u201D; \u201Cfix: extract bundled native libraries into private directories (#6987)\u201D; \u201Cfix: load the Iceberg storage scheme lists from the native factory (#6065)\u201D; \u201Cfix: load the bundled native library only once per class loader (#6493)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/java/org/apache/comet/NativeBase.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":"spark/src/main/java/org/apache/comet/NativeBase.java"},"region":{"startLine":282}}}],"partialFingerprints":{"codehealthFindingId/v1":"164d608eb4220dd8de725345811d77e6e783ee4dacdb6b685049685f7b793ca9"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/memory_pools/fair_pool.rs: native/core/src/execution/memory_pools/fair_pool.rs changed 5 times in last 90 days and 5 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 CometFairMemoryPool::try_grow at line 238), 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: \u201Cfix: spill a native PartialMerge whose input is sorted on some of its keys (#7222)\u201D; \u201Cfix: make fair_unified\u0027s per-consumer limit bind when tasks run concurrently (#7096)\u201D; \u201Cfix: count pool overcommit as untracked memory in the native memory usage log (#6271)\u201D; \u201Cfix: check each fair_unified reservation against its own share (#6205)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/memory_pools/fair_pool.rs\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":"native/core/src/execution/memory_pools/fair_pool.rs"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcd5a4a85115ff2f18bc5048731239eddb70d2ae92396ccfa0d7fc6f9010ddb8"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/ExtendedExplainInfo.scala: spark/src/main/scala/org/apache/comet/ExtendedExplainInfo.scala changed 7 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 ExtendedExplainInfo.generateTreeString at line 145), 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: \u201Cfix: scope fallback reasons to the current conversion (#7095)\u201D; \u201Cfix: draw the cached plan below CometInMemoryTableScan in EXPLAIN (#6574)\u201D; \u201Cfix: count each reused exchange once in extended explain (#6379)\u201D; \u201Cfix: ignore structural tags when lifting expression coverage (#5471)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/ExtendedExplainInfo.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":"spark/src/main/scala/org/apache/comet/ExtendedExplainInfo.scala"},"region":{"startLine":145}}}],"partialFingerprints":{"codehealthFindingId/v1":"e68c7e7ca8c28e29913dd14101451690173de1d04c55b16f9a6e63f480d98a52"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/hash_funcs/xxhash64.rs: native/spark-expr/src/hash_funcs/xxhash64.rs changed 7 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 9 (its worst body is datafusion_comet_spark_expr::hash_funcs::xxhash64::type_compatible_with_spark_xxhash64 at line 131), 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: \u201Cfix: hash NullType and ANSI interval values natively (#7084)\u201D; \u201Cfix: hash NaN the way Spark does in hash, xxhash64 and native shuffle (#6413)\u201D; \u201Cfix: apply the parent struct\u0027s null mask before hashing its fields (#5754)\u201D; \u201Cfix: keep the dictionary hash fast path off nested and reseeded buffers (#5757)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/hash_funcs/xxhash64.rs\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":"native/spark-expr/src/hash_funcs/xxhash64.rs"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"7041b0d3fa5abe40747502fafbacd5a29e37c1f3574b9f23105c0fe72eb638c3"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.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 CometNativeWriteExec.prepareOutputPathForMode at line 270), 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: \u201Cfix: run InsertIntoHadoopFsRelationCommand\u0027s post-write steps in the Spark 3.x native writer (#6821)\u201D; \u201Cfix: honor Spark\u2019s commit protocol in Spark 3.x native writes (#4746)\u201D; \u201Cfix: restore Spark write execs when reverting transition-heavy stages (#5957)\u201D; \u201Cchore: Fix Scala code warnings (#5876)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala"},"region":{"startLine":270}}}],"partialFingerprints":{"codehealthFindingId/v1":"daa702effb06ab13c28887a21589e0d9f4b03beb5944161b8f7cfb7e2c093c5b"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/hash_funcs/murmur3.rs: native/spark-expr/src/hash_funcs/murmur3.rs 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 5 (its worst body is datafusion_comet_spark_expr::hash_funcs::murmur3::spark_murmur3_hash at line 28), 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: \u201Cfix: hash NullType and ANSI interval values natively (#7084)\u201D; \u201Cfix: hash NaN the way Spark does in hash, xxhash64 and native shuffle (#6413)\u201D; \u201Cfix: apply the parent struct\u0027s null mask before hashing its fields (#5754)\u201D; \u201Cfix: keep the dictionary hash fast path off nested and reseeded buffers (#5757)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/hash_funcs/murmur3.rs\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":"native/spark-expr/src/hash_funcs/murmur3.rs"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"48184b0cf5c66180350a7003a97fec02377eddd214a1475030e962399ff4f609"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/IcebergCommitExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/IcebergCommitExec.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 4 (its worst body is IcebergCommitExec.collectAndCommit at line 75), 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: \u201Cfix(iceberg): preserve Spark 4.2 write transactions (#6587)\u201D; \u201Cchore: Fix Scala code warnings (#5876)\u201D; \u201Cfix: wrap Iceberg split-write failures the way Spark does when abort fails (#6153)\u201D; \u201Cfix: Delete completed tasks\u0027 data files when an Iceberg write job fails (#5663)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/IcebergCommitExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/IcebergCommitExec.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc2e4bc13d8ed7355cf99e6f80409e313dfe1bc0ff2fdcf11901da65c501aa67"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/serde/CometSortOrder.scala: spark/src/main/scala/org/apache/comet/serde/CometSortOrder.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 CometSortOrder.convert at line 79), 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: \u201Cfix: preserve Spark nested null ordering in native sort (#6968)\u201D; \u201Cfix: fall back for nested sort keys whose null elements Spark orders differently (#6683)\u201D; \u201Cfix: fall back for RANGE frames over nested keys that can hold a null (#6684)\u201D; \u201Cfix: match Spark\u0027s float ordering for sort and window keys nested in arrays and structs (#6475)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/CometSortOrder.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":"spark/src/main/scala/org/apache/comet/serde/CometSortOrder.scala"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"dd6ce06e6260e2116cac9587d8335e623363a6ad7b39ace2956f1449144d9acf"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/float_semantics/mod.rs: native/spark-expr/src/float_semantics/mod.rs 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 6 (its worst body is datafusion_comet_spark_expr::float_semantics::compare_floats at line 107), 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: \u201Cfix: normalize float operands in the native comparison builder (#6447)\u201D; \u201Cfix: match Spark\u0027s float ordering in min, max, greatest and least (#6457)\u201D; \u201Cfix: hash NaN the way Spark does in hash, xxhash64 and native shuffle (#6413)\u201D; \u201Cfix: match Spark\u0027s float semantics in array_remove and sort_array (#6518)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/float_semantics/mod.rs\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":"native/spark-expr/src/float_semantics/mod.rs"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"a602562a022d44bf3273eddcddedd66966484734ec721963a1638d0bb96720be"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.scala changed 5 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 7 (its worst body is CometWindowGroupLimitExec.convert at line 64), 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: \u201Cfix: declare required child distribution on aggregate, window and join operators (#7231)\u201D; \u201Cfix: preserve Spark nested null ordering in native sort (#6968)\u201D; \u201Cfix: match Spark\u0027s float ordering for sort and window keys nested in arrays and structs (#6475)\u201D; \u201Cfix: fall back to Spark for RANK and DENSE_RANK limits over nested floating-point keys (#6468)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometWindowGroupLimitExec.scala"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"3525ab8fa5ea4bd0632d936c92a02f09a33eb24c89946b63326f84f48bbc80ce"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/DataTypeSupport.scala: spark/src/main/scala/org/apache/comet/DataTypeSupport.scala changed 5 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 DataTypeSupport.isTypeSupported at line 50), 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: \u201Cfix(cast): fall back for duplicate struct field names (#6671)\u201D; \u201Cfix: fall back when struct field names collide case-insensitively (#6326)\u201D; \u201Cfix: fall back when a schema repeats a Parquet field id (#6004)\u201D; \u201Cfix: decline structs with duplicate field names before they reach Java Arrow (#5866)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/DataTypeSupport.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":"spark/src/main/scala/org/apache/comet/DataTypeSupport.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"42251ff9af66f0ffdf47d366980733af56ac72c2ab6f3a5cbb1a3172df2782eb"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/datetime_funcs/timestamp_trunc.rs: native/spark-expr/src/datetime_funcs/timestamp_trunc.rs 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 8 (its worst body is TimestampTruncExpr::evaluate at line 105), 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: \u201Cfix: handle truncation operands in scalar evaluation and rewrites (#6831)\u201D; \u201Cfix: truncate per-row date_trunc formats with the literal-format kernel (#6354)\u201D; \u201Cfix: match Spark 4.2 date_trunc overflow for SECOND and MILLISECOND (#6740)\u201D; \u201Cfix: keep the input\u0027s timezone label on native date_trunc results (#6345)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/datetime_funcs/timestamp_trunc.rs\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":"native/spark-expr/src/datetime_funcs/timestamp_trunc.rs"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf964ff01e4b22c8511d558219dfd81715bf7c101fccdf8fcb538dc473c1bed0"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/operators/iceberg_partition_path.rs: native/core/src/execution/operators/iceberg_partition_path.rs changed 5 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 10 (its worst body is datafusion_comet::execution::operators::iceberg_partition_path::human_string at line 164), 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: \u201Cfix: match iceberg-java for Iceberg partitions past year 262142 in the native writer (#6239)\u201D; \u201Cfix: render float and double Iceberg partition values like iceberg-java (#5840)\u201D; \u201Cfix: match iceberg-java\u0027s exception for unclustered input to a clustered Iceberg write (#5779)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/operators/iceberg_partition_path.rs\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":"native/core/src/execution/operators/iceberg_partition_path.rs"},"region":{"startLine":164}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0dbf538af6dbe81f8351d300d455176663d85b0443421f0e55431be14098687"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala changed 5 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 CometArrowStream.readerBatchIter at line 347), 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: \u201Cfix: rethrow the exception a JVM input throws instead of a CometNativeException (#6243)\u201D; \u201Cfix: release input Arrow streams that native never takes (#6372)\u201D; \u201Cfix: decode dictionary input for PyArrow UDFs (#5560)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala"},"region":{"startLine":347}}}],"partialFingerprints":{"codehealthFindingId/v1":"f82dd940c326d5aeb701f11a57d083df38495f19459c61b7c02fe3b6e25770fd"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/array_funcs/nested_comparison.rs: native/spark-expr/src/array_funcs/nested_comparison.rs changed 5 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 14 (its worst body is NestedPredicate::evaluate at line 250), 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: \u201Cfix: evaluate the right operand of AND, OR and IN only for rows the left side has not decided (#7326)\u201D; \u201Cfix: return an empty array from CASE WHEN for an empty batch (#6763)\u201D; \u201Cfix: normalize float operands in the native comparison builder (#6447)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/array_funcs/nested_comparison.rs\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":"native/spark-expr/src/array_funcs/nested_comparison.rs"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f6c6c66ae210179f0dda11052e1a2bb3d74333926bab8e57515b04a5899935c"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/CometTakeOrderedAndProjectExec.scala: spark/src/main/scala/org/apache/spark/sql/comet/CometTakeOrderedAndProjectExec.scala changed 5 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 CometTakeOrderedAndProjectExec.doExecuteColumnar at line 153), 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: \u201Cfix: apply the session\u0027s Comet configs in map stages of jobs outside a SQL execution (#7302)\u201D; \u201Cfix: skip an array or map function\u0027s later arguments where the array or map is NULL (#6716)\u201D; \u201Cchore: Fix Scala code warnings (#5876)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/CometTakeOrderedAndProjectExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometTakeOrderedAndProjectExec.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"4260cfee377bcfacbe09e34746c0905dd085eadd7bc279f2b09180bdeef405cb"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometDiskBlockWriter.java: spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometDiskBlockWriter.java changed 5 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 CometDiskBlockWriter.insertRow at line 228), 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: \u201Cfix: cap spark.comet.shuffle.jvm.batchSize at spark.comet.batchSize where it is read (#6366)\u201D; \u201Cfix: count every hash-based JVM shuffle batch as shuffle bytes written (#6369)\u201D; \u201Cfix: make CometDiskBlockWriter spill registry per-task instead of executor-global (#5493)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometDiskBlockWriter.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":"spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometDiskBlockWriter.java"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"dce7754476a3f9373c09f1b7ef2d341822e406f69763b2521fa077fcb55c5bbf"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/jvm_udf/mod.rs: native/spark-expr/src/jvm_udf/mod.rs changed 5 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 JvmScalarUdfExpr::evaluate at line 153), 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: \u201Cfix: initialize dispatched kernels with the partition the native plan computes (#6700)\u201D; \u201Cfix: zero sliced boolean offsets at every level before exporting to the JVM (#6339)\u201D; \u201Cfix: decode invalid UTF-8 at the JVM to native FFI import boundary (#5310)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/jvm_udf/mod.rs\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":"native/spark-expr/src/jvm_udf/mod.rs"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"910b09323a7821de7fa62667227e145f4c5c87f97eb801cb7fd450a6566fc4f8"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/parquet/objectstore/s3_blob_fs_support.rs: native/core/src/parquet/objectstore/s3_blob_fs_support.rs 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 5 (its worst body is datafusion_comet::parquet::objectstore::s3_blob_fs_support::normalize_object_store_url at line 76), 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: \u201Cfix: keep URL passwords and SAS queries out of Azure and object store errors, keys and logs (#7127)\u201D; \u201Cfix: load the Iceberg storage scheme lists from the native factory (#6065)\u201D; \u201Cfix: decide libhdfs routing from the scheme as written (#5825)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/objectstore/s3_blob_fs_support.rs\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":"native/core/src/parquet/objectstore/s3_blob_fs_support.rs"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"3be6380a7d24d6fb88e7ac7059430263d11a38c7be04f5d193b053446199c542"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/agg_funcs/sum_int.rs: native/spark-expr/src/agg_funcs/sum_int.rs 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 13 (its worst body is SumIntGroupsAccumulatorTry::update_batch at line 893), 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: \u201Cfix: preserve native sliding integer sum overflow semantics (#6069)\u201D; \u201Cfix: count grouped integer SUM state in the aggregate\u0027s memory reservation (#6370)\u201D; \u201Cfix: include try_add suggestion in ANSI SUM overflow error (#6732)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/agg_funcs/sum_int.rs\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":"native/spark-expr/src/agg_funcs/sum_int.rs"},"region":{"startLine":893}}}],"partialFingerprints":{"codehealthFindingId/v1":"02d661bb7e2078fccb7df491cf2b3a80aa4e66f9c424fdfe38257ef2771279a2"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/serde/maps.scala: spark/src/main/scala/org/apache/comet/serde/maps.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 5 (its worst body is CometMapFromArrays.convert at line 192), 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: \u201Cfix: stop building maps natively when the key type holds a FLOAT or DOUBLE (#6992)\u201D; \u201Cfix: skip an array or map function\u0027s later arguments where the array or map is NULL (#6716)\u201D; \u201Cfix: validate map constructor row lengths and null short-circuiting (#5846)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/serde/maps.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":"spark/src/main/scala/org/apache/comet/serde/maps.scala"},"region":{"startLine":192}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd5e81c618aeec62faa663826bc1aec75a68063a6dd2cb4287ec67e4135c3821"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.scala: spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.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 5 (its worst body is CometScalaUDFCodegen.lookupOrCompile at line 175), 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: \u201Cfix: give each nondeterministic dispatched expression its own kernel (#6712)\u201D; \u201Cfix: initialize dispatched kernels with the partition the native plan computes (#6700)\u201D; \u201Cchore: Fix Scala code warnings (#5876)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.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":"spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.scala"},"region":{"startLine":175}}}],"partialFingerprints":{"codehealthFindingId/v1":"492797e2a337eac3565d2c049bbf131a361e7694243319c3250bf0336bd3594a"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/memory_pools/unified_pool.rs: native/core/src/execution/memory_pools/unified_pool.rs 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 4 (its worst body is CometUnifiedMemoryPool::try_grow 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: \u201Cfix: build with Rust 1.99, which deprecates the legacy f64 constants and fetch_update (#6507)\u201D; \u201Cfix: count pool overcommit as untracked memory in the native memory usage log (#6271)\u201D; \u201Cfix: let Comet memory pools overcommit on grow instead of panicking (#6128)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/memory_pools/unified_pool.rs\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":"native/core/src/execution/memory_pools/unified_pool.rs"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"62491b0d4e45db8826ef9896233d67162e9b748503ef2f21e13ae46df7b68213"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleInputRDD.scala: spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleInputRDD.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 4 (its worst body is CometNativeShuffleInputRDD.getPreferredLocations at line 128), 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: \u201Cfix: recover native Celeborn shuffle from oversized rows (#5668)\u201D; \u201Cfix: report native child spill metrics in shuffle tasks (#5445)\u201D; \u201Cfix: Native shuffle fails with a 2GB task serialization OOM on jobs with many partitions (#5392)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleInputRDD.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometNativeShuffleInputRDD.scala"},"region":{"startLine":128}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b8c9f821ac9d52bd5b0b887c640ab5b0a37fcc4f73fb0937adc4f51ef686eee"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/parquet/objectstore/azure.rs: native/core/src/parquet/objectstore/azure.rs 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 11 (its worst body is datafusion_comet::parquet::objectstore::azure::resolved_settings at line 214), 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: \u201Cfix: keep URL passwords and SAS queries out of Azure and object store errors, keys and logs (#7127)\u201D; \u201Cfix: fall back to Spark when the driver cannot use the ABFS authentication (#7221)\u201D; \u201Cfix: resolve Azure ABFS authentication through Hadoop and keep ambient credentials out (#6059)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/parquet/objectstore/azure.rs\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":"native/core/src/parquet/objectstore/azure.rs"},"region":{"startLine":214}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a42cdd7c9de8028271037f4b4ea972f444d38f1c1fb5799c090abb5ed20c2ce"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/memory_pools/spill_replay.rs: native/core/src/execution/memory_pools/spill_replay.rs 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 3 (its worst body is SpillReplayPool::track at line 91), 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: \u201Cfix: spill a native PartialMerge whose input is sorted on some of its keys (#7222)\u201D; \u201Cfix: make fair_unified\u0027s per-consumer limit bind when tasks run concurrently (#7096)\u201D; \u201Cfix: keep one row per key in a native PartialMerge that runs short of memory (#6867)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/memory_pools/spill_replay.rs\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":"native/core/src/execution/memory_pools/spill_replay.rs"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"8dd8a610b480b9555e1b498b232c415b0438493b1153271344a8c0ed1b64daf5"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/core/src/execution/memory_pools/task_shared.rs: native/core/src/execution/memory_pools/task_shared.rs 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 3 (its worst body is TaskSharedMemoryPool::drop at line 123), 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: \u201Cfix: make fair_unified\u0027s per-consumer limit bind when tasks run concurrently (#7096)\u201D; \u201Cfix: count pool overcommit as untracked memory in the native memory usage log (#6271)\u201D; \u201Cfix: make task-shared memory pool as ref-counted RAII guard (#5494)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/core/src/execution/memory_pools/task_shared.rs\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":"native/core/src/execution/memory_pools/task_shared.rs"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"beae8abe0e0560902e27d4d0b918f71a787f850d0ddb98c6f177356edb6ec071"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: native/spark-expr/src/agg_funcs/regr.rs: native/spark-expr/src/agg_funcs/regr.rs 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 RegrR2Accumulator::evaluate at line 378), 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: \u201Cfix: raise DIVIDE_BY_ZERO from native corr on a zero denominator in ANSI mode (#6830)\u201D; \u201Cfix: match Spark statistical aggregate updates and merges (#6076)\u201D; \u201Cfix: gate the regr_r2 degenerate-case swap on the Spark patch release (#6042)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- native/spark-expr/src/agg_funcs/regr.rs\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":"native/spark-expr/src/agg_funcs/regr.rs"},"region":{"startLine":378}}}],"partialFingerprints":{"codehealthFindingId/v1":"257f7bc2fe6b89c55c948ff9205bf9a3c706c0af910afc8e0216ff2bf0250914"}},{"ruleId":"D15","level":"warning","message":{"text":"Repeated repair: spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala: spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.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 1 (its worst body is CometArrowPythonRunner.workerConf at line 55), 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: \u201Cfix: check accelerated mapInArrow output against the declared schema (#6365)\u201D; \u201Cfix: decode dictionary input for PyArrow UDFs (#5560)\u201D; \u201Cfix: align Spark 4.2 Python worker configuration (#5561)\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 2026-08-16..2026-11-14, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-16 04:49:54 \u002B00:00\u0027 --until=\u00272026-11-14 04:49:54 \u002B00:00\u0027 --full-history --no-merges -- spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.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":"spark/src/main/spark-4.2/org/apache/spark/sql/execution/python/CometArrowPythonRunner.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"708289dbed238c3d301a84d3b67c08934eb5382f22d38fef309227b96bf0979a"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #1: If anonymized user #1 becomes unavailable, 56 significant file(s) lose their only recent owner: native/core/src/execution/operators/iceberg_write.rs, dev/ci/check-ci-config.py, native/spark-expr/src/agg_funcs/collect.rs, native/core/src/execution/planner/shuffle.rs, spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CachedBatchIpc.scala, native/spark-expr/src/conditional_funcs/null_short_circuit.rs, native/spark-expr/src/agg_funcs/mode.rs, native/common/src/schema.rs (\u002B48 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"c960797f28224f49dc4594f59b92bd3a578d145c9b0966308c26cfadd5514e5d"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #2: If anonymized user #2 becomes unavailable, 7 significant file(s) lose their only recent owner: spark/src/main/java/org/apache/comet/shuffle/CelebornTransportCallbackTracker.java, spark/src/main/java/org/apache/comet/shuffle/CelebornShufflePartitionPusher.java, native/shuffle/src/remote_schema.rs, native/jni-bridge/src/shuffle_partition_pusher.rs, native/core/src/execution/operators/dynamic_filter/parquet_reader/schema_adapter/tests.rs, native/core/src/execution/operators/dynamic_filter/parquet_reader/schema_adapter.rs, spark/src/main/java/org/apache/comet/shuffle/ExecutorShufflePushAdmission.java. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"8ce2e75533d1bb6a1ea05593a972ca17ea4132fc440d1cae7d3629f16d224f4c"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #3: If anonymized user #3 becomes unavailable, 6 significant file(s) lose their only recent owner: contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala, native/core/src/execution/planner/delta_spark_scan.rs, contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/CometDeltaNativeScan.scala, contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/CometDeltaNativeScanExec.scala, contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala, spark/src/main/scala/org/apache/comet/iceberg/IcebergStorageSchemes.scala. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"84fac6e6318bec0654a80b71efbfda4d866185bf7566e12b25e5b9ea15a797ad"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #4: If anonymized user #4 becomes unavailable, 4 significant file(s) lose their only recent owner: dev/ci/check-iceberg-shards.py, native/core/src/execution/operators/dynamic_filter/early.rs, dev/ci/test-iceberg-shards.py, dev/ci/iceberg-test-shards.gradle. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"79f06460de08df8ab02a7cbf817efb746759d109f4d62c1c6aefa3d57842d6cc"}},{"ruleId":"D16","level":"note","message":{"text":"Further sole-owners (lower concentration): 8 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 (83 single-owned of 581 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; 581 of the 813 production source files in this repository met that bar). They are anonymized user #5 (2 file(s)), anonymized user #6 (2 file(s)), anonymized user #7 (1 file(s)), anonymized user #8 (1 file(s)), anonymized user #9 (1 file(s)), anonymized user #10 (1 file(s)) (\u002B2 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: dev/ci/local-ci-config.py, spark/src/main/scala/org/apache/comet/CometExecutorMemoryUsage.scala, spark/src/main/spark-4.2/org/apache/spark/sql/comet/IcebergTransactionalCommitExec.scala, dev/ci/check-versioned-source-parity.py, native/spark-expr/src/array_funcs/flatten.rs, spark/src/main/java/org/apache/comet/MissingTaskEntryRetry.java, spark/src/main/java/org/apache/comet/cloud/s3/CometS3LocationScopedCredentialProvider.java, native/spark-expr/src/math_funcs/signum.rs (\u002B2 more)."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6eac528f2429e724e1a97ed868f79eefbcf1888dab4af9a9e673429369bb5b2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: https://github.com/apache/datafusion-comet/issues/392"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/spark/sql/CometTPCDSQuerySuite.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"d600ac7333a23eeabe38378dc3ffb65b46740d41365e2997e4c8c7148993a8e8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: think a better way to install on each worker node \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/spark/sql/GenTPCHData.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb18910d99e872c01bbd8713ca5bb0fe898cd2cc39546b4e326dcb6836486f62"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support dictionary encoding in vectorized 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":"spark/src/test/scala/org/apache/spark/sql/benchmark/CometExecBenchmark.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"a30774f0052ad6c2cbc138cc91f317875106004ff15960580b3e1bc772218716"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support dictionary encoding in vectorized 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":"spark/src/test/scala/org/apache/spark/sql/benchmark/CometShuffleBenchmark.scala"},"region":{"startLine":107}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b19ffa75a3573af5df5481d275daf153e5c1838841175da8ff8469a8f32526a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: https://github.com/apache/datafusion-comet/issues/2539"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":905}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e36aec6574c0539018ff9c7ae629a443c31fb1dea2d559b710b656c778b2865"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: test ANSI 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":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":1070}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ab5458c217fb3c7fc9accae25dca52f97922c88fafbb60ba3ded3a43339ce05"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: why with not in, the plan is only \u0060LocalTableScan\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":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":2411}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d019778e83f9bce01564a8c0b52a2ad251b39ce8810b6b1d4e0b0ba9f4d67bd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: DataFusion supports only -8334601211038 \u003C= sec \u003C= 8210266876799 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":2651}}}],"partialFingerprints":{"codehealthFindingId/v1":"dba27e8c1387d4ce1c711fe2edf0ebe3f091e50432e39807bf37b8b979785b92"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: DataFusion supports only -8334601211038 \u003C= sec \u003C= 8210266876799 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/unixtime.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"df11094f9f71a888c803a284c813c7286b6293e5edcc31b0f562a114a17b5086"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: DataFusion toChar does not support Spark datetime pattern 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":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":2657}}}],"partialFingerprints":{"codehealthFindingId/v1":"28d32b41d0b34e47a49e31112c29ce2365cb7cbc0ca17e22ba742f2047591572"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: DataFusion toChar does not support Spark datetime pattern 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":"spark/src/main/scala/org/apache/comet/serde/unixtime.scala"},"region":{"startLine":72}}}],"partialFingerprints":{"codehealthFindingId/v1":"addefe4d6d365de4a6ec26bdb93999cd9588ae9139dca20d6d70debd86c4acf1"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME: Change checkSparkAnswer to checkSparkAnswerAndOperator after resolving \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala"},"region":{"startLine":4094}}}],"partialFingerprints":{"codehealthFindingId/v1":"24c335cf69d80a588964621ee2881f264745a38dad3785d6a6b9c2a54e292a62"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: try_cast is not compared for this value because the native TRY path goes through \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometNativeCastSuite.scala"},"region":{"startLine":685}}}],"partialFingerprints":{"codehealthFindingId/v1":"2b894499f95063fe93dbd0830da5c918578d94e5021d904cbcb4884e98d19736"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: try_cast is not compared for this value because the native TRY path goes through \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometNativeCastSuite.scala"},"region":{"startLine":835}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c7f87b240a56e2e6492396cdc0ec03634f5952c7f77647a4f3cbaf6884f6b0e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO add _16 when https://github.com/apache/datafusion-comet/issues/1068 is resolved"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometNativeCastSuite.scala"},"region":{"startLine":2353}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6d2174b23bf0502a6310abea2cb83e3e1110c17dc8b149c96bf83959a72f9f4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO test fails with non-UTC timezone \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometTemporalExpressionSuite.scala"},"region":{"startLine":291}}}],"partialFingerprints":{"codehealthFindingId/v1":"761cb18e173e5151692eb977ad1cfaae3574a0cd79d244b9463ce4145150ed8d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO test fails with non-UTC timezone \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/CometTemporalExpressionSuite.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"8d578c4becb590b6ca2dbddea095fb1818b1d9ae23964bf2eb27336b887a9816"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider merging this with the same method 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":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":873}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e0add5ec79d01f8879e546688c80d8586ccf94839920d7a9a8a689d104f3178"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(https://github.com/apache/datafusion-comet/issues/3432): \u0060_metadata.row_index\u0060 is"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":996}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd4f5d4e1c12a976e4d84edae468a9c49cef3efe64715dbe6da65518ee4da6ea"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This produces incorrect results in the native Parquet scan \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":1389}}}],"partialFingerprints":{"codehealthFindingId/v1":"f231b3913348e678926d0daee2e8a6581c1f99842d86f7efa9a6da6b2d82090d"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This produces incorrect results in the native Parquet scan \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":1451}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc9186d94d7c694c13884be57d6941bc17aa1ed57ba6fec36b4acd3879d3e798"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This test fails for the native Parquet scan \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":1402}}}],"partialFingerprints":{"codehealthFindingId/v1":"54423e9c74c7a73a4d76bdb8feba85517e3baef8d7190c8680ce4e45863cac7c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: pushed down filters do not used schema adapter in datafusion, will cause empty result \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/parquet/ParquetReadSuite.scala"},"region":{"startLine":3154}}}],"partialFingerprints":{"codehealthFindingId/v1":"a10585efb8a0ad2d42f2649a840af194df6c681ce42d026087c761e5e6faaf43"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: To be addressed after DF 55 migration \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometAggregateSuite.scala"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"030eede320df798c68ba0206d2b3af6662c50b4799405c60f81f5939d77d2af2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: To be addressed after DF 55 migration \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometAggregateSuite.scala"},"region":{"startLine":105}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3467353318a27a844d8ccd43e7ed6c7f93f9afca41676a7fd83de66a2661179"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // \u0022DATE\u0022: TODO: needs to address issue #1364 first"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala"},"region":{"startLine":2643}}}],"partialFingerprints":{"codehealthFindingId/v1":"91eacf442445360e81f6c458575ef28ac0853463227137bebc203c0c464ea1c6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // \u0022TIMESTAMP\u0022, TODO: needs to address issue #1364 first"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala"},"region":{"startLine":2644}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c81746cdaefc728bc87059585ee05b235bcd75ee8c9e261985312fbf06c6a39"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We should be able to sort on dictionary timestamp column \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala"},"region":{"startLine":3494}}}],"partialFingerprints":{"codehealthFindingId/v1":"301ed5b60f8e52ca850589cc504f6f7a6fc0c775fa33a366f601ab094fcf3566"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Spark 3.4 returns SortMergeJoin for this query even with SHUFFLE_HASH hint. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometJoinSuite.scala"},"region":{"startLine":1060}}}],"partialFingerprints":{"codehealthFindingId/v1":"f630e7674a1a9ba2ab0e9ed132eb54eb2b9f7b9a7c33e44aaafc68a4b144dc75"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: this test takes a long time to run, we should reduce the test 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":"spark/src/test/scala/org/apache/comet/exec/CometNativeShuffleSuite.scala"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"c151cd2d20f1ee53c1555b5c03d80f9cb1007b706ff9d0319bd0bedf2e628187"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: test nulls \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometWindowExecSuite.scala"},"region":{"startLine":663}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbd3f9db4dd626c6ac5c31c2667ed746efa0dc1867e72e9bf9c25af61415eec7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Test all the aggregates \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/scala/org/apache/comet/exec/CometWindowExecSuite.scala"},"region":{"startLine":671}}}],"partialFingerprints":{"codehealthFindingId/v1":"7adca02220cbd4ea8bf4b0b7e34db4febe46a7941ee1bf234e19004b838d6d92"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: should this be more specific? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/test/java/org/apache/iceberg/rest/RESTCatalogAdapter.java"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7819183df36ca71bde4b1e1624a53f28a8f7cc934d4fb56ed219b8677d85d74"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove after dropping Spark 3.4 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":"spark/src/main/spark-3.x/org/apache/comet/shims/ShimCometShuffleExchangeExec.scala"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"c60916151d24eaa40ea10ae429355197b149628814b737c0e465caf6bdef0c3f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove after dropping Spark 3.x 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":"spark/src/main/spark-3.x/org/apache/comet/shims/ShimCometShuffleExchangeExec.scala"},"region":{"startLine":44}}}],"partialFingerprints":{"codehealthFindingId/v1":"d54c8317720ff36198c30e3af721dc0d6c23ade6318dbe095b0bef4c802e2a68"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: remove after dropping Spark 3.x 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":"spark/src/main/spark-3.x/org/apache/comet/shims/ShimCometShuffleExchangeExec.scala"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"a17ea23448d0458d3a6a0d425d19c7285bdbf05aac79058a64aa9f7a8afa890f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: find a better approach than this hack \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometBatchScanExec.scala"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"a387a5013c4d935b955aea14c558c5560bef9f3db46acd5e9aaf2a124d569ed7"}},{"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":"spark/src/main/scala/org/apache/spark/sql/comet/CometColumnarToRowExec.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"46848c6a335c29e9640ce0b3d50036ee6b55aa19eef9b5b22fa190624227ad20"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: throw an exception, e.g. IllegalArgumentException, instead? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala"},"region":{"startLine":221}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b7ee1ca476204aadad2b1ae2c7ae04670aa855ea9f5e94cc1060b294663f342"}},{"ruleId":"D17","level":"warning","message":{"text":"FixmeComment: // FIXME: ideally we should reuse wrapped.supportsColumnar, however that fails many 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":"spark/src/main/scala/org/apache/spark/sql/comet/CometScanExec.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"777379dc1cd610d109146fa24141f7d41c217a60a1483b3110e03e78b730634a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider to use \u0060org.apache.spark.sql.types.DecimalExpression\u0060 for Spark 3.5\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":"spark/src/main/scala/org/apache/spark/sql/comet/DecimalPrecision.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1c5c7f30b33f1f543f79ef0aa993c209b0d59b56f2efbce733b054c48911c3a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(#3510): once TreeNode.makeCopy preserves @transient fields, the"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1424}}}],"partialFingerprints":{"codehealthFindingId/v1":"6307ad443f0b88c25dcb890d824c296156a70ff72ecfa8ec950157c4abfe8f08"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // the matching TODO in CometPlanAdaptiveDynamicPruningFilters. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1426}}}],"partialFingerprints":{"codehealthFindingId/v1":"bce5980669a6bf8a8e393cc414d6d1edaae38be0791c7a3e2be9c8acf3081005"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: support native Expand metrics \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1845}}}],"partialFingerprints":{"codehealthFindingId/v1":"513502464e8959ca7cfbc75a14f902d4272c6064158253753e94101f7214f736"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO add support for map 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":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":1952}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b89c9d87f2c0c55d35ed117f771e3ad1e3f77c48f884b1bb531216c2f43e1c0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add \u0060override\u0060 keyword after dropping Spark-3.x 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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":196}}}],"partialFingerprints":{"codehealthFindingId/v1":"71d14761fa78504e1a1bab140df1eec5becdc1df50722c72f047907a1644cd22"}},{"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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala"},"region":{"startLine":1191}}}],"partialFingerprints":{"codehealthFindingId/v1":"f625d4091c09df3480dc95f4029d0fb6af126e46118eb60c6357efe05516d9d3"}},{"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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffledRowRDD.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"af9ce17659beb6606700d7c1bdf3f52ef66bdba05885fa70d49e317c03a2c504"}},{"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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffledRowRDD.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fed758d703fa0c0550c43fff69db26887bbe4bcfd14ca0abff9da0d59a9d536"}},{"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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/ArrowWriters.scala"},"region":{"startLine":1550}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3f7ef3459bca26c0bfc7ecad7c89d7f1a0081328ea78b7bff9fb380985924a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(dict-encoded): kernels assume materialized inputs. Dict-encoded vectors would fail 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":"spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.scala"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6e66561b81fa206a4f677572592689d8ed81e3a0f2819a2d9741c6990ef60b4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO PromotePrecision \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"58b704331b321ecf3a0f50eede79c189df50652d6a31dcf10ebfecfef771e333"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO the ASC form (\u0060reverseOpt = Some(false)\u0060) returns the smallest tied value, which 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":"spark/src/main/scala/org/apache/comet/serde/aggregates.scala"},"region":{"startLine":1403}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b56f6417ec5bfc5ff46f9325e27cd9545c083c3c77a64c002692b00cc5cfac6"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO implement these types with tests for formatting options and timezone \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/structs.scala"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"c534691242674040fad15f37da8b45011f45defd4300d5ecb7f01c032a22f445"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this guard once the native reader implements Spark\u0027s strict Variant layout \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala"},"region":{"startLine":209}}}],"partialFingerprints":{"codehealthFindingId/v1":"a767878c5ea24523f8104d6309a464aca3304f2ca36d220663851c5a25a6e1b5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this guard once the native reader receives these settings and applies \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.scala"},"region":{"startLine":216}}}],"partialFingerprints":{"codehealthFindingId/v1":"faac2234f16ef9020142b800daba8245f464221fe63a6605e7a96bc8d52327c5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: consider converting other intermediate operators to columnar. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1647}}}],"partialFingerprints":{"codehealthFindingId/v1":"87cff1d7ba4f4f5452d662c03a9d75b37275ddc89135e65832f3661f71b773e3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(#3510): CometNativeScanExec needs special handling because its makeCopy"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/rules/CometPlanAdaptiveDynamicPruningFilters.scala"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"33074eaddeb72e6fab3e5f3d4756fe1cc41cc12dfa907b404f4c088c2419c1b8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO is this restriction valid for all native scan 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d3ff7bcfb091657d938146667080d3b31617aed81e748edb58ad27598f570ef"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this fallback once DataFusion can ignore embedded Arrow schema hints 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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":358}}}],"partialFingerprints":{"codehealthFindingId/v1":"a433a9b64c7feb00948134114176c56f735e55124d1c377d12b94a8d7cf9befe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this fallback once Comet columnar-to-row conversion supports Variant \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"0493460680abbba4d17ed8fee99e7a8ce38a29dc706de704f9bb151092f66657"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Remove this guard once Comet Python operators preserve Variant identity \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala"},"region":{"startLine":307}}}],"partialFingerprints":{"codehealthFindingId/v1":"c92d32842bce05def40e8ce8c316ceca5fd3c4ba81e8ec09d40a29b4a0e64beb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Are there any other properties to 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":"spark/src/main/scala/org/apache/comet/parquet/CometParquetUtils.scala"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"51fbb2b226b530f410063b574a9017df9c712501d24b3037894a245ffd217be4"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(method-size): perRowBody is inlined inside process\u0027s for-loop and not split. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegen.scala"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"65c3d1910b62c73cc391ebbd94a4687bd301daadeafb5b3077bbe821a237b6a5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(#4280, #4279): once offset-address caching and validity-bitmap byte cache land in"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenInput.scala"},"region":{"startLine":865}}}],"partialFingerprints":{"codehealthFindingId/v1":"c050c1a033890b0a3e70a44e85ae0648aa16fa7af4ffff8ed270d98bc5165d50"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO(utf8-unsafe-write): output-side equivalent of \u0060UTF8String.fromAddress\u0060. Coupled \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/comet/codegen/CometBatchKernelCodegenOutput.scala"},"region":{"startLine":263}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1e44258ac3493f8a8df64be22d50a8a6cb48731f4f4cb1a30ac979b6b05918b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: We probably can move checksum generation here when concatenating partition 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":"spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometBypassMergeSortShuffleWriter.java"},"region":{"startLine":264}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9a081e6cfad55e3110e4668ced4cd77bf9e2e7439ac32cbdb1c88b018817d38"}},{"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":"spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/SpillWriter.java"},"region":{"startLine":170}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3e95df60892c269ba899057d525ac2b54c71da21bbdf16c90057b80b26784bd"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Write the null bit directly and remove the sentinel/masking 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":"native/spark-expr/src/math_funcs/wide_decimal_binary_expr.rs"},"region":{"startLine":408}}}],"partialFingerprints":{"codehealthFindingId/v1":"9d84781164c2b8d7338baf1da4b29559735733923eb9c7e8079afeaa9b036af2"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO upstream this to DataFusion as long as we have a way to specify all \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/json_funcs/to_json.rs"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"71c9cd1aa6ca18329ada5b2986d7cabdc1f66ac6cefdb883a48eae54a37f107b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we should change timezone to Tz to avoid repeated parsing \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/conversion_funcs/cast.rs"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3b2a89a319910fca9ae25899867ef13c5097da7244c0a5bc56276cf82a9929f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO we should change timezone to Tz to avoid repeated parsing \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"794e4528b14fee6d5eb2dce3111f2170386ae124c875cb6537f74cce98716451"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Reuse functions from DF \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/array_funcs/arrays_zip.rs"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"dafff85341732f7d5eb3ff6bafa9a22d3036c405aace4cf548e0fa32ac5804a3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: /// TODO this is copied from the object store crate and has been adapted as a workaround \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/parquet/objectstore/s3.rs"},"region":{"startLine":289}}}],"partialFingerprints":{"codehealthFindingId/v1":"430aab497c9bb7ca0fd7a7047e7cbea81e240f93317d556b4853a46c7a99b051"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: /// TODO: Remove this workaround once an arrow-rs release includes \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":676}}}],"partialFingerprints":{"codehealthFindingId/v1":"7c44631a3cefcd8f74c48e0a7f6c32c581db8e2ac902a5f4dfe82bd1296aef2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: /// TODO: Remove this output rewrite once every supported Spark profile includes SPARK-58949."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/parquet/cast_column/variant.rs"},"region":{"startLine":1176}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c7479fa46773b495bb1a2b6835ac41e98e33bbf4d184077722ba22bf6fa5470"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO this should try and find scalar \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/planner.rs"},"region":{"startLine":2164}}}],"partialFingerprints":{"codehealthFindingId/v1":"f512d4e9e937332913a565e0ed1fae81719a9be02e5129c48c4fa599bd73005c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: Spark does not support DISTINCT ... OVER \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/planner/window.rs"},"region":{"startLine":539}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fc841fc38648e2a290e933cb6a57bd24f4f1773d41a3ee113413188fc2d2da4"}},{"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 \u0060spark/pom.xml\u0060 makes this repository a deployable product (line 648)."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/pom.xml"},"region":{"startLine":648}}}],"partialFingerprints":{"codehealthFindingId/v1":"af1d2c89b9f149bf2d8ff548b8d59862e8567d3753a4a85faa4389e12e351137"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060getByteArrayRdd\u0060 spells \u0060Rdd\u0060 where 22 names in the project spell it \u0060RDD\u0060: 22 of 24 names in project repository spell the token \u0060RDD\u0060 (22 of 24; unit: names in project repository containing \u0060RDD\u0060). Peers: org.apache.spark.sql.comet.CometBatchRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometBroadcastExchangeExec.scala:314); org.apache.spark.sql.comet.CometExecRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala:57); org.apache.spark.sql.comet.CometExecRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala:187); CometExecUtils.emptyRDDWithPartitions (spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:55); CometExecUtils.getNativeLimitRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:65). Rename to \u0060getByteArrayRDD\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometBroadcastExchangeExec.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c4fcc9d55270e6e9b3406c1639f23debc28a3b7cf8d2ca8f6ec2139aad75a08"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060jobTrackerID\u0060 spells \u0060ID\u0060 where 123 names in the project spell it \u0060Id\u0060: 123 of 126 names in project repository spell the token \u0060Id\u0060 (123 of 126; unit: names in project repository containing \u0060Id\u0060). Peers: DeltaPlanDataInjector.sourceKey(planId) (contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala:78); CometExecIterator.taskMemory(planId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:444); CometExecIterator.memoryUsageEvent(executorId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:773); DataTypeSupport.fieldId (spark/src/main/scala/org/apache/comet/DataTypeSupport.scala:146); Native.createPlan(taskAttemptId) (spark/src/main/scala/org/apache/comet/Native.scala:67). Rename to \u0060jobTrackerId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala"},"region":{"startLine":304}}}],"partialFingerprints":{"codehealthFindingId/v1":"504846899ec8012c876d963612ffa175daf89375ea4e5608fa84bae261395ded"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060jobTrackerID\u0060 spells \u0060ID\u0060 where 123 names in the project spell it \u0060Id\u0060: 123 of 126 names in project repository spell the token \u0060Id\u0060 (123 of 126; unit: names in project repository containing \u0060Id\u0060). Peers: DeltaPlanDataInjector.sourceKey(planId) (contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala:78); CometExecIterator.taskMemory(planId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:444); CometExecIterator.memoryUsageEvent(executorId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:773); DataTypeSupport.fieldId (spark/src/main/scala/org/apache/comet/DataTypeSupport.scala:146); Native.createPlan(taskAttemptId) (spark/src/main/scala/org/apache/comet/Native.scala:67). Rename to \u0060jobTrackerId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometWriteFilesExec.scala"},"region":{"startLine":206}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ecb4c26c30416a088f172584ad1c84335a3dac68f254b755609ff023610e39a"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060jobTrackerID\u0060 spells \u0060ID\u0060 where 123 names in the project spell it \u0060Id\u0060: 123 of 126 names in project repository spell the token \u0060Id\u0060 (123 of 126; unit: names in project repository containing \u0060Id\u0060). Peers: DeltaPlanDataInjector.sourceKey(planId) (contrib/delta-spark/src/main/scala/org/apache/spark/sql/comet/DeltaPlanDataInjector.scala:78); CometExecIterator.taskMemory(planId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:444); CometExecIterator.memoryUsageEvent(executorId) (spark/src/main/scala/org/apache/comet/CometExecIterator.scala:773); DataTypeSupport.fieldId (spark/src/main/scala/org/apache/comet/DataTypeSupport.scala:146); Native.createPlan(taskAttemptId) (spark/src/main/scala/org/apache/comet/Native.scala:67). Rename to \u0060jobTrackerId\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometWriteFilesExec.scala"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"c885bb50e4b97b2a237be3157fd1f2a7ab8bd3a07d080edd484190ca90cc5f2a"}},{"ruleId":"D21","level":"note","message":{"text":"\u0060getByteArrayRdd\u0060 spells \u0060Rdd\u0060 where 22 names in the project spell it \u0060RDD\u0060: 22 of 24 names in project repository spell the token \u0060RDD\u0060 (22 of 24; unit: names in project repository containing \u0060RDD\u0060). Peers: org.apache.spark.sql.comet.CometBatchRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometBroadcastExchangeExec.scala:314); org.apache.spark.sql.comet.CometExecRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala:57); org.apache.spark.sql.comet.CometExecRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecRDD.scala:187); CometExecUtils.emptyRDDWithPartitions (spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:55); CometExecUtils.getNativeLimitRDD (spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:65). Rename to \u0060getByteArrayRDD\u0060. [rule N6]"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/operators.scala"},"region":{"startLine":863}}}],"partialFingerprints":{"codehealthFindingId/v1":"e48e3c77fde0cad505ad8a911e47c2d0cf95516611065df744740bd8270534a3"}},{"ruleId":"D26","level":"note","message":{"text":"Projects may be oversized for their cohesion: 3 of 17 project(s) overshoot their size bounds, lowering Project Cohesion to 6.5/10. The most over is \u0060native/spark-expr\u0060 (81420 LoC, 244 module-visible types across 25 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":"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":"cc428d8013d66ce7f4c360a11360a9f21698b588e061af8b1081071bddbca070"},"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":"368ac5d0a98a2e56ad69a458fe6c3a7d58025adeb300f0d90f904d93b104907c"},"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":"b275fa3b4a97a76bb531ea652ad6c642f7d02f9345bdc898d4e71b1ed87b503c"},"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":"9b42d4e043f03a6160baf1e7044ff348d99c969bbcb26581aa2d5959a09601f3"},"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":"5010591a34687ebad25b50802641f2b67bf52718473570aa6ed4f571175ab2ad"},"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":"70b06268f4addc7bf2221c34609abc2d827db5fa73ef4b2d7f56a4c58e1005f0"},"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":"b6089b81cc1c20a8b7ef7d86949fd18536d578c453e47ab8ac20ca0a7c5ee82b"},"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":"dbe6caff0973c89c5d156ea4a1e4fbcb650c37e494c0f55fa971cf67510f2589"},"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":"a2248d3eb62ff05ec0287485693c1aabdfcbd0283b927b689ffd0d58bf2ea2a6"},"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":"cd7ccfb78075159095251406ba30f6e3f3064ddc99804c82d0eec85d3433794d"},"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":"b5d342ca3b3e0de3d031dc7dda6bef43a7e76f6d2c0551db65cfd3d32c63b460"},"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":"566c14cfec3293f0c959635ecc71d7d708d0643730414c98a24dad878c11aafd"},"taxa":[{"id":"CWE-494","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":"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":"a536f591634cce78ada2ddab7a30f8ca525e1ea28048295f3371436091bcf94e"},"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":"2efa8a933dbcb484e2b7086e9067bf025187d1f37263b4f533fb35a34c18508d"},"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":"a1292010bc1a1a0bea133f0f97da905c2dc7803d5190800dd51cfec02ee39685"},"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":"06765fe1ebc7fe103460c9601a06f9048feae3c07175cd43b39dea7446a4b316"},"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":"e37ac92b0f7b20aae288b66c4c9d7f4ca456d94ca829108f020565eba11c23bf"},"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":"33dd14322aed63a89ab00ba53443b89a9774ee29bd961ae4c76b8e1d89c326ed"},"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":"32970809da385d436b1d22f0f407b3c073f866dd7660f7a46d85be690848365e"},"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":"e8b01bbd10010f703d1e85bc380bbe65dc1a7944890ec9f580a86e1192c99e78"},"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":"28642ca4f3fa1392da2350a4221354ae120528f6164f4cf412ba3b225ce0af6f"},"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":"1fce5882c82a42a6d589b956cbff4e69fbf1c1955e14ea409feb866c0515a6f0"},"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":"5ea1d3531415228f16f5d63d1075b8343bffc111fa114fc9f9eb53cc602c4224"},"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":"c415a3df12cc713a4a6611321b743d742f7e4e9aaf70adf62acfcf80b71a9292"},"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":"6e5258070a8038241d2abdb80132d66b3a750cd05add4c483799c8d7c12a91f4"},"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":"051cf4cd28498157495be452c485885afcc6ced0c815b0d9a753c925d4af8657"},"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":"d5b8f11381d61a58459ffc7c595fd52d09c03c711894a63a9578043d2338412b"},"taxa":[{"id":"CWE-829","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":"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":"a1f31e3fc38e806c632551480508ae27b2701acddad0a9d80c648ba1fc9463b3"},"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":"b084deba18fe695fd181ce54d9bc60c94af417f07daf68e37cdadef3853e8975"},"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":"8109dce38defa2356a4dadc0d0de54d2a3068d55e0fa05a6643a42adc1a4628c"},"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":"482e3b19efd040fb2215efbc5e65f5b9996234817368c5a9198eb89910e46231"},"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":"c1bb7814097052b3b9e49cf20adb5ffa3c94da3abc00863955683dc4725b2e91"},"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":"68183d2258834ef78d4f4f95f6e1df2979f34f7d4e8052232e4bbc03dee672b5"},"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":"651d681534ab68d469795695942cd49d77ede15715867b9674af4b1f8ff4b322"},"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":"f55c9d2e3e2efe372b988ca71d1558dc16675a14b2ad8767e039aa5011d81893"},"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":"8f1fd707caa1ffa803c10281adc917bc678f50e9f11b795531fa01ea3ee1bdb2"},"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":"e36a30807bf97b7c93128644f19a48a6051ab59b9a1f2ea004523cd228547d3c"},"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":"fbf4521b45d3c070b8e8450db473f2101a88f7a726705d895f0a33998f9ddc42"},"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":"ef341a5ff156096a96b6f794bbe1f4a6ae2eb567551b590310710f29759053d4"},"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":"dc7a0e349ff0d9415211df0076631dd35293574eb578739bf257bc67ed43cd3e"},"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":"b1cab78826f3c45f3fd4c28486586f05ebf111e07aaae5ef1ce61d282f274d41"},"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":"23fe02dcffc3345d6e2ec0cb803b2c734c6c28e467770b1c191ea26dad261c38"},"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":"458f85f67f4e1e5a0950a2608347237d884c99836f90a3de321398d919f063d5"},"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":"8ddf18e38aede604a7200be705454e1ef5dbe4f0f35356eb4f18cf5088b23098"},"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":"462ad564a73be074971522fa1fe365d87db775ebd85b391d51a66ba4c42bcd17"},"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":"5288fe5e6edd0d4fc05bc6c25e510c70db4f751ab798016d76011994071fffdc"},"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":"796abda890a080b4c744af16d75192f125c98d9e214847e86eceb3cf06853373"},"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":"67aaa88405e1e396d7701f1405457cc542055af10fd19445cefec4f50918166e"},"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":"152a97275b59e1b8495189d3e55480be190f1abfe110cfd3b7d6a6ac93f57a06"},"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":"47be4b0140019dd10eb29579d8de3875ffaf6a80a294e641f845aa2da715cb3d"},"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":"f64c0b8d1c4fb37065028245478b03b7d9c6c5b2478ca81d64fcb41dd7a06c2b"},"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":"ba24cab204e87b0c20668c62fafa0b3830ae0b9e5553d2c2386a0b8b335b55cd"},"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":"eaf9cf7bc7567e12275aad578c089966c72be1d80bab103a9c4a5956157986a9"},"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":"0039dc1f3b0fd4511d0724977c9be68d629c318b857e6306bd8b06544a3fa051"},"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":"619a77f76c804bb1a4abb8ac930cdadc19f4924b48ecbcd9e30d0e0c944607d6"},"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":"38eb715d39728782f003c37544ec8f9b22e9fd41d41ae71eec22aeb68eba51e5"},"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":"79e757be4ff47dd0240798bf52c0a4214dfebeaf07c9d4bfb804eda924f40866"},"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":"41bfde5aa4ef7eb50a79793d33b4ba8b700695d3ca07c4beb08d5af579c8efc8"},"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":"285ff907b8a4de4e22194effa475e2346a0f7302af00a5b7b52d6d6d65197dee"},"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":"64a44caf52777c207d63be208ead528c70450aa3be6b0ab49adc83cfd93d51ee"},"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":"079948285eae34be98b02170a360425794e768a884cd3ef4ba74540eb84796b7"},"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":"5a2ddc6db874229271511638c6ee786fbb2bd68a4212c9f29557d8f9f92522ff"},"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":"93e70c1896e459ed7ee3c7f39caeda0435ef73dced31b2daeb57c1329cfee1cf"},"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":"53050fdb1f7079398feb1a4c843a1ee6b03ed4882a67c23e515c81967a1ab253"},"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":"a799ba2e77a6bcb3d796337bcddfa509382cac318a6c7a501f95991bb6f2c0c9"},"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":"5f4eeb05c8240e2772aaf9a06dfe182a1331ade3f640a091ab123505e313e2bc"},"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":"4fd25f2999e9e0fb22bc8c669f71e92c23e9cd632835a876d64bdd25353b4f52"},"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":"239238340c33c772246c74549a10393e99af2f4cf79f2222746888b30756dc5a"},"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":"f1749969f406677d72d9756f067051718383116d5fd236215d0361c7de5465f4"},"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":"4b5a53632ed56f3af07f96cd56d0326dd7b8eec5100130d56902931df608a6a4"},"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":"21f94205c6dcfb0551deff1624189eff53b2a13954662aecb63dd62cee22653b"},"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":"f39a25b2be3d22da0d885a66d677318a125eb1455b4471de7a6b2f17b3e91c78"},"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":"ae7d33c886709dfad1b777439e7df8df3f9491608b8a7fa6934628ca2c45a35d"},"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":"b3373b045092941de177b68059c4a881c4b9ff6b750527e92340c08935f43878"},"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":"d41ef8bcc864c716588ab4fe336c6c0ed6b8eec64943b1e954e72df9c676ce17"},"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":"cde0766568b96d55191c9470256319c5fccbe1621aeb89d3440340fa48b9ce6c"},"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":"fff3c9bdee73189a431ed6d74423fea434a58ef4614c6abd375e419ca042e576"},"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":"3dfe86827b1c6b365dac222d9e10b1a105037ca879f893f7b7dd3d69c28306cb"},"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":"03fe5daab4f7aff1fd8f6e3ea9ca6169876afd01b4312b1fa9707196039f89a4"},"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":"906baee09a78969e5abe1077c36a3b8b7921a8ef2f3a19ef41fa3b45ddea0c59"},"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":"fda484dec495595e91dd3b6e5cf027b5ccfddecd4263885e3945bc04b9ef287c"},"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":"e27e3d56fa04b5492d3b85a61a75af52b30dac4e6fb53f10f478c79fccb0df12"},"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":"06d04a7103c7449680b0ea85cf1ae1dd68fc1cb374c930a4ad7bc7cbe4ffb5d7"},"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":"8ef6cf1091420497d9991c816b40a2140f2333f5415faff43e7a0ebeb36b929d"},"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":"442cddc5a8f4083e4f5f9ab88c4c72e4d0499ea34f121878a335b3262b2ff0ce"},"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":"59ecb0c1afed17bbb37e76e396f25a9fafd78d4dfca03981a575dc94bb263ca7"},"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":"7753129a42675e99b3108f3f0c0a79b21ac9fbb39fba596d69d9303b664b7767"},"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":"bc12af717c38926e93dd8b8ecce3d9240f22e92eb572f9b336a4e2a8b9c8a383"},"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":"ef367f149a4cc26ddcd5c6ab997dbd8fc228c6ac8daa4608a01e60209d256452"},"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":"6ec6dbeddbe46b99e2cd17084e78f5cdddbeed6d49dabb0a326185978c5c2664"},"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":"a934bbdd0abe97a8d2df3ec6b6a3fcf84cd05fd071ad1e6006b55dc380372da7"},"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":"efd910f540fed167eb9fa1fe6abb1e92dc94694882a90959549031fd1dcc14c7"},"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":"cba2da24f4eedfcd4f5b84d7553275cce7757271cd0cf41038a660f9cce5bc7a"},"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":"31fd70c52a1331e76ca21d3041ca59d05421a961824446dafedb181b33611eec"},"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":"aca88d260d23dcf411f6370fdae7e427f40bb04617b645c07c21eadd032c60e9"},"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":"a9ebcd2b6af0c6ad1e6b7d374833b23ddf41ff80cc0ade8111b6765eb23d00fd"},"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":"5464a731ce798f56d66ceeb8a19a635bf914dd95b59b7e61a228e5c4365900b6"},"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":"d7b16f91b70ea011be031de1c04b6ec4ecef9e4849c1fb814c7d1b12dcc991ff"},"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":"18f38f923315e6946733bc59a90a7826796e86aca9d4627335dcfadc64b10a86"},"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":"373f8f9a181d4308a82bce91353dee9db336bab5eb73b7267fc104efe96e42a3"},"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":"4a786e865582041133ca19b534dda2232a50212e96df6ea7c6cff8f6508fa8fe"},"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":"c53a2503b715fd7a4d2655b9e5d6ce692688f212ee918bfb6e1f7698cb498622"},"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":"7b8397be7d6fce98af3afe9be92b2188407684888252b3ce0c3f9e76373824d4"},"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":"e084071cdf04810995b3f1a902fc9e5788a3f391840a7e0584e8198b64673e16"},"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":"1699892338ff715b152eb6489b0ae724862d057d5cc5b33d17bcc07f8bfeef20"},"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":"7a83488949b314b43abf67aa9476e2361c591727a29f10b2f9a705d4beb32d77"},"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":"21422fbd5fe3af75e926f7bcdc00fd34311253ee9b55d0c29965586ab74b0120"},"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":"34516af4a478a1cbaf7b8c663eecf3b2379b4d6a54f392530d050c7fafc207bb"},"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":"ed1d334a4d755993081c0431cd6bc4c1a10a3faed7cc6d1b03b76d97ecc17e17"},"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":"9f7b9d49764c126183638b1972e4ae6742f967ed288cc5f2a1e32e5dd217a298"},"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":"e5d4f145dc0a9193d9c7ec4a341278d52e4c95c69c9b2bfe92bd1af29f8539b8"},"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":"bb015d67b0a3a62760719c2d6a2e13e9c185d89b4b1584f95c0c4fc9aee58177"},"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":"e9e6b2a275f320b26ecef99f76fb4b93bd20f7ecdc05c9661b2bb5891a4cf8dd"},"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":"f74d7d97e2bd3fa6541404d17bf97c74355bef142cb4357ade8725a26a9808a0"},"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":"53b82bc0536a4b2a4eed617fb7e34caba63c74be2aa8e5a4f0cfe43612baf367"},"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":"08b4976f8b8283cbd36ee8eba550780c31c0740b1aa3113dc559149d231f9ba3"},"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":"2c3d77ec4d0a4ecbc210498d58fc7243923367434c9b969be7953f20bcea6252"},"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":"190b6ae94ec624523e40acfbf151f6e75141941149d16388053386d20272a87a"},"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":"085693164341061004902c71d51e50925f9acfa6d602dcc4af0cea24fd8e20d2"},"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":"c3b4fe56cec7e6d65ca7365a7e6b61e548352fbc226de691b9617f326f7bcce0"},"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":"4265f810a8106e0cf68fa6091a45c51e06d88d252185e7237fff9ab6dd85b752"},"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":"374533b6d53fe1fd3cdeb9cdb01e8cd798cf3bf0eb2d6b00770a5928d8492923"},"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":"40903632d9b232b5b1624c6e91d5598f68d074d768bdf7ec2a74950291080dbd"},"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":"dcd3d315b5e888a157df87e82b1e946dbb6e0fa8587363399325d25be7c45e88"},"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":"f4cdd4669bd19d1b9308744e9ce887517b60415d0a352b5575ebc7d8a169738c"},"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":"45a038b61d10e6a553fc0487c159dc7e13dcdf626d86419fe1affb30dccdc53a"},"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":"818f65e6ae0df0c0cf67e4277c8f4ced3e7fc8557098d5d35be27fc2805e4e8a"},"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":"b0c21b5101c135c8148900d9a57a21f2e083daa416a51b98ed4a68f9ba88bf1a"},"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":"0f9719c90ce4d35c5a79ae542997bf02d7a110b98ab6b2dcbca45e36e3992fc7"},"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":"cfa118788dec80351b62e15925cdb3892eabe759bb2b0727b5068e31e48b8c00"},"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":"91374ee2011dabe7fbab27777137ceedc5314e7c66c7dc85c859bfce1c816fa9"},"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":"8fa16f6d6dd056ff1ba8e5fba1b0987c34644ea28754e0cd41b888930d22a34d"},"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":"708f6a8de997b60c796a4571393b4c201fa201a736e9f3e63ed3be6a5cf6ed8a"},"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":"523b0089b972018478657bdbcebf152acd48d44b09b3d9b89b8128ce8f30c650"},"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":"c7df55a1a12a3f4b0b1b35505c7d2c8fe53ac478185ceca8ca6806586ae28301"},"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":"ecfad5497f00ffb888f85e17fb7af7e037476adae37bfa9aa020b3ea16340a33"},"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":"d56053bcafe5c1fb30d09e2df9231b16555973c141b6cff9b94d7681ce823ccb"},"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":"268859c845c2fafe2f57a777d8bfe8ee602bd98743f7edef76c1e76b0ba2c63e"},"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":"028b895a2382f41cab338d315bb43c1c3d34ec37825d14c1844d7b3d4e2ede0c"},"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":"e48cb9c2f4431913647e9fa1b7dab6223091c8d591d3bc79343f7dbf76185258"},"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":"c9c76b9260bdd795611c5548fc914713c163c4c1c2bdf046490dc50b1c9db8fa"},"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":"37f3fd44437f5f11768dfc447b38da565e125a1685fb92a14ffad48f91d5833e"},"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":"98fd527533c8c975323519034a9c94188078aca0890f26ec0e1f46cda1fd0308"},"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":"8c3f7ae864683e66ba62282c33a2fc4f965ab689cd7731868e27bcc26e423dc4"},"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":"f33c9a452aee6f123113804301970c0e889d54ebf7bdca0cd8de21f2414d65f4"},"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":"184fdf2b2b7acfb307ea6f35c5b0cd55e45b96e4a8fdf630e8e53b1fe12d44b7"},"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":"b1854881af6a356e2ca7d1d572889a2bb4cb955c14fbb7f0167d68f9e6afc888"},"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":"e156037956322ef9e9b8199ca19671bc46b12c84478c2ed35cc9cf62e1415c61"},"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":"be533fcb7f5002fb6703c5db084e2b6f309abb49ef32d9e53a458652dc003a67"},"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":"47f4c02cd3b021e9e15b730f2a9489e4718cee086688e9e9c3641a688dd227a5"},"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":"a8f23155013c1b1dcaa01573d28b09522f1a10f4ae7bbd04800f1e2c10057015"},"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":"db27d132d8da9789c0009106bf9843ee71cd323bc66158018bbb5ab90407266a"},"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":"d11514e9c2718797e6e0b22988fabc680619e7522ae04256d34b3c0590c80d43"},"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":"062e8eced558c4f78a4206701e4305231f56caafefafa03f6fcb9d42cec271c5"},"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":"e09781a09cd182c76b45c735ee510fb3d87a74022e63df8e91cde07819550efa"},"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":"131f6e377a09fc8a2176ac3117858e5e1d3c97499be57e471c9b0d022f77b962"},"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":"f9c2c06f01e38726f0c55e138b734a6bea31572fbaaa6e2f825f873c57465523"},"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":"02dcd002b3f25245c39ea36f2abbbf0a364f14103b9423053ee4bb51be35fae1"},"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":"4ac6de2b44c4849f2001186a8cbe80e7af13feb328a3c62fd675e39ae1e6f31a"},"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":"fea37a74a64fdc1c6609b853f6b1d04e7906a60891f815cfa468a3ad0eeea1f2"},"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":"59e1a722b8c4416a6e4f0c8538892c1e06ebe498915564435f700c68cd3b7303"},"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":"e37454f94485414fa0a5bef384a4698f742a01d80c32f64d8063d0402c735458"},"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":"2ede6d3ee4dfd5f79cecaa6ef928dc49cb0a3f2c9ffe125634c06d5cd0b01bc1"},"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":"3d01c35d7bcaeb9e4a87a6de78846ab4f0761c3c59ba8d436c3031f4f41a31f6"},"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":"e5ab9c77741d8dcf99b854f1cc65d3339135313d73a0a824a3f954ce04e85fd9"},"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":"c48f53b8ccc3273439c45fa6324252ffd27a0dfe6e8ecd88e8edc6ab597a52e4"},"taxa":[{"id":"CWE-94","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":"89354abca330686800546b58d97beb73b3b53e60da4d88c11812acec0dd63c97"},"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":"3fb9e571de1e62372dc12ed86f42a1b23d38dd5a1fe39bb74850b7f8b2220ff0"},"taxa":[{"id":"CWE-327","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":"4738d0215bcb6cee8cf6f53785b07352621b7491b0871e0909f7edb588f4f3cf"},"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":"5e7bf29ffdbb3cb26cf287cbe688ff76bf0a7e7b3b97827fdde35f19dca1526b"},"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":"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":"a19ccec3e702ffb3802377c869496f6bab087316207e5614639b2679cdbed1b9"},"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":"1aea0f5aacd4db12c0d1b4bf9044aeb07759c7dce978b2d603846256bdb17fb6"},"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":"1c22104f13bcb26c148cb56b4e24bf589177776e196969b342010ddb09daa26a"},"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":"4cc935eee7d71dd27f92a2ce9e004dacbd599d091b3f6386981d047162539806"},"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":"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":"7f9a462118f7e2c1febe03427aab6848b3767140a0a148084738e31876fc63cd"},"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":"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":"1b11cd824b6d1e760a908e6a1fead8a83cf25b4f3808a12e8b0d60d161b1fb9f"},"properties":{"dependency":{"package":"org.codehaus.jackson:jackson-mapper-asl","version":"1.9.13","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"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":"c66d2a41ee3e6ec14d48a33b16767ba15774e4cfb2c0803c95fcb836925cb6b1"},"properties":{"dependency":{"package":"com.google.guava:guava","version":"33.7.1-jre","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":"b052d4f9f5fa2c53eca4f5243de8e7fadff245ce0cad4aafadd7a4ac47a04850"},"properties":{"dependency":{"package":"rustix","version":"1.1.5","advisory":"RUSTSEC-2026-0486","aliases":["[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":"e3abd3292295237ed2ba72ff9f5790761b9abc5a7b7e1d7df17b612e06f95fad"},"properties":{"dependency":{"package":"zstd","version":"0.13.3","advisory":"RUSTSEC-2026-0391","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":"b91166056bd4ce0071000a40c3ae414e56d1dae529719deb898c97a52b75860e"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0395","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":"3b6fb5969539a15444cea849738fd546c8cc4a6d4686d505fe6352d3e9152d53"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0396","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":"099bce300eb2bf9dc25932dd4d964824e97338cfb970c719194f658a8850a68c"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0397","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":"8d058c03f29c8810382151881adea98a6018aec79b497955a91c5bd74f4c1bc0"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0399","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":"71b7cb6db245f80cc99a41d0ec5e23a12ca16db9dfd905a73084e1a5b8fdd3b7"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0400","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":"c6a82a58923286d1a4e8456013224b7e41180b42fdbb1a7fc5fef86f49e1b03e"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0401","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":"79d4e5c01171bbf6f714066383b9b8ac02a9c0d8f0e6b36b12dc0a00dbc63af8"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0402","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":"27bf8402638886a5718e82dcc4089fdac026e0bae455f2fc3545227a5fd8cf70"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0404","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":"24af2b372561ea2faec6b77cfa24b9b648cb065ec7542df7f2646f3e63ffdfed"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0405","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":"9919f9b4b939c7a157556cff915cad297a948e67cf9597849c3b7c87747dca9a"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0406","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":"f9d0c1a0d9d4b65d1d6eb39e206e1f1166450035a98629aaa038be82b7943d20"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0398","aliases":["RUSTSEC-2026-0403"],"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":"1e7cb3f178023735022e913b8187880bba291a10a3041d61dc7a1b1505650220"},"properties":{"dependency":{"package":"pin-utils","version":"0.1.1","advisory":"RUSTSEC-2026-0441","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":"0adacff805dd07a4e8e8e525dc6f9c38273ccbb7441a8c35d77a237f437235d2"},"properties":{"dependency":{"package":"rustix","version":"1.1.5","advisory":"RUSTSEC-2026-0486","aliases":["[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":"deb7d83e2cf949f5e081d098b5e8ce8352f0c3377503f63d5e7ae9fa78da2c07"},"properties":{"dependency":{"package":"pulldown-cmark","version":"0.13.5","advisory":"RUSTSEC-2026-0433","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":"9cbf80e76f8868a0aeda2b4566038a3ead101af8f621e857fca1281614455357"},"properties":{"dependency":{"package":"rustix","version":"1.1.5","advisory":"RUSTSEC-2026-0486","aliases":["[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":"cb1ae122ca5730e1daf3aaca4bf936f9a4b53a48b3dea05a6441fa3520fc61fa"},"properties":{"dependency":{"package":"org.eclipse.jetty:jetty-server","version":"11.0.26","advisory":"[GHSA redacted]","aliases":["[CVE redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"9ffa0ea31194cf047fd5b7c022df06666f2849b4763711c80914a99d99394b27"},"properties":{"dependency":{"package":"async-std","version":"1.13.2","advisory":"RUSTSEC-2025-0052","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"84fef050298786e23d4461b745ac84e1ce1befd54083db7b705e39fe5faed2c4"},"properties":{"dependency":{"package":"paste","version":"1.0.15","advisory":"RUSTSEC-2024-0436","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"92b4acacd14454d083ae6b93b780c8c390b435de631923a9a41719cd1e9bf7ad"},"properties":{"dependency":{"package":"quick-xml","version":"0.26.0","advisory":"RUSTSEC-2026-0194","aliases":["RUSTSEC-2026-0195"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"7176a1fd12ee3fcbd8df9030593104985e79bfd6feac71555e319f6ca92974af"},"properties":{"dependency":{"package":"quick-xml","version":"0.39.4","advisory":"RUSTSEC-2026-0194","aliases":["RUSTSEC-2026-0195"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"071b6a5a43e775bb704ac166c7b7690e7f6c7b0e366f296d7886d97b0108b2d1"},"properties":{"dependency":{"package":"rsa","version":"0.9.10","advisory":"RUSTSEC-2023-0071","aliases":["[CVE redacted]","[GHSA redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"821bc6da8b4edcd0cc184e1a70f27b17313708065ea2e0255cc3c76278033c9c"},"properties":{"dependency":{"package":"unsafe-libyaml","version":"0.2.11","advisory":"RUSTSEC-2024-0449","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"fa65532652a56e160fa5437ff061845afc3c90056a8a21210732362782ed8f81"},"properties":{"dependency":{"package":"zstd","version":"0.13.3","advisory":"RUSTSEC-2026-0391","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"33ca8ba1965a64346af501419631d1285b3b81421a0057ecf3b637d04df74ef0"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0395","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"b37b0d05d4df7efdca710e740b9de7ddf5a63b5eb2a74ac4a055842a6a0da9df"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0396","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"c77bdfdc982801406d50e3d339b6558cf2583ea9ac170ca95113c70e264b54d3"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0397","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"709737d964d7fbfd880a5108dfc70185f458440f6c1db0544442ceab35d57311"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0399","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"6fcad4f55f9aca8e060e90cfdf75447992615c92dec129e2430c48ee0da2690e"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0400","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"4065bad0f1a4fdaa506a05c3fde065f2784e06b33b215944e16ecd4de5b99e4a"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0401","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"ac5e38446e12d4eba1723ebfb50f4385bc682e35ccd26946e9267ed6b3042a1a"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0402","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"b1e85752aed4bc125d540f496af9e97ed37cbac38289eadb7d63344c59831adc"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0404","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"2c1941936945e85b9b7f2966341afa744681a406f434d71d250e0f440221cdfb"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0405","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"6a2ddf8f0ead3ba037db20d8e96e89652cb686afa09441b6b8330195107b7446"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0406","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"d2bbe9fca7ac71dd396c217caa3f41b4bfc5ccbc8c4724103c337f0549177df4"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0398","aliases":["RUSTSEC-2026-0403"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"2c90638f1b1e33a7f7205f8cca563a21ae9deea90e2980d1746653cc2d0b74ea"},"properties":{"dependency":{"package":"paste","version":"1.0.15","advisory":"RUSTSEC-2024-0436","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"c45f40e199ec7c71ae3565853c2ece76ecb68de63371f29cf5c99be597b2f0a2"},"properties":{"dependency":{"package":"quick-xml","version":"0.39.4","advisory":"RUSTSEC-2026-0194","aliases":["RUSTSEC-2026-0195"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"10b8cbce1be12b3239b06635b47b4fa9e160610c8919e777e01f237d4de1ac19"},"properties":{"dependency":{"package":"rsa","version":"0.9.10","advisory":"RUSTSEC-2023-0071","aliases":["[CVE redacted]","[GHSA redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"b760af5226fe4b741e6132936bf5dc01fa0d1b660d8de6d52548a0ff7d394637"},"properties":{"dependency":{"package":"unsafe-libyaml","version":"0.2.11","advisory":"RUSTSEC-2024-0449","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"064e54cf3f6ccda1bf691cb0a3ca6a8d3f37339720590198fef94625fb6c8c93"},"properties":{"dependency":{"package":"zstd","version":"0.13.3","advisory":"RUSTSEC-2026-0391","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"8ad0f0b2ba4b4dc6edf64b7b692dd91710b7f2fff454e20366d278d945ef6ea6"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0395","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"db59d8a5d069fe688e76c34bbed0ce89c08dc857a7f66d8297eb69b96c614c81"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0396","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"84e5f30c2236b46c5f5fbf207b5fdb31703046bdaca9b9c69746d2b1388cbee2"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0397","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"beaa720be30788662752fe97ec525f53a5d03625fd0dde925ba942a38823a1e1"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0399","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"96ba7bc997413d732fc18dcfb38abee4ad498135f6a27a44593856ae1d83833d"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0400","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"69e546cdeb76d4400727fa526565bd2e5708d1af3619c5ba23d387b7ffdbe3cb"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0401","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"a34ab3f8e62f74861f93b2f2ad020689e943865e56e673a09e93c09b9f23d12f"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0402","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"90a5e9a2623f0425eef1281037fcab0f84ba135a2b8d36b2df6b5c38f77886db"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0404","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"3d78d39ba15fbec3dcabe43a50d4b3f4c8a22ecd6b9967ddc3e05959180f42cc"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0405","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"2704caceda002c77fa6814dd502f869002ec30ebe64fd209472087597eed32b3"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0406","reachability":{"kind":"unknown"}}}},{"ruleId":"D30","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":"cae892128decd82bc99b23d60fa869de7f5f973e650e26c06e14c80af1bef994"},"properties":{"dependency":{"package":"zstd-safe","version":"7.3.0","advisory":"RUSTSEC-2026-0398","aliases":["RUSTSEC-2026-0403"],"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":"3c5b60dda11b4ff268f96ea6331f24ad474548c0daeca7dd4c7873420e52fb87"},"taxa":[{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","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":"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":"b12bc805ebded9ea612f97d6b5a4a0fc1c674310228f3eebd429733d9acd593d"},"taxa":[{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A08:2025","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":"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":"45f1f93efb298984e7864827bfd5549a7970476c41de1f359f632b40e10c4917"}},{"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":"05d995d15ae27a26baedf06beeb2c3cd14922a942aa44ec4c6c37dee32bf14e3"}},{"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":"aea7f262c31ee5c5502267a18f3fdbf8a02e231ad5a4c13d469453b83adaf354"},"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":"7fc56f07eeb6596c4d88d1c049106b43e1b61ef236d002f2139436fb9ac1104d"}},{"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":"25850cc4e6388bd377a65409a1eab2c38c0ae65fc8c88cfa76608252f53216e7"}},{"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":"9991135e591629500450826990af5886589d193c65917d1b403787b7be991b73"},"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":"ea3cabf8b069d378ae7dda350139a2f73f8dda9a783a9856719886e970b8773a"},"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":"c52c27783fa3ed82a1dd7f39881d70ede23c977c2d22e07fba1dd9a96784de30"}},{"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":"b18356701603ca6d16a6070ccfbfca7f6c72e91041ff0bbb4022b1381186b699"}},{"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":"8f3b6cfef25ed0fad6e332a982862e08076abeca8c5f1d29f10c855b0b25227b"}},{"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":"3a8aaf40435a2935ff9359b9d47cc20a5c29efc4a453ca42d819e71479a8487b"},"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":"D34","level":"note","message":{"text":"Orphaned files with no living knowledge: 4 of 581 analysed file(s) have no living knowledge left \u2014 their last meaningful change has decayed away, so if one breaks, no one currently understands it (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; 581 of the 813 production source files in this repository met that bar). None is large enough to earn a read-through of its own, so this row stands in for the per-file rows rather than raising one each \u2014 most significant first: native/spark-expr/src/nondetermenistic_funcs/randn.rs, native/spark-expr/src/nondetermenistic_funcs/monotonically_increasing_id.rs, spark/src/main/scala/org/apache/spark/sql/comet/CometCollectLimitExec.scala, native/spark-expr/src/predicate_funcs/is_nan.rs. 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":"native/spark-expr/src/nondetermenistic_funcs/randn.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf32c986f7ee26b5511aac28032e3c958cdb35c8a64e8d98bdc296c1ceebd260"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/nondetermenistic_funcs/monotonically_increasing_id.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"03f652b1c6ee06aa8d9f9cbf74adc43ef502784b92e96b9a437aad90204110f9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/src/main/scala/org/apache/spark/sql/comet/CometCollectLimitExec.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e061a6587e0e1d33c222de2bf7c30d66422ddeea6b9951c8b0c474f2ee2bb1d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/predicate_funcs/is_nan.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"96d7674dfb92d0c469f0bdf2d53072c51d749748fe11a0a404caa97f0ae811da"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: spark_config.rs \u2194 CometExecIterator.scala: \u0060native/core/src/execution/spark_config.rs\u0060 (context native) and \u0060spark/src/main/scala/org/apache/comet/CometExecIterator.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 82% of the time (9 of the 11 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 9 shared commits counted here, the most recent 3 are \u00609a3d2a29\u0060 perf: load the next Parquet file\u0027s footer and page index while the cu\u2026; \u0060cae599ac\u0060 feat: add config to disable or restrict native UDF library loading (#\u2026; \u006066e0c700\u0060 test: fail Comet tests when a native plan mislabels a timestamp\u0027s tim\u2026 \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/spark_config.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"64731ea1631ed4476b8b333913b51a1fa3476f534cfdfbc2bfe0c63e78c34d30"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: error.rs \u2194 ShimSparkErrorConverter.scala: \u0060native/common/src/error.rs\u0060 (context native) and \u0060spark/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 76% of the time (13 of the 17 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 13 shared commits counted here, the most recent 3 are \u006072c48471\u0060 fix: preserve Spark errors for Parquet timestamp overflow (#5891); \u0060b8432a00\u0060 feat: Surface native scalar Arrow UDF errors as Spark\u0027s PythonExcepti\u2026; \u0060070951d2\u0060 feat: convert OneRowRelation to Arrow by default (#6666) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/common/src/error.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a673821b900face7786c1229f0c3d38af81de277e777fed14dc50ec506442fa4"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: error.rs \u2194 ShimSparkErrorConverter.scala: \u0060native/common/src/error.rs\u0060 (context native) and \u0060spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimSparkErrorConverter.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 65% of the time (11 of the 17 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 \u006072c48471\u0060 fix: preserve Spark errors for Parquet timestamp overflow (#5891); \u0060070951d2\u0060 feat: convert OneRowRelation to Arrow by default (#6666); \u006083a7cfb1\u0060 fix: match Spark ANSI integral overflow errors (#6217) (#6249) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/common/src/error.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ada874d3c2c3d7d3863bb5087ec77774fd156c67d1b73768ce4535c89414919"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: comet_scalar_funcs.rs \u2194 CometExprShim.scala: \u0060native/spark-expr/src/comet_scalar_funcs.rs\u0060 (context native) and \u0060spark/src/main/spark-4.1\u002B/org/apache/comet/shims/CometExprShim.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 60% of the time (6 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 6 shared commits counted here, the most recent 3 are \u0060cb0b584b\u0060 fix: \u0060get_json_object\u0060 returns first value for duplicate keys to matc\u2026; \u006036146a87\u0060 fix: align time parsing and native second extraction with Spark (#5738); \u006082d674e3\u0060 feat: support Spark expression json_array_length (#4365) (at that commit the file was still \u0060spark/src/main/spark-4.1/org/apache/comet/shims/CometExprShim.scala\u0060) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/comet_scalar_funcs.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"595cec15801e1a96bbc0228326d1efb7e2c7a68dc59e1e339c95dd9b29b3f170"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: utils.rs \u2194 CometMetricNode.scala: \u0060native/core/src/execution/metrics/utils.rs\u0060 (context native) and \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometMetricNode.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 55% of the time (6 of the 11 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 6 shared commits counted here, the most recent 3 are \u0060f0688148\u0060 fix: report input and SQL metrics while a native shuffle write runs (\u2026; \u0060f90a3aa4\u0060 feat: expose native aggregate spill and memory metrics (#5423); \u00600215f83f\u0060 chore: surface DataFusion 54 PruningMetrics and Ratio in CometNativeS\u2026 \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/metrics/utils.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccd8730b95f1983efc7ceebbd3dea6d63b917f7731aae9c8556458221a8d9391"}},{"ruleId":"D35","level":"error","message":{"text":"Boundary-crossing change coupling: parquet_writer.rs \u2194 CometNativeWriteExec.scala: \u0060native/core/src/execution/operators/parquet_writer.rs\u0060 (context native) and \u0060spark/src/main/scala/org/apache/spark/sql/comet/CometNativeWriteExec.scala\u0060 (context spark) sit in DIFFERENT parts of the tree yet change together 50% of the time (5 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 5 shared commits counted here, the most recent 3 are \u00600f7f8e45\u0060 feat: adding \u0060elapsed_compute\u0060 to the writer (#5143); \u0060e8c7ee73\u0060 fix: honor Spark\u2019s commit protocol in Spark 3.x native writes (#4746); \u00602fd3960d\u0060 chore: Support native writer \u0060Overwrite\u0060 and \u0060ErrorIfExists\u0060 modes (#\u2026 \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/operators/parquet_writer.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"81b0dba976c0195109d7c678f133100ebe27309c52ce795b292d9dc37af81599"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: mod.rs \u2194 comet_scalar_funcs.rs: \u0060native/spark-expr/src/array_funcs/mod.rs\u0060 and \u0060native/spark-expr/src/comet_scalar_funcs.rs\u0060 change together 71% of the time (17 of the 24 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \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 \u00601dec4c05\u0060 fix: match SPARK-58821 and SPARK-60118 in sequence and string to deci\u2026; \u0060348d38f2\u0060 fix: preserve Spark nested null ordering in native sort (#6968); \u00607d8d9b15\u0060 feat: normalize floats in native array_distinct and array_union (#6563) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/spark-expr/src/array_funcs/mod.rs"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f2d6553a62c18b0e7dbc619acfc4879f689a40a5db76a5d8d3d5c51ae2e8230"}},{"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":"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":"eb00976a698a5d68999b7ee6d27206fd374e916853e7ff1ead5eed42386f043f"},"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":"89fee31c08e289ca57206f753bcf00e3f58988d56ca1ec0805ca761fc8bc3574"},"taxa":[{"id":"CICD-SEC-4","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":"a9943a1da79cb8d41ac7ea92cafbe67b845b55dc4b66a3e182cb3766487b1df4"},"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":"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 6/9 runnable modules use logging (modules with no entry point or server are excluded \u2014 they are libraries a runnable module hosts). Silent: \u0060.\u0060, \u0060dev/release\u0060, \u0060docs\u0060."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"91a94e21d6d4d0e6a2003f94505b0b02b157176f0b24c4820f3f82b4447a97fe"}},{"ruleId":"P3","level":"note","message":{"text":"Dependabot does not watch pip/maven: \u0060.github/dependabot.yml\u0060 schedules updates, but no \u0060package-ecosystem\u0060 entry covers \u0060pip\u0060, \u0060maven\u0060, which this tree depends on \u2014 so those dependencies get no update pull requests and no advisory pressure, however complete the dep-scan credit looks. Add the missing entries to the \u0060updates:\u0060 list."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":".github/dependabot.yml"},"region":{"startLine":19}}}],"partialFingerprints":{"codehealthFindingId/v1":"b088426099e1fa1ceee804f122e0a555a563eb08f94238f80e8d2b25ab9b18e0"}},{"ruleId":"P7","level":"warning","message":{"text":"Outbound HTTP without resilience: \u0060reqwest::Client::new(\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":"native/core/src/parquet/objectstore/s3.rs"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f0c3984c1101e746914b1c9828b88f948f52ce4bfc47d6f74d852fc1c6d8481"}},{"ruleId":"S1","level":"note","message":{"text":"No security response headers detected: None of the 11 security response headers the OWASP Secure Headers Project recommends (Content-Security-Policy, Strict-Transport-Security, X-Content-Type-Options, X-Frame-Options, \u2026) is configured \u2014 defense in depth, even when a reverse proxy could set them. This is reported because \u0060Dockerfile\u0060 builds the web-server image that serves this application, so the configuration that would carry these headers is in this repository and was read in full. (\u22122.0 on this card.)"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kube/Dockerfile"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"7baa0e9832933d5746e9dc2af573b2b860dfca5f5577ff8b14f0a05e50eccc8d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060block.pageNumber == MemoryBlock.FREED_IN_ALLOCATOR_PAGE_NUMBER || block.pageNumber == MemoryBlock.FREED_IN_TMM_PAGE_NUMBER\u0060 appears character-identically in 2 files \u2014 spark/src/main/java/org/apache/spark/shuffle/comet/CometUnboundedShuffleMemoryAllocator.java, spark/src/main/java/org/apache/spark/shuffle/comet/CometUnifiedShuffleMemoryAllocator.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":"spark/src/main/java/org/apache/spark/shuffle/comet/CometUnboundedShuffleMemoryAllocator.java"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"00eeb6bc73c39fefe11b794c3dd857ed5e3bd00181e75b6c05b980ba5016ca3e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060spill.file.exists() \u0026\u0026 !spill.file.delete()\u0060 appears character-identically in 2 files \u2014 spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java, spark/src/main/java/org/apache/spark/sql/comet/execution/shuffle/CometUnsafeShuffleWriter.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":"spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java"},"region":{"startLine":247}}}],"partialFingerprints":{"codehealthFindingId/v1":"c90951c78b251e04999ae103f70252709fab0168d54887ee15d824aae7adca56"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060matches!(e, arrow::error::ArrowError::InvalidArgumentError(_)) \u0026\u0026 e.to_string().contains(\u0022too large to store in a Decimal128\u0022)\u0060 appears character-identically in 2 files \u2014 native/spark-expr/src/conversion_funcs/string.rs, native/spark-expr/src/math_funcs/internal/checkoverflow.rs. 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":"native/spark-expr/src/conversion_funcs/string.rs"},"region":{"startLine":419}}}],"partialFingerprints":{"codehealthFindingId/v1":"094eac7e5cc2a6f2edee576994d54a96ab7c68cf55073a11d28513f3e0490356"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060msg.contains(\u0022_LEGACY_ERROR_TEMP_2094\u0022) \u0026\u0026 msg.contains(\u0022id=1 matches [x, y]\u0022)\u0060 appears character-identically in 2 files \u2014 native/core/src/parquet/parquet_support.rs, native/core/src/parquet/schema_adapter.rs. 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":"native/core/src/parquet/parquet_support.rs"},"region":{"startLine":3168}}}],"partialFingerprints":{"codehealthFindingId/v1":"77238445d21ad6c7088fae18398011f049116ce42747ff6094980db48ec93c62"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060opt_filter.is_none() \u0026\u0026 values.null_count() == 0\u0060 appears character-identically in 3 files \u2014 native/spark-expr/src/agg_funcs/avg.rs, native/spark-expr/src/agg_funcs/avg_decimal.rs, native/spark-expr/src/agg_funcs/sum_decimal.rs. 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":"native/spark-expr/src/agg_funcs/avg.rs"},"region":{"startLine":250}}}],"partialFingerprints":{"codehealthFindingId/v1":"d732e51fa249e669e70afcc0e0da4ab71e114480c56168cbb67ef175785c0b26"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060values[0].null_count() == 0 \u0026\u0026 values[1].null_count() == 0\u0060 appears character-identically in 2 files \u2014 native/spark-expr/src/agg_funcs/correlation.rs, native/spark-expr/src/agg_funcs/regr.rs. 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":"native/spark-expr/src/agg_funcs/correlation.rs"},"region":{"startLine":325}}}],"partialFingerprints":{"codehealthFindingId/v1":"43d4b6c250dba74840f64715921a556b4f34da69b0986427569bb58f1712d83b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!isSpark35Plus \u0026\u0026 scanExec.partitionFilters.exists(isAqeDynamicPruningFilter)\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala, spark/src/main/scala/org/apache/comet/serde/operator/CometNativeScan.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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1a77a1f8450ccf5c9691db645f8dcdeb73465925cbc4278720bf28fded0be00"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060!op.checkCardinality || rowIdOrdinal(op).isDefined\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":177}}}],"partialFingerprints":{"codehealthFindingId/v1":"c51bfaa4bf6906119b57aebb4a01370aef3346a2f05750fb2ab92c4f83ff01b0"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(expectedNulls || !actualNulls) \u0026\u0026 dataTypeCompatible(actualElement, expectedElement)\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":213}}}],"partialFingerprints":{"codehealthFindingId/v1":"2924a172ca17dd9842b4c807c039aa06a1746b8cd688c573f972f85950d64b34"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060(expectedNulls || !actualNulls) \u0026\u0026 dataTypeCompatible(actualKey, expectedKey) \u0026\u0026 dataTypeCompatible(actualValue, expectedValue)\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5b97a29ca2e6a320d92300ee8910c4c8273101a86adff9d6ab8fa5b8c22bef4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060actualField.name == expectedField.name \u0026\u0026 (expectedField.nullable || !actualField.nullable) \u0026\u0026 dataTypeCompatible(actualField.dataType, expe\u2026\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":223}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e974cf51489e8c1b260e00f612a57fbccf8824245f7de18fa7fe6317e547984"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060childOp.nonEmpty \u0026\u0026 matched.forall(_.isDefined) \u0026\u0026 notMatched.forall(_.isDefined) \u0026\u0026 notMatchedBySource.forall(_.isDefined) \u0026\u0026 isSourcePrese\u2026\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"625a2f43d388453bc3132b49cee1026e2bd6f7f09f12ca7d4d17cc8bae08e060"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060condition.isDefined \u0026\u0026 outputs.forall(_.isDefined)\u0060 appears character-identically in 2 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"943c231db7f51b1dd6e633de997a30d47dce168544583bd83ccc50222aef7540"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060d != null \u0026\u0026 (d.isInstanceOf[ArrayBasedMapData] || d .isInstanceOf[GenericInternalRow] || d.isInstanceOf[GenericArrayData])\u0060 appears character-identically in 2 files \u2014 contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala, spark/src/main/scala/org/apache/comet/rules/CometScanRule.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":"contrib/delta-spark/src/main/scala/org/apache/comet/contrib/delta/DeltaScanSupport.scala"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"b50a7696f37b0acecad89b71481ebb6f796279cd095af7e7c3f9c533642065eb"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060key.equals(\u0022DataFilters\u0022) || key.equals(\u0022Format\u0022)\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala, spark/src/main/scala/org/apache/spark/sql/comet/CometScanExec.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":"spark/src/main/scala/org/apache/spark/sql/comet/CometNativeScanExec.scala"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"35136fd796bd34a2e244780c867350fc7836bbb16a75a0611e3be2998161c3d6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060leftExpr.isDefined \u0026\u0026 rightExpr.isDefined\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala, spark/src/main/scala/org/apache/comet/serde/arithmetic.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":"spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala"},"region":{"startLine":1209}}}],"partialFingerprints":{"codehealthFindingId/v1":"91f43e3a77d22a0260fb182bb6ec4ac8aff40b9a4cc9f81ac2ff0aa45391b777"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060op.conf.resolver(attr.name, MergeRows.ROW_ID) \u0026\u0026 attr.dataType == LongType\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"653efa2cb588d166e20b2805f5d016cebcea86d29f8c554ad7ea3132c7008e56"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060op.matchedInstructions.forall(instructionShapeSatisfied(_, outputTypes)) \u0026\u0026 op.notMatchedInstructions.forall(instructionShapeSatisfied(_, ou\u2026\u0060 appears character-identically in 3 files \u2014 spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.0/org/apache/comet/serde/operator/CometMergeRows.scala, spark/src/main/spark-4.1\u002B/org/apache/comet/serde/operator/CometMergeRows.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":"spark/src/main/spark-3.5/org/apache/comet/serde/operator/CometMergeRows.scala"},"region":{"startLine":188}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ea1a1b7845ba8c48317b2bafe7685123b202ef8a43c55ef61d8f4781200c13f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060rowIter.hasNext \u0026\u0026 rowCount \u003C maxRecordsPerBatch\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometArrowConverters.scala, spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/RowArrowReader.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":"spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometArrowConverters.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"5274c5c3c17b1a1e6db4e6b3d29b9c30412b18af07a43c62c8d635fe29db9aac"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060scan.relation.cacheBuilder.serializer.isInstanceOf[ArrowCachedBatchSerializer] \u0026\u0026 ArrowCachedBatchSerializer.supportsSchema(scan.relation.ou\u2026\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/comet/rules/CometCacheColumnarRule.scala, spark/src/main/scala/org/apache/comet/rules/CometExecRule.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":"spark/src/main/scala/org/apache/comet/rules/CometCacheColumnarRule.scala"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"32b45dac8be57cd83f16849383086ca15bab473001baa9c633ff0b43d04820f5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060showTransformations \u0026\u0026 !newPlan.fastEquals(plan)\u0060 appears character-identically in 3 files \u2014 spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala, spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala, spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.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":"spark/src/main/scala/org/apache/comet/rules/CometExecRule.scala"},"region":{"startLine":1036}}}],"partialFingerprints":{"codehealthFindingId/v1":"2396d911b5d5ecfb960f883c1822ac854a2a36696df3d58355006e0499e3f580"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060stageAttempt \u003E= 0 \u0026\u0026 stageAttempt \u003C MAX_STAGE_ATTEMPTS\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/comet/shuffle/CelebornShufflePusherFactory.scala, spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.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":"spark/src/main/scala/org/apache/comet/shuffle/CelebornShufflePusherFactory.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7f7aa778308e3103f71de3db3089e51ddceb7ace67933f120cc4e24b7e31331"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060taskAttempt \u003E= 0 \u0026\u0026 taskAttempt \u003C MAX_TASK_ATTEMPTS\u0060 appears character-identically in 2 files \u2014 spark/src/main/scala/org/apache/comet/shuffle/CelebornShufflePusherFactory.scala, spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometCelebornShuffleReader.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":"spark/src/main/scala/org/apache/comet/shuffle/CelebornShufflePusherFactory.scala"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"802c7b38e7b368fa50694925c2705257cdef2b110ff187def2a33e2413b8b245"}},{"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 425 (\u0060u32::from_le_bytes\u0060), then used to size a \u0060Vec::with_capacity\u0060 at line 426 \u2014 and nowhere in its scope is \u0060n\u0060 compared to anything, clamped, or bounded against the input that remains. Whoever wrote those bytes therefore chooses the allocation directly: it reserves the whole length before a single byte of the payload is known to exist, so a 32-bit length asks for up to 4 GiB, and an allocation the allocator refuses aborts the process with \u0060memory allocation of \u2026 bytes failed\u0060 \u2014 an abort, not a panic, so no \u0060catch_unwind\u0060 intercepts it and the whole process dies; a 64-bit length past \u0060isize::MAX\u0060 panics with \u0060capacity overflow\u0060 instead, 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":"native/spark-expr/src/agg_funcs/quantile_summaries.rs"},"region":{"startLine":426}}}],"partialFingerprints":{"codehealthFindingId/v1":"01233764674d443a79be86ad90bfd7bfec13f16b2a279b0e0691d3723e564104"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 306 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.info(\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":"spark/src/main/java/org/apache/spark/shuffle/sort/CometShuffleExternalSorter.java"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0f9de4ea397b26dad40cca86da3ad3645f1dec6eb06e5c3b6f7505adcdfce78"}},{"ruleId":"X5","level":"note","message":{"text":"Scala\u0027s null is not held to the type system everywhere: No build over this repository\u0027s 349 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 on parse failure: \u0060inspectLocation\u0060 (in \u0060validateIcebergFileScanTasks\u0060) answers \u0060\u0060 when \u0060URISyntaxException\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":"spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala"},"region":{"startLine":1598}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d2a84a51dc83fd61917336246f78bf45f7fd9d6ad9f1958f8d20649e0ca4a1a"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default on Err: \u0060from_spark_config\u0060 turns every \u0060Err\u0060 into \u0060false\u0060 \u2014 a failure becomes a plausible value and a silent behavior change with no trail. Log the error or propagate it with \u0060?\u0060. 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 arm or in the doc comment, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/c_udf/policy.rs"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"66dc864ce924f834c41d8d5b55d2dd5a7027137725e810bdbf62062e541b9140"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default on Err: \u0060create\u0060 turns every \u0060Err\u0060 into \u0060false\u0060 \u2014 a failure becomes a plausible value and a silent behavior change with no trail. Log the error or propagate it with \u0060?\u0060. 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 arm or in the doc comment, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"native/core/src/execution/operators/dynamic_filter/parquet_reader/schema_adapter.rs"},"region":{"startLine":73}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c8efc5f03718ac8c99d3f45b9fe2c8c1b58a8c84ac28667275fad5c6cb7c654"}}],"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-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-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-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-327","guid":"e51910ff-67b5-3c51-aa3d-92837d9eab90","name":"Use of a Broken or Risky Cryptographic Algorithm","shortDescription":{"text":"Use of a Broken or Risky Cryptographic Algorithm"},"helpUri":"https://cwe.mitre.org/data/definitions/327.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-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-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-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"}]},{"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":"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":"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-4","guid":"c859d8ea-8b24-a157-9406-94929c10397a","name":"Poisoned Pipeline Execution (PPE)","shortDescription":{"text":"Poisoned Pipeline Execution (PPE)"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-04-Poisoned-Pipeline-Execution"},{"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":248,"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."]}]}