{"$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":"D9","name":"Test Distribution","shortDescription":{"text":"Test Distribution"},"helpUri":"https://codehealth.canine.dev/dimensions/D9"},{"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":"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":"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":"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":"AX6","name":"Interface segregation","shortDescription":{"text":"Interface segregation"},"helpUri":"https://codehealth.canine.dev/dimensions/AX6"},{"id":"AXB2","name":"Runtime readiness","shortDescription":{"text":"Runtime readiness"},"helpUri":"https://codehealth.canine.dev/dimensions/AXB2"},{"id":"ED5","name":"Idempotency","shortDescription":{"text":"Idempotency"},"helpUri":"https://codehealth.canine.dev/dimensions/ED5"},{"id":"GD1","name":"Unfinished \u0026 placeholder code","shortDescription":{"text":"Unfinished \u0026 placeholder code"},"helpUri":"https://codehealth.canine.dev/dimensions/GD1"},{"id":"IC1","name":"Incompleteness \u0026 stubs","shortDescription":{"text":"Incompleteness \u0026 stubs"},"helpUri":"https://codehealth.canine.dev/dimensions/IC1"},{"id":"M1","name":"Documentation (README)","shortDescription":{"text":"Documentation (README)"},"helpUri":"https://codehealth.canine.dev/dimensions/M1"},{"id":"M2","name":"Architecture documentation","shortDescription":{"text":"Architecture documentation"},"helpUri":"https://codehealth.canine.dev/dimensions/M2"},{"id":"M3","name":"Folder \u0026 project structure","shortDescription":{"text":"Folder \u0026 project structure"},"helpUri":"https://codehealth.canine.dev/dimensions/M3"},{"id":"P1","name":"CI/CD gates","shortDescription":{"text":"CI/CD gates"},"helpUri":"https://codehealth.canine.dev/dimensions/P1"},{"id":"P10","name":"Library API \u0026 versioning","shortDescription":{"text":"Library API \u0026 versioning"},"helpUri":"https://codehealth.canine.dev/dimensions/P10"},{"id":"P12","name":"CI test-gate honesty","shortDescription":{"text":"CI test-gate honesty"},"helpUri":"https://codehealth.canine.dev/dimensions/P12"},{"id":"P2","name":"Observability","shortDescription":{"text":"Observability"},"helpUri":"https://codehealth.canine.dev/dimensions/P2"},{"id":"P3","name":"Security \u0026 performance tooling","shortDescription":{"text":"Security \u0026 performance tooling"},"helpUri":"https://codehealth.canine.dev/dimensions/P3"},{"id":"P4","name":"Deployment \u0026 Rollback","shortDescription":{"text":"Deployment \u0026 Rollback"},"helpUri":"https://codehealth.canine.dev/dimensions/P4"},{"id":"P6","name":"Release Hygiene","shortDescription":{"text":"Release Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/P6"},{"id":"PF2","name":"Allocation hygiene","shortDescription":{"text":"Allocation hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/PF2"},{"id":"X1","name":"Async correctness","shortDescription":{"text":"Async correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X1"},{"id":"X10","name":"Duplicated predicate","shortDescription":{"text":"Duplicated predicate"},"helpUri":"https://codehealth.canine.dev/dimensions/X10"},{"id":"X12","name":"Unreachable branch","shortDescription":{"text":"Unreachable branch"},"helpUri":"https://codehealth.canine.dev/dimensions/X12"},{"id":"X13","name":"Undrained process stream","shortDescription":{"text":"Undrained process stream"},"helpUri":"https://codehealth.canine.dev/dimensions/X13"},{"id":"X14","name":"Bypassable address classification","shortDescription":{"text":"Bypassable address classification"},"helpUri":"https://codehealth.canine.dev/dimensions/X14"},{"id":"X15","name":"Unvalidated length from an untrusted reader","shortDescription":{"text":"Unvalidated length from an untrusted reader"},"helpUri":"https://codehealth.canine.dev/dimensions/X15"},{"id":"X16","name":"Unfloored truncation loop","shortDescription":{"text":"Unfloored truncation loop"},"helpUri":"https://codehealth.canine.dev/dimensions/X16"},{"id":"X17","name":"Uncapped recursion over a caller-supplied document","shortDescription":{"text":"Uncapped recursion over a caller-supplied document"},"helpUri":"https://codehealth.canine.dev/dimensions/X17"},{"id":"X18","name":"Disposal-pattern correctness","shortDescription":{"text":"Disposal-pattern correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X18"},{"id":"X19","name":"Unrestored process-global state","shortDescription":{"text":"Unrestored process-global state"},"helpUri":"https://codehealth.canine.dev/dimensions/X19"},{"id":"X20","name":"Mistyped argument guard","shortDescription":{"text":"Mistyped argument guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X20"},{"id":"X21","name":"Side-effecting pattern guard","shortDescription":{"text":"Side-effecting pattern guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X21"},{"id":"X22","name":"Contradicted release guard","shortDescription":{"text":"Contradicted release guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X22"},{"id":"X23","name":"Unguarded diagnostic materialisation","shortDescription":{"text":"Unguarded diagnostic materialisation"},"helpUri":"https://codehealth.canine.dev/dimensions/X23"},{"id":"X24","name":"Document value interpolated into markup unescaped","shortDescription":{"text":"Document value interpolated into markup unescaped"},"helpUri":"https://codehealth.canine.dev/dimensions/X24"},{"id":"X25","name":"Inert configuration knob","shortDescription":{"text":"Inert configuration knob"},"helpUri":"https://codehealth.canine.dev/dimensions/X25"},{"id":"X26","name":"Unsynchronised callback handoff","shortDescription":{"text":"Unsynchronised callback handoff"},"helpUri":"https://codehealth.canine.dev/dimensions/X26"},{"id":"X27","name":"Collection changed while being enumerated","shortDescription":{"text":"Collection changed while being enumerated"},"helpUri":"https://codehealth.canine.dev/dimensions/X27"},{"id":"X28","name":"Index access outside its own emptiness guard","shortDescription":{"text":"Index access outside its own emptiness guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X28"},{"id":"X29","name":"Per-element action decided by a fixed element","shortDescription":{"text":"Per-element action decided by a fixed element"},"helpUri":"https://codehealth.canine.dev/dimensions/X29"},{"id":"X3","name":"Exception handling","shortDescription":{"text":"Exception handling"},"helpUri":"https://codehealth.canine.dev/dimensions/X3"},{"id":"X30","name":"Support guard that admits what it rejects","shortDescription":{"text":"Support guard that admits what it rejects"},"helpUri":"https://codehealth.canine.dev/dimensions/X30"},{"id":"X32","name":"Type resolved by simple name across every loaded assembly","shortDescription":{"text":"Type resolved by simple name across every loaded assembly"},"helpUri":"https://codehealth.canine.dev/dimensions/X32"},{"id":"X4","name":"Structured logging","shortDescription":{"text":"Structured logging"},"helpUri":"https://codehealth.canine.dev/dimensions/X4"},{"id":"X5","name":"Nullable reference types","shortDescription":{"text":"Nullable reference types"},"helpUri":"https://codehealth.canine.dev/dimensions/X5"},{"id":"X6","name":"Hand-rolled structured-format parsing","shortDescription":{"text":"Hand-rolled structured-format parsing"},"helpUri":"https://codehealth.canine.dev/dimensions/X6"},{"id":"X7","name":"Silent fallback defaults","shortDescription":{"text":"Silent fallback defaults"},"helpUri":"https://codehealth.canine.dev/dimensions/X7"},{"id":"X9","name":"Subsumed condition operand","shortDescription":{"text":"Subsumed condition operand"},"helpUri":"https://codehealth.canine.dev/dimensions/X9"}]}},"results":[{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.createConverterToAvroFromInternalRow (cyclomatic 28): SchemaConverters.createConverterToAvroFromInternalRow 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca9bb58dba2f131ac80fef41fd38055c0cbdeef8cbd51de2b6fdb7293a351db6"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.createConverterToSQL (cyclomatic 27): SchemaConverters.createConverterToSQL 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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"3d3bd4d375b93e04959868cc8d58c06e30f65cab5d315b7d6cc3bb039ed89823"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.createConverterToSQL (cyclomatic 27): SchemaConverters.createConverterToSQL 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"608c8e7240ec185a3fb28d0e917b6528a7a03df752c3ce3b5891b411a3c6001e"}},{"ruleId":"D1","level":"warning","message":{"text":"HBaseRelation.transverseFilterTree (cyclomatic 23): HBaseRelation.transverseFilterTree 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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"191e0a1892dd7fee23fdc012542917291ee036a65152171a2437d5d101f091ae"}},{"ruleId":"D1","level":"warning","message":{"text":"HBaseScan.traverseFilterTree (cyclomatic 21): HBaseScan.traverseFilterTree 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseScan.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1eca9c0a41ab5b720f15aa0390dbb234a2b6b7947b10eea193bcac6b3ee08f5"}},{"ruleId":"D1","level":"warning","message":{"text":"HBasePartitionReader.buildDynamicLogicExpression (cyclomatic 19): HBasePartitionReader.buildDynamicLogicExpression 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBasePartitionReader.scala"},"region":{"startLine":409}}}],"partialFingerprints":{"codehealthFindingId/v1":"b7fcfbc50c7eebf7cad066e72a228bb21cd8958cbb218a7df942c737e966d9a3"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.toSqlType (cyclomatic 18): SchemaConverters.toSqlType 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"f44a5d04a385785702a32a0f09a42b9c7826f691607485e5e084cb57c3ffacab"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.toSqlType (cyclomatic 18): SchemaConverters.toSqlType 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"47ac655f32983b06b0d8ca2a373c4aa196572fe135da5537542d2533c1c37acc"}},{"ruleId":"D1","level":"warning","message":{"text":"HBaseScanBuilder.pushFilters (cyclomatic 18): HBaseScanBuilder.pushFilters 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseScanBuilder.scala"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c575459c29ac7f9faa3b2762d4bd721baa25aaf26be693945b7f8b510e47372"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.createConverterToAvro (cyclomatic 17): SchemaConverters.createConverterToAvro 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"fbfb4a8bd67008747b7e112d9a992f8cae9085ea801347ab018dd8c529417520"}},{"ruleId":"D1","level":"warning","message":{"text":"SchemaConverters.createConverterToAvro (cyclomatic 17): SchemaConverters.createConverterToAvro 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":345}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d16442a5ce7e95b9b4548f09e65c6b581083038e7c33161abd82b6e0477ccb7"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.createConverterToAvroFromInternalRow (cognitive 64): SchemaConverters.createConverterToAvroFromInternalRow has cognitive complexity 64 (threshold 15). Drivers by points: if/else 28 (49 pts), loops 3 (9 pts), match/switch 4 (6 pts) (nesting depth added 29). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident. This file is where this pass\u0027s cognitive complexity CONCENTRATES: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala holds 3 of the 19 methods over the threshold \u2014 including the worst \u2014 and 88 of the 187 points over it (47%), 2.3\u00D7 the next-largest file (spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala at 39). No single row can show this, because each is measured only against the threshold: reducing this one file moves this dimension further than any other file in the repository."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c421b133edc90f6355de839eba760cda9b45b1d651d49b3b0efadebf7a0ea46"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.createConverterToSQL (cognitive 45): SchemaConverters.createConverterToSQL has cognitive complexity 45 (threshold 15). Drivers by points: if/else 18 (27 pts), match/switch 4 (12 pts), error handling 1 (3 pts), loops 1 (3 pts) (nesting depth added 21). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef09e6c8932e0533cf2ba2d1959b900a5569b7754a95684053459f9f66a85247"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.createConverterToSQL (cognitive 45): SchemaConverters.createConverterToSQL has cognitive complexity 45 (threshold 15). Drivers by points: if/else 18 (27 pts), match/switch 4 (12 pts), error handling 1 (3 pts), loops 1 (3 pts) (nesting depth added 21). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident. This file is where this pass\u0027s cognitive complexity CONCENTRATES: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala holds 3 of the 19 methods over the threshold \u2014 including the worst \u2014 and 88 of the 187 points over it (47%), 2.3\u00D7 the next-largest file (spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala at 39). No single row can show this, because each is measured only against the threshold: reducing this one file moves this dimension further than any other file in the repository."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"de3c8a63763b9f0d3254e3579f823e074ff22e4913f32fd187c1e7883f2f3261"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseRelation.transverseFilterTree (cognitive 32): HBaseRelation.transverseFilterTree has cognitive complexity 32 (threshold 15). Drivers by points: if/else 13 (31 pts), match/switch 1 (nesting depth added 18). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":511}}}],"partialFingerprints":{"codehealthFindingId/v1":"8c9bdb8f2b0288b0f25bebf8be8400435dfcf4ce09ef7d830198bb65f25c0c14"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.createConverterToAvro (cognitive 24): SchemaConverters.createConverterToAvro has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (15 pts), loops 2 (6 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":346}}}],"partialFingerprints":{"codehealthFindingId/v1":"90b6bebcb874d06b7edae8ade42ff2e855a841bd31c16f32a9a6b1d91fe2064f"}},{"ruleId":"D2","level":"warning","message":{"text":"SchemaConverters.createConverterToAvro (cognitive 24): SchemaConverters.createConverterToAvro has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (15 pts), loops 2 (6 pts), match/switch 2 (3 pts) (nesting depth added 10). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident. This file is where this pass\u0027s cognitive complexity CONCENTRATES: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala holds 3 of the 19 methods over the threshold \u2014 including the worst \u2014 and 88 of the 187 points over it (47%), 2.3\u00D7 the next-largest file (spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala at 39). No single row can show this, because each is measured only against the threshold: reducing this one file moves this dimension further than any other file in the repository."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":345}}}],"partialFingerprints":{"codehealthFindingId/v1":"547d4b81f1a541cffee5c70932529e467247049569b615fcd118fd6c2f396978"}},{"ruleId":"D2","level":"warning","message":{"text":"HBasePartitionReader.buildDynamicLogicExpression (cognitive 23): HBasePartitionReader.buildDynamicLogicExpression has cognitive complexity 23 (threshold 15). Drivers by points: if/else 16 (22 pts), match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBasePartitionReader.scala"},"region":{"startLine":409}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ad8d6338e2b7a99abcc0f4dd36de8dddfb8bf4b3f29af8cb21be89c8c6069d6"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseConnectionKey.equals (cognitive 22): HBaseConnectionKey.equals has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 4, loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":224}}}],"partialFingerprints":{"codehealthFindingId/v1":"2479cf0a4b90135ebe98cb763bc10143b66e742dfc7d6c903674ba5fbd2ebfbd"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseConnectionKey.equals (cognitive 22): HBaseConnectionKey.equals has cognitive complexity 22 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 4, loops 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":220}}}],"partialFingerprints":{"codehealthFindingId/v1":"48ac188b75872853af184d7ecade3dd55c4d7364db48df5b6255d19eaaac7313"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseScan.traverseFilterTree (cognitive 20): HBaseScan.traverseFilterTree has cognitive complexity 20 (threshold 15). Drivers by points: if/else 7 (13 pts), boolean chains 6, 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseScan.scala"},"region":{"startLine":80}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f6e22d382a7cc44f139603350200ba3a4f78573e83bcedbe954cf23a99ccc15"}},{"ruleId":"D2","level":"warning","message":{"text":"KafkaProxy.checkForOrCreateReplicationPeer (cognitive 19): KafkaProxy.checkForOrCreateReplicationPeer has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (15 pts), error handling 2 (3 pts), loops 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaProxy.java"},"region":{"startLine":285}}}],"partialFingerprints":{"codehealthFindingId/v1":"80bd61b8021151e74a7fe3fdda415bc7e2c2de41c8be02978a79fe17189ab512"}},{"ruleId":"D2","level":"warning","message":{"text":"DynamicLogicExpressionBuilder.build (cognitive 18): DynamicLogicExpressionBuilder.build has cognitive complexity 18 (threshold 15). Drivers by points: if/else 16 (18 pts) (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/hbase-spark-pushdown/src/main/scala/org/apache/hadoop/hbase/spark/DynamicLogicExpression.scala"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc4b3dad511dc96f2c353e64c9bed37cf85f3a4f74f6bb15cc1dc6379e104db4"}},{"ruleId":"D2","level":"warning","message":{"text":"NaiveEncoder.ranges (cognitive 17): NaiveEncoder.ranges has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"25fa69334a85c03b5b70854baa8431efb117a8a73e5f9a7c85d9cf9c37af48ca"}},{"ruleId":"D2","level":"warning","message":{"text":"NaiveEncoder.ranges (cognitive 17): NaiveEncoder.ranges has cognitive complexity 17 (threshold 15). Drivers by points: if/else 11 (16 pts), match/switch 1 (nesting depth added 5). The drivers above price the dispatch low by construction \u2014 a dispatch is charged once however many cases it lists, while each branch inside an arm is charged in full \u2014 so most of this count is what the case bodies hold, and the arms are where it can be reduced. To reduce it, keep the dispatch but shrink the arms: move each non-trivial case body into its own named function (or onto the value being matched) so the dispatch reads one line per case, and group related cases into a sub-dispatch. Keep every case explicit, and make the behaviour for cases you do not list a deliberate choice rather than an accident."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bebe4eceba31c41ca6fbb4d37010e4bb8a50d66307b9d8ab01e502bb4e2ac87"}},{"ruleId":"D2","level":"warning","message":{"text":"RowKeyFilter.mergeIntersect (cognitive 16): RowKeyFilter.mergeIntersect has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10 (15 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":1215}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce9d46e3f4e11d5b605740f0f4178de00a65bf1b275b2ba2f9cf5d4a350567cd"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseContext.bulkLoadThinRows (cognitive 16): HBaseContext.bulkLoadThinRows has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 3 (6 pts), boolean chains 1, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":721}}}],"partialFingerprints":{"codehealthFindingId/v1":"54bd5e9beb768c1d3f398286aacfd88f5de152c42875c106a4a4ea93cc06d975"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseContext.writeValueToHFile (cognitive 16): HBaseContext.writeValueToHFile has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":943}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9c90d2a6c46a2f210d2e11b06099d58c65fe9725386ae339c14f7e9d645746a"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseContext.bulkLoadThinRows (cognitive 16): HBaseContext.bulkLoadThinRows has cognitive complexity 16 (threshold 15). Drivers by points: if/else 5 (8 pts), loops 3 (6 pts), boolean chains 1, match/switch 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":541}}}],"partialFingerprints":{"codehealthFindingId/v1":"63c3bbcacd6efe552656841dfd58b3936c79f7a84d496e4f2b1942bb66e8b3d5"}},{"ruleId":"D2","level":"warning","message":{"text":"HBaseContext.writeValueToHFile (cognitive 16): HBaseContext.writeValueToHFile has cognitive complexity 16 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":763}}}],"partialFingerprints":{"codehealthFindingId/v1":"9968ccdac2546f26654a19878a77b3e44b0dc7ddd24eaa839b2d98897f7293d1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/DefaultSource.scala: FileTooLong \u2014 778 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 278 over it, 1.56\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b23062dc15fcd07d1f891ec95657994cb6d8bdc532c8dc1566b4479a27176f77"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: HBaseContext: ClassTooLong \u2014 512 significant lines (blank, comment-only and punctuation-only lines excluded), 25 methods. The bar is 400 significant lines; this is 112 over it, 1.28\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"a64b7193b23d54529f155f1ae8516debd17fd7b64430785e00248b091907f6d3"}},{"ruleId":"D3","level":"warning","message":{"text":"ClassTooLong: HBaseContext: ClassTooLong \u2014 484 significant lines (blank, comment-only and punctuation-only lines excluded), 20 methods. The bar is 400 significant lines; this is 84 over it, 1.21\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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"f66dabd27afabd02b52ea511182dcca58a8e2f3550416b83bfddb1bb225beef8"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/HBaseContext.scala: FileTooLong \u2014 547 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: HBaseContext (60-1113). The bar is 500 significant lines; this is 47 over it, 1.09\u00D7 the bar. Moving the declarations that sit BESIDE it into sibling files will not shorten this file. Extract from INSIDE that declaration instead: lift each cohesive group of its body \u2014 the parts that share the same inputs and are named together \u2014 into its own unit in a sibling file, and have the original call them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"16272599d58d271b775a2e133fb3a7d3fc5b058de9a5495dc49ca08001751441"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: spark/HBaseContext.scala: FileTooLong \u2014 517 significant lines (blank, comment-only and punctuation-only lines excluded), about 94% of them inside a single declaration: HBaseContext (56-946). The bar is 500 significant lines; this is 17 over it, 1.03\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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"90c122063962e1f3692364fbf00df79e53acac6f69cd3d79097b31c8592f8b3a"}},{"ruleId":"D3","level":"warning","message":{"text":"MethodTooLong: SchemaConverters.createConverterToAvroFromInternalRow: MethodTooLong \u2014 createConverterToAvroFromInternalRow runs 102 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 2 over it, 1.02\u00D7 the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body \u2014 the runs of statements that work on the same values and would earn the same name \u2014 into its own named unit, and have this one call them in order."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"883b888378c1f32b723a5ae047d96bde28dfa791f43cc2bc9c6c4bb2e4cd5b47"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 50 shared lines): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:598-687 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:729-854 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:418-507 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:549-674 \u2014 These 4 members are variants of one another: a block of 50 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":598}}}],"partialFingerprints":{"codehealthFindingId/v1":"7de38bbdcd81d3c1eeb4c57cc61206ef973a6d10dcd53dd350223d43b2b580e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 29 shared lines): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:35-83 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:35-87 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala:36-86 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseForeachPartitionExample.scala:36-92 \u2014 These 4 members are variants of one another: a block of 29 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"1043a03028268c386889c5f792ae6003defa450223a4b3055c10c8e5cee596dc"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (63 shared lines): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:153-247 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:153-246 \u2014 These two members are variants of one another: 63 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":153}}}],"partialFingerprints":{"codehealthFindingId/v1":"147ad8ff63507c7b4d6e35e2e55b353a182bfe6e75ebcf84dc93ea2a5767209b"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (36 shared lines): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:66-121 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:68-122 \u2014 These two members are variants of one another: 36 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":66}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdf39a33b174a3500d151e8742210d1e41605ca5b90f373a443c9cc91732f6a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Edited copy of a member (26 corresponding lines): spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java:43-73 | spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkGetExample.java:46-76 \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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"552d248aa17e42f986a0695cc01a440abff9fe9c69c781d4caf58d639bd91c35"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala:35-66 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala:37-99 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkDeleteExample.scala:36-69 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkGetExample.scala:38-100 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseMapPartitionExample.scala:36-98 \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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"902868af36b57bb485102cc4c92e7c081c90eb2e784601d0c6c9c66c404f9a20"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (110 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:82-191 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:65-174 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 193 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":82}}}],"partialFingerprints":{"codehealthFindingId/v1":"78d0b914aa46c04094e5a2b09287e7a6a05d899e14532bf4d74b8ac8f7beb5cb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (83 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:605-687 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:425-507 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:605\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":605}}}],"partialFingerprints":{"codehealthFindingId/v1":"26e791d1f1238c04bd154add3372f887cfde5d1a46ee1f6c1aff000f9c422a3f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (70 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:964-1033 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:784-853 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:964\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":964}}}],"partialFingerprints":{"codehealthFindingId/v1":"479705b252d6b12074e8cdbb1fce8dc5f6e36368941527afa1816d54238ec5ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (68 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:787-854 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:607-674 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:787\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":787}}}],"partialFingerprints":{"codehealthFindingId/v1":"3cdebf187f1aa00c55cabb74ed058a1fd4f6f251a86985fa377b1a320b2570e4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (68 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:350-417 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:349-416 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":350}}}],"partialFingerprints":{"codehealthFindingId/v1":"f063309e4b1ac1dfb6e7f5308ab02ce725b0dd7131a6af6d481f297407859db2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (50 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:736-785 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:556-605 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:736\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"0de58e4daa99c1b5932992f3c51b8679a4825a6c2d1b004ace624f8b58f4d8a6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (48 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:874-921 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:694-741 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":874}}}],"partialFingerprints":{"codehealthFindingId/v1":"278dd9d6ebe94789f5f1a661c31fdaa116edbc0088bd93a8e170952162e3fe26"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (46 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:219-264 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:202-247 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 193 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:219\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a08eb1292b5b43de20171eb8c617085e6b5baf20e525a78283845189150351e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (30\u201345 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:55-99 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:50-79 \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:55\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"aac7f27ea843a6e3174be73952e9c3091219d060980e5b2a772b63f0c26213ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (42 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:832-873 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:1102-1143 \u2014 both copies are in the same file, so extract the block 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":832}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbf3159c784a72d2912d5284b84f974bdfcb0d9d2d57d2cd0039bd07e532e73e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (40 lines \u00D7 2): spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala:68-107 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseStreamingWrite.scala:71-110 \u2014 before extracting anything, compare \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseStreamingWrite.scala\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"a36387d2622b1497e27bfc0dd68c40861e66c0d03b00d78878f347835820b211"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (33 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:1148-1180 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:151-183 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":1148}}}],"partialFingerprints":{"codehealthFindingId/v1":"96bfffb1a5ef2ee56efebf6e2100be045c221d4dc036d93fc77450c6dbefb13b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (32 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:258-289 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:257-288 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"1abeaa0031d664e4413f9f75892ce2c7bd4d5c814520584619e791ed9c0ceb7e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (32 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:301-332 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:300-331 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":301}}}],"partialFingerprints":{"codehealthFindingId/v1":"392f760a2f37f5b776453bb65cd85a3ed465fd9a200b26d237a37615597bf1f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:225-255 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:221-251 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 93 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"c19e21ed6864c4681127abd612447b2c6d8667829e224538682fd234ee864599"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala:69-99 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkGetExample.scala:70-100 \u2014 \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkGetExample.scala\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 2 separate duplicated blocks between them, totalling at least 50 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala:69\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f8c8a7c1f432dd7dcc1df073afd7862fb46bfd49ad8318b1434f19f20a39839"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27\u201329 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:163-191 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:156-182 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"2df980efdb36e59cab89d3bed1807fabe42fa38b1574c72a6f22bd6fe1aaca3b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27\u201329 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:274-302 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:257-283 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 193 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"33c661d8fbfb091dd77f5e1e61f7451fb9a7ee93c1dad28ec5d599fec6894363"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:91-119 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:89-117 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 72 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d399ee7dec4dc9592ea05b200129db2910ebd06384ab034f4ec197aa8817b0e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (26 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:1078-1103 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:898-923 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":1078}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d7c9e19a8d752eb4480d3a1d141bb1450af28d9637f76937117385cae7c0276"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 4): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:37-60 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:38-61 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala:38-61 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseForeachPartitionExample.scala:38-61 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:37\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":37}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a8687cd12aecd575c274c6ad97c6210c5c47a05c07a281b19a3b7f52c2be6b9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (22\u201323 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:320-342 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:313-334 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:320\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":320}}}],"partialFingerprints":{"codehealthFindingId/v1":"65c24b4a79becf645e3cdd52928d556e7c1777844f933acbac54a0f69241025b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:360-382 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:350-372 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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 \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:350\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"f49c6da8202602895e9386c99785d8bc440b07820a55d70bba4c7ad65ed1bc13"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201323 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:154-176 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:154-174 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:154\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"33d05ef246decef1ed86047f1e38ea7b4835e4851785e191fd8b6990bedbf0ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:225-247 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:224-246 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:225\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":225}}}],"partialFingerprints":{"codehealthFindingId/v1":"af4ce610ce08d6d635bcfce50c123988e204d6afc3ef58bb89de9ced9c768e30"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201322 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:731-752 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:85-104 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":731}}}],"partialFingerprints":{"codehealthFindingId/v1":"055eceee3f6fe858dfa7280b8779402b28daf9d5fe4f6c7ff79090bbde5f285c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 4): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:615-635 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:747-767 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:435-455 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:567-587 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:746\u0060 calls \u0060currentTimeMillis\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:614\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":615}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb31bdd0c3ed43deba2599471283bab44924034cd10ed9ac8fc540d355dae801"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:91-111 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:88-108 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 93 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad5baf9f5194846a1f34f30dcb1f7c6cf614b3cf3594f9c631a0eda2b572bc46"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:933-952 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:1272-1291 \u2014 both copies are in the same file, so extract the block 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":933}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c639db1f9fcbbbb8fd07e11ff47d128303f2c4bac87104d0515778aad115092"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201320 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:122-141 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:101-115 \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala:122\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala"},"region":{"startLine":122}}}],"partialFingerprints":{"codehealthFindingId/v1":"a953dff8361d74e9e2ba614b8a2ab5b385a848e69fc1ac062fc562d2017f171b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17\u201319 lines \u00D7 5): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala:36-52 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala:38-56 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkDeleteExample.scala:37-53 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkGetExample.scala:39-57 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseMapPartitionExample.scala:37-55 \u2014 \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkDeleteExample.scala\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 1 separate duplicated blocks between them, totalling at least 19 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala:36\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala:57\u0060 calls \u0060toBytes\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala:53\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkDeleteExample.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"4989ebec0407e9683bc364c46c3bad249c274d2e3e84b959a8c8e47dca5cbd55"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:665-682 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:45-62 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":665}}}],"partialFingerprints":{"codehealthFindingId/v1":"9feb329121839047b10e02bcd3d7b52954459dfb3d8812482a160143c18959a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:691-708 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:65-82 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":691}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b7807268dab53d3baf764f0deba667effae08f353a1515a6da62ff3ced47f2d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201317 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:131-147 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:132-147 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":131}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a4af52050a17ff9854a8b19b3c2497094cad7d3ab17e758925abaf72169ded0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala:45-60 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala:45-60 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.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. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala:45\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, \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala:44\u0060 calls \u0060getPartition\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala:43\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/BulkLoadPartitioner.scala"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3b86507703363331379580b8f9ae54a051749620892b0b740d447da93b3fde8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 4): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:637-651 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:769-783 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:457-471 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:589-603 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:637\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"76a18972d8745864732dd3b333ab58580317dd155c3c01e56f1fc6aa79e19900"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:266-280 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:276-290 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:266\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":266}}}],"partialFingerprints":{"codehealthFindingId/v1":"0dc0226f18aff9f1944a959d2a4ad001d82c921080923b7cb16d2b2c6ee830f9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:36-50 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:35-49 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 72 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:36\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5839f8bbd90d2a24436edb84a6eec11884b2ffd3c2df9e8f9c07f42d1880807"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 4): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:599-612 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:730-743 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:419-432 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:550-563 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:599\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:746\u0060 calls \u0060currentTimeMillis\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:615\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":599}}}],"partialFingerprints":{"codehealthFindingId/v1":"941bf107e07dfa91b9438d73b7370f18dfc75bc8650c902d308aa15f08405c59"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:882-895 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:1192-1205 \u2014 both copies are in the same file, so extract the block 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":882}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ffe5b9889c4c581bb1fe71250ee5fb249a697784e6537cf1f33185b69b8f55c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:210-222 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:206-218 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 93 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"1624b29e754dcd9df8a82a1814a6f8421f0f40ae7a3bb92c72c5cf591d7fff59"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:87-99 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:87-99 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:87\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d0a079a217b70f5306cf696a40ab3091e07af4e41a9f5fa6a4e0b8a1afb354a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:232-243 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.scala:118-129 \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:232\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd60e1677ee2d1023d2e1634b591b933b958cf49d251f5279b5ff78e098c3b5d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:1050-1061 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:870-881 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":1050}}}],"partialFingerprints":{"codehealthFindingId/v1":"931b11abfb0345293d6394b86e00365423437378c03698ae0e9415ac08da9b92"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:67-78 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:69-80 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala: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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"762007c5329abb8026d57edb3c23b1f9409cf228edf429ba8aa8491a94c1390e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11\u201312 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:52-63 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:51-61 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 72 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:52\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":52}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d5185b16d61e52b2ee0205907cbb75b81c2097578bd20b4ad068ce24deb5c1b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/DataType.scala:85-96 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/HBaseSource.scala:75-86 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/DataType.scala"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"20d5ee8fa67e5630e6fcf06c19bb17354400e694059ffab0ca1d3bd29d50ef3a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala:46-56 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala:46-56 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala\u0060 as WHOLE FILES: 98% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 1 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. Each matched range is the entire body of the declaration above it, so the region is already a complete unit: move that whole declaration to the shared location and have each site call it, rather than lifting the lines out of their bodies. Any \u0060return\u0060 inside it is the body\u0027s own exit and keeps its meaning in the moved unit."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"0c48d4882e408d145d9167b61bf18615a6d1fc6a0693a0e685f84de7cfc311f7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:306-316 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:300-310 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. The two sit in different directories, so one cannot simply be deleted in favour of the other while both are reached separately: hoist the shared part into a location both already depend on and have each file call it, and retire whichever file turns out to have no caller of its own left. Extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":306}}}],"partialFingerprints":{"codehealthFindingId/v1":"a14954bf9c110a2c41ac5617d60aea62b908fdcca6255183cdb71f1c0716897e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:111-121 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:112-122 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:111\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"364c4eb016afcbdbfcbe11c91e1afa7920072f1abb676a34aecd0f67ce2492a2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:187-197 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:185-195 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:187\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":187}}}],"partialFingerprints":{"codehealthFindingId/v1":"77e9d8c1d0c00a5472c0861934fbb78a17451656a128fc911e65b7718777a8c7"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:429-438 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:568-577 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala: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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":429}}}],"partialFingerprints":{"codehealthFindingId/v1":"fdc7d143cf850a09f9961d70d1392cf70ffd85ec9be458f0fdf8e17ff7680682"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:786-794 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:121-128 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":786}}}],"partialFingerprints":{"codehealthFindingId/v1":"4797da77e4fc0a2c73fa08502a5f3f0d8e01eb7c3b0fd488598ab528abde51c6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:67-75 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:65-73 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 72 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala: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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"aeca4c2222f362349e7389de71cd54f0417866bcb594b9830f7f03e9d8217d7b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:548-555 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:566-573 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:548\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":548}}}],"partialFingerprints":{"codehealthFindingId/v1":"73fc6ff8dbdd05a1fadff73660efc1956120b9ca112958e66fbdabb1cc8e657a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:248-255 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:259-265 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":248}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee6bb77caf6b24360cad9164687e2ece66fb52aede1800c7d152361798b34364"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:256-263 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:266-273 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:256\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"44e826826f8c79ea2b6341caedc79595d3c909cfc3a328ddcc2129eb1f598b06"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:178-185 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala:176-183 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 260 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala:178\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"49f63387d9fce1443db33c2da0bf68724ba673a9787be733f1ce5e05c38a5ffb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 3): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:65-71 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala:66-72 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseForeachPartitionExample.scala:66-72 \u2014 \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 3 separate duplicated blocks between them, totalling at least 36 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:65\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"19943e225cfb287cf144e5fdd7c0821d55ce24cf58134c724ced5502da0240a3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:294-300 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBasePartitionReader.scala:326-332 \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:294\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":294}}}],"partialFingerprints":{"codehealthFindingId/v1":"846401b2cf439c7ab38e3273c41639155234010df328d52707ac53918d03b182"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:81-87 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:79-85 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 72 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala:81\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"871b79fe898badc908c8fa04ff06534519e302c66a18f2b90b5dbae8a28371ce"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:543-549 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseScan.scala:92-97 \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:543\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":543}}}],"partialFingerprints":{"codehealthFindingId/v1":"4e025f79bdf318c34bfa19ebb722b291836a1331b4243763d7ad79446d5d2da0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:561-567 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseScan.scala:104-109 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:561\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":561}}}],"partialFingerprints":{"codehealthFindingId/v1":"a8370b00292a7b2557de4d9f0b46b820335eaa92f003c0e8bc37020aa954dc1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:582-587 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:596-601 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:582\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":582}}}],"partialFingerprints":{"codehealthFindingId/v1":"0455c5461ff39fe70110cdf47cc88462e25c82fdcadbae6c7292c36cd7b922aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:71-76 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:74-79 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:71\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:72\u0060 calls \u0060currentTimeMillis\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5a8997a68dfa8c42a8094303ff030f2c31691709c43848689e2a72f4ff68708"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 4): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:65-69 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:66-70 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala:66-70 | spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseForeachPartitionExample.scala:66-70 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 35 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:65\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala:72\u0060 calls \u0060currentTimeMillis\u0060 and \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala:71\u0060 does not \u2014 after which the two agree again for 4 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"31e26d5345ea146e1bef71d4d1f79883e0cb243b1794c76e70655c2396075e7e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/ByteArrayWrapper.scala:34-47 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/ByteArrayWrapper.scala:34-47 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/ByteArrayWrapper.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/ByteArrayWrapper.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/ByteArrayWrapper.scala"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0ec89e9642bdcf9fae44f2c1dad9758fd70288f07a3a805eb99972cf3a8e7fb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/KeyFamilyQualifier.scala:40-50 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/KeyFamilyQualifier.scala:40-50 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/KeyFamilyQualifier.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/KeyFamilyQualifier.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/KeyFamilyQualifier.scala"},"region":{"startLine":40}}}],"partialFingerprints":{"codehealthFindingId/v1":"2425d5556bf63cee955c37c9dca39648719682804f3b86d3e628dbde62b5ef1a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerializableConfiguration.scala:27-44 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerializableConfiguration.scala:27-44 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerializableConfiguration.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerializableConfiguration.scala\u0060 as WHOLE FILES: 97% 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerializableConfiguration.scala"},"region":{"startLine":27}}}],"partialFingerprints":{"codehealthFindingId/v1":"cbe26a0611f7069a2bf05dda045254f1a32518ad82336116938e72d45e92b2ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala:775-780 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala:113-118 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.scala\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 106 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":775}}}],"partialFingerprints":{"codehealthFindingId/v1":"757960791a38c56ee1294eda537f07657fa65e056fcc4cac6847625d478d5f8b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:75-88 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:72-85 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 93 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"4516b7d26c76f5ee1d261e4f5da11074175196e31c2f7bc4137325fba3d0eb58"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:114-127 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala:111-124 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 93 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdb236fb552e3b3258381ed37d8e9d143a30921a55b2e86da0a842dda22443f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:360-365 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:179-183 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:360\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":360}}}],"partialFingerprints":{"codehealthFindingId/v1":"98ca62c0e7c485c7316268bcd244a56c237fc4366996d33184a8808f14f59bec"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:497-506 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:299-308 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala\u0060 as WHOLE FILES: this scan already matched 12 separate duplicated blocks between them, totalling at least 423 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala:497\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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":497}}}],"partialFingerprints":{"codehealthFindingId/v1":"17428fe9c3444321ffa07eddb683fc36cb8d952bbe9eeab24fbbea5249e80367"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/Logging.scala:96-104 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/Logging.scala:82-90 \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":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/Logging.scala"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"7112891339534ef299a868e0706ee434d0354d8249382edfdfe18b8dfd49ead5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:104-108 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:103-107 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"07e217fc173b1a102a26a0baa208a9086e34aa194cf4ce2074fada26483bf0f2"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:118-127 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala:115-121 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 132 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":118}}}],"partialFingerprints":{"codehealthFindingId/v1":"4c76b71d288127eab58561c11733933833c1d80ee749220f02c8e2aa6866799e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:193-200 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala:176-183 \u2014 before extracting anything, compare \u0060spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala\u0060 as WHOLE FILES: this scan already matched 4 separate duplicated blocks between them, totalling at least 193 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala"},"region":{"startLine":193}}}],"partialFingerprints":{"codehealthFindingId/v1":"3af1bc88ab5c526a1c52c08026b80f3466f7388798926c0781b8cbe927003d7e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatch.scala:108-112 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala:52-56 | spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseStreamingWrite.scala:55-59 \u2014 before extracting anything, compare \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala\u0060 and \u0060spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseStreamingWrite.scala\u0060 as WHOLE FILES: 82% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 2 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatch.scala"},"region":{"startLine":108}}}],"partialFingerprints":{"codehealthFindingId/v1":"da7c4cb6c9e51b36211c1893a18d3c49a4be07539432a490f320f0ce09f0a0b6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15\u201318 lines \u00D7 3): spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java:49-66 | spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkGetExample.java:52-69 | spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseMapGetPutExample.java:59-73 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java:49\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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"60bf900eeebee6746b88264c35e37a91947e5eff7f8365455b08919fac85afa9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkLoadExample.java:70-79 | spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkPutExample.java:58-67 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkLoadExample.java"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b4acb9c121c2cf070cb6d0970023490399e1a6396721c6e2da63462aec1af1f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkPutExample.java:81-85 | spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseStreamingBulkPutExample.java:80-84 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkPutExample.java:81\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. 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":"spark/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkPutExample.java"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"e47ca3d5572094a1d87228d7a5060439c0a4724dd0d12ff1a3298b46e2139f4c"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala changed 2 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 28 in SchemaConverters.createConverterToAvroFromInternalRow at line 428. 1 of those changes was a fix/bug commit, and the other 1 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 2026-08-07..2026-11-05, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-07 11:27:36 \u002B00:00\u0027 --until=\u00272026-11-05 11:27:36 \u002B00:00\u0027 --full-history --no-merges -- spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"476b15c70045678910e59060b01e0f928d865d95586507dca8d666a24670e633"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.scala: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.scala changed 3 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 15 in HBaseDataWriter.getValueBytes at line 140. 2 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 2026-08-07..2026-11-05, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-08-07 11:27:36 \u002B00:00\u0027 --until=\u00272026-11-05 11:27:36 \u002B00:00\u0027 --full-history --no-merges -- spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.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":"spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.scala"},"region":{"startLine":140}}}],"partialFingerprints":{"codehealthFindingId/v1":"40f42a6d76d4f9b717f5bb2c19268c283389eee2b7bc9a5e1efb3e72193a6554"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #1: If anonymized user #1 becomes unavailable, 12 significant file(s) lose their only recent owner: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/SchemaConverters.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala, spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/NaiveEncoder.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseStreamingWrite.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseBatchWrite.scala (\u002B4 more). Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"025cc976b3c735e198caeb96e9dcb86573bd4c3b4dcf42db6be8681b69772a3e"}},{"ruleId":"D16","level":"note","message":{"text":"Further sole-owners (lower concentration): 1 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 (13 single-owned of 66 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; 66 of the 97 production source files in this repository met that bar). They are anonymized user #2 (1 file(s)) \u2014 spread or document their files in the same way, at lower priority than the named off-boarding risks above. The files folded here: spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6eac528f2429e724e1a97ed868f79eefbcf1888dab4af9a9e673429369bb5b2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add avro 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"fda0cad80b2cd8d66cbe1fd349afc047873ef7a688f957450fca90165e26c96c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: There is no need to deprecate since this is the first release. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"45b2f1cd78477b8a0a22d2b32160e065b9ea5f96de130c7b7f0bbc5e3ed3d14c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":439}}}],"partialFingerprints":{"codehealthFindingId/v1":"b9a44b7a93420c2c007a9874e7ce160ca95b83665720f3132ae6569107976d26"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This is not really used in code. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerDes.scala"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"3929fdbeac124d03d41921df920bf3abf38abee1c704bd64c7fa789c07f522f1"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: This is not really used in code. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060// REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SerDes.scala"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a70f38aef4ce36d904a5f0d49d7a29aeb12aa26ad13054bb84c9b5d8299c3b5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: SparkSqlSerializer.deserialize[Any](src) \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"898cd86b8e2584901b54a4f0fb64fa5f796da82b0264c6d9fa3420d018f3563c"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: // TODO: add @InterfaceAudience.Private if https://issues.scala-lang.org/browse/SI-3600 is resolved"},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/package.scala"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"978c97700a08f664586dd020ae31e5da7e0b8ffee61c5a8558ce8e54126722e3"}},{"ruleId":"D19","level":"note","message":{"text":"Documentation: no build, run or usage example: the repository holds project manifests and neither \u0060README.md\u0060 nor the documents it links hold a code block or a command. Show the command that builds or runs it, or a usage snippet."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"README.md"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c33a5992d4bd6ac1ea4b853ae69753fcd7e0410099c58731c86be53325ba8c96"}},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"77820b9deaf6ead917e31506aab31fbe29c3bad181452b04c1ff9185e6d39e9b"},"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":"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":"f4c06ae68e39c603b0cba88bebc8617fadc8028cc0e99e040d9bcdb34bc9ba35"},"properties":{"dependency":{"package":"com.google.protobuf:protobuf-java","version":"2.5.0","advisory":"[GHSA redacted]","aliases":["[CVE redacted]","[CVE redacted]","[CVE redacted]","[GHSA redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D30","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"e313bbddce504f9ec8228383aa1ebb5f91a6aea94138ba89ef5f1d87fe96ecfb"},"properties":{"dependency":{"package":"org.apache.kafka:kafka-clients","version":"2.0.0","advisory":"[GHSA redacted]","aliases":["BIT-kafka-2021-38153","BIT-kafka-2026-33558","[CVE redacted]","[CVE redacted]","[GHSA redacted]"],"reachability":{"kind":"unknown"}}}},{"ruleId":"D31","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f05942f3238e9f9ce720c9851bd600aa7818b25647503c19d03ee61bfa42cbce"}},{"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":"ff1df3fe364557a33ea19e46e29a8d6af6f90f4bc1c23367305041d84ec6723d"},"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":"Concentrated knowledge decay: 41 of 66 significant files have no living knowledge, while the repository is still being changed at a low rate (11 commit(s) in the last 90 days) \u2014 so this is one repo-wide knowledge-decay state, not 41 separate risks. Counted over 66 of the 97 production source files in this repository: the rest are under the ~2,400-byte size floor this dimension measures over. The code moved on without the people who understood these files: document them or schedule a read-through before the next change lands in them."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"008bd8d3156a7f5206da709f59f1f87af76671c6b9becea72c8c9cffbcbd4f8e"}},{"ruleId":"D34","level":"note","message":{"text":"Most significant orphaned file: One of the orphaned files carrying the most lost knowledge \u2014 ranked by size weighted by the file\u0027s role in the codebase, the same weighting behind the score above, so core code outranks equally large plumbing. A reasonable place to start a read-through before the aggregate risk above bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4387aef424c47ed4c730634855e2f22c5f8d40b058b46c7de1a6dc75364227a4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/SchemaConverters.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c4e580b0e4d0a4277acd96a3ec2ff6c31d90f306da2594551048aaa44cec418"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/JavaHBaseContext.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"70fa81fd856704be510db0d0a491f4271affad4f6ad2c41a7d04968a4fd45083"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaProxy.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5336aab1f73fce43de8a38f20a3e418618303fa1d271c457192ed37b9885ad88"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8742bd8a9466a6ab4137623c5db1a2be3f360831dce2ea71a49fb893a050289f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark-pushdown/src/main/scala/org/apache/hadoop/hbase/spark/DynamicLogicExpression.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"797500b72d62818798ca68000c092f896fd94876585d768d1897c7b554f95f25"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseRDDFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"869902c98d5c7564db83f13f57f861574ca56be421c044558aed723fd2ab9c9c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark-pushdown/src/main/java/org/apache/hadoop/hbase/spark/SparkSQLPushDownFilter.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3148c07e3199bd4ec65700667ac51f06e72a06b3e8ceac0d33dd64cb44a4684b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f997998843ffba24bd23bd0efd4aaa99f70f0319740f6afe5e171d44af384eb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/TopicRoutingRules.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cdb5e9a43f9b06c93c9044f2044051c59be5e08b3c9468e588a41c29c3b444be"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseDStreamFunctions.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a0f8caf9028e6f79d5ce36b3c57fef4a7c587e6d6f50c726629d81143f45196"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaTableForBridge.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e41b2695ec0a2d589b71eb12eb7c8a7b5161550f38e4f4637039d800583145a0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaBridgeConnection.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e28b4b6d8fdfdc4d1b7a0d04928edcf9876404678ebd304ae115d74bc404f913"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/AvroSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c77d8e784972151f0389b80a6fb9e7b1ed03e49e6d301173f8b83526d4f9e7f1"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/Rule.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"34a3f3bd43a1bcbbae3786ffa45ffa3699461b2df9fdb7343712c825757f1c66"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/DataType.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5c278293c6a5a807b39241cbddd7cd87ff0383d812083f638cf1ecea28f13a8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Utils.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cae86843957963f93f8fd830b43e4b75c060ac3c45d25ffd169cc834bc6a0787"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/DumpToStringListener.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0b8ce8184baec40d8ab1a3a86d274ac2f662ccaae61a9800e0665279a6e75bc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseResources.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9bfb916eac13e991d10ef655613ef907466e7cdee3f7942899acac25c2205437"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/Bound.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3263635cc7be0b41e3dd81612ffbcbb57df98540c23c8e7fee7c96c25c1ba83e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/Logging.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ec72223495a264afcb788feeae0458dfeecfc2665c24374fd96269cf8195385"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkLoadExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"da7fd34e3c79fabe201f1344fafab522bb5718d432af9039e9e06cda1e7d1629"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkGetExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e3812afb643e656f0a006872bc298a7482ba5a924c7f65dd9be3965b544275e"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseMapGetPutExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b33472a81fc41f498788b59f29b5b6ab16ae40d3aca767f2085d70b4c4f52bbd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/datasources/HBaseSource.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bac9645f8f7ddbe22c630a320c8a7bf66d6f17b12a93b0d4d00bc261e569d159"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseSparkConf.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"76936fc50498d90d4e89f3cb9c30f87997ee9950ecee2e9cc577ff0fa4d660b5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseForeachPartitionExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b327503c40080cda0e0961c759746108b5d803f214451ac815018a9f608c4f61"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseMapPartitionExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d334e628dc635dc96259eca67474b9a3393f483ff229ade79de752ade7945206"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkGetExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0cd5b9048e614286a98ce0968f44479a8f732ab0d616431b71c86710be3cd02"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutTimestampExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb6441f4c3cae81b355029619791eae762172d63e4e9ccb09d4a3970452da85c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkGetExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f179690c50c473a14d7803165dde04bde6cdcba68befd0de7be5fe587dd043a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseStreamingBulkPutExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8fe123bb2942d7c372d75c5f55c80176c00748711f64b292aa8c83d75bce67f5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"519456989eb0ecb9f52eeddf132ad33982ff03427c43290ada48b1091953429f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/rdd/HBaseBulkPutExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff5782d664d9515e81333d4cd2dc72db6e0b1a553720986ab8949c096b29676b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkPutExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"32e78c9229d3fd0b873ac3cf9a0726d4313d762eab6eab9f68ffc82c3d6437c6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/ColumnFamilyQualifierMapKeyWrapper.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"91824f310b19e661229000087486105252589cbeabcda3ce85c68c01846508f2"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseDistributedScan.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce52b860fe638773ccc24f4040822ba42c032869a65e6e1d855a8f956ffc29d4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseBulkPutExampleFromFile.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0beefc137bda12c04844f3dea56f7ccbd670659405f98b676d2eee3713c3ab35"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/java/org/apache/hadoop/hbase/spark/example/hbasecontext/JavaHBaseBulkDeleteExample.java"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"99618dc442614123d428c3713cae4f3c6c4dadda0a910fdae1ab34984167681c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/example/hbasecontext/HBaseStreamingBulkPutExample.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"20d94eec1e1b56960e926533db1c56ffadb247ba65f726472be2932724aa337c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/FamiliesQualifiersValues.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7d0888445ecf841eac0ffd904f27ce7ac9c566550c5a495941c19a946458696"}},{"ruleId":"M1","level":"warning","message":{"text":"README may be stale: 42 code files changed in the last 6 months but the README was not touched \u2014 it may no longer reflect the system."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"e973e7a8d5d866995cbf78b120250fe7f132bf928812d48ca62e69aba11b9910"}},{"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":"M2","level":"note","message":{"text":"No architecture diagram/doc: No C4/Structurizr/PlantUML/Mermaid/Graphviz/D2 diagram, no drawn diagram named for the architecture, no file named \u0060architecture\u0060 or \u0060design\u0060 in any markup this check reads, and nothing in the README, docs or contributor guides that announces the shape \u2014 no \u0060## Architecture\u0060 heading, no \u0022architecture overview\u0022/\u0022high-level design\u0022 phrasing, no \u0022the architecture is \u2026\u0022 introduction, no guided code tour. A shape laid out in prose that never names itself as the architecture is not visible to this check, and neither is one kept outside the repository, so this row reports the absence of a re-findable shape document \u2014 not evidence that nobody wrote the shape down."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"0c190e7c159d1850ee706c3ac4486e151e8a4fe169de4bf61436b9f399654f06"}},{"ruleId":"P10","level":"note","message":{"text":"Large public API surface: 10/12 types (83%) declared in the published library are public. For a library, every public type is a stability contract \u2014 keep implementation types off the surface and expose only the intended API."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"ed2ba843444ae377c17142f58f714e281e4bd3f183ab100ee1fbef389875d3e6"}},{"ruleId":"P3","level":"note","message":{"text":"No SAST: No static application security testing detected. For this repository\u0027s stack, add scalafix or scapegoat (or \u0060semgrep --config=auto\u0060, which runs on any language) \u2014 this repository has no CI pipeline yet, so run it locally to clear the existing findings, then make it a step of the first workflow you add so a regression fails the build. What was searched, so you can tell an absence from a miss: the 0 CI workflow file(s) in this repository, and the scanner and linter configuration checked in beside them. A scan that runs outside CI, one configured in your forge\u0027s web UI rather than in a committed file, or a tool whose name is none of those this check carries, is not seen \u2014 if that is your case the row is wrong, and saying so is more useful than adding a second scanner."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6e54424179c892f03ef2fd003130ac4bd43f39bbf3b1ca0a0143e25acb80ec87"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060((isLowerBoundEqualTo \u0026\u0026 lowerCompare \u003E= 0) || (!isLowerBoundEqualTo \u0026\u0026 lowerCompare \u003E 0)) \u0026\u0026 ((isUpperBoundEqualTo \u0026\u0026 upperCompare \u003C= 0) ||\u2026\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":789}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8a693197fe2839af1e72566c58f3b06b3301cbe9e76fb825294a437013d4e29"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060cmp \u003E 0 || (cmp == 0 \u0026\u0026 (previous.isUpperBoundEqualTo || range.isLowerBoundEqualTo))\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":1155}}}],"partialFingerprints":{"codehealthFindingId/v1":"5563bc9b06f44bd5376c723a102835c58494d8f87e6f6ca3e4003afda72764d3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060colName == that.colName \u0026\u0026 cf == that.cf \u0026\u0026 col == that.col\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseTableCatalog.scala"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"fe4a7137f38bb79740813cac4a2f487aa05e439dc28a7a14409e0c80f914790f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060compareRange(lowerBound, other.lowerBound) \u003C 0 || compareRange(upperBound, other.upperBound) \u003C 0\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":736}}}],"partialFingerprints":{"codehealthFindingId/v1":"dce5b373db58236d5c361c7e071f4e30bc3ddda031fbb61f126297e133327eee"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060field.length != -1 || index == rkIdxedFields.length - 1\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"b569a5cc9dcd872b989c64843764f4a883623cc3606b504316ea7e95d87f83b3"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060field.length == -1 \u0026\u0026 field.dt == StringType \u0026\u0026 index \u003C rkIdxedFields.length - 1\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/HBaseDataWriter.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":232}}}],"partialFingerprints":{"codehealthFindingId/v1":"27409747b03f4119b5e45a3f169d61371c0b6843ad798f33e1d452037f42c1d6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060flag \u0026\u0026 (thisValue == null || !(thisValue == thatValue))\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":249}}}],"partialFingerprints":{"codehealthFindingId/v1":"5be8cc60f6fae1734e06a4758c4c56d3804bbabb8aa058fea82570250e174bb7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060forceClean || ((x._2.refCount \u003C= 0) \u0026\u0026 (tsNow - x._2.timestamp \u003E timeout))\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"79aa76d58b32f96ded1efd3e6511443075fd49a5aaed23d59232355af23ac1ce"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isLowerBoundEqualTo \u0026\u0026 other.isLowerBoundEqualTo\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":673}}}],"partialFingerprints":{"codehealthFindingId/v1":"478d0ece9d679decd5de904c8d8ac58ed7f572bbd716d4486fa0a6e7531a6d3b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isLowerBoundEqualTo || other.isLowerBoundEqualTo\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":699}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ccb56f3e83e4740c674326a764d522aef1682ff4e8642ee728c5d3fb2aea033"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isUpperBoundEqualTo \u0026\u0026 other.isUpperBoundEqualTo\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":679}}}],"partialFingerprints":{"codehealthFindingId/v1":"82c8e1ad6e9568b3a2231430bad0a84da0f3f841efcc3f3dda4437ac53cc01f5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isUpperBoundEqualTo || other.isUpperBoundEqualTo\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":705}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6985584c73d012d5eea439e64ad3348af90beeaad8827e2aeb34f0a466970b2"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060low \u003E 0 \u0026\u0026 sortedRanges(low - 1).containsPoint(point)\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/datasources/ScanRange.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/DefaultSource.scala"},"region":{"startLine":1178}}}],"partialFingerprints":{"codehealthFindingId/v1":"14fce047b7446ba66bb4867bf2697db8eefd164af67f2b47ba98af652bb20b0b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060rollOverRequested \u0026\u0026 Bytes .compareTo(previousRow, keyFamilyQualifier.rowKey) != 0\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":672}}}],"partialFingerprints":{"codehealthFindingId/v1":"80526051997efbdae0fe21bcc5e2696b0a5e70097956c4448ee81ffb78e9cf7d"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060rollOverRequested || wl.written \u003E maxSize\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseContext.scala"},"region":{"startLine":668}}}],"partialFingerprints":{"codehealthFindingId/v1":"ff0530a4dbe64b802a1d365d61f34bff739c6a457916a26932f41db5a5eaccc0"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060this.username != null \u0026\u0026 !(this.username == that.username)\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":228}}}],"partialFingerprints":{"codehealthFindingId/v1":"be66a6e8c88f8a9f43608326234b51403d4969ead0d6fb71117121d04a49cdc1"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060this.username == null \u0026\u0026 that.username != null\u0060 appears character-identically in 2 files \u2014 spark/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala, spark4/hbase-spark4/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.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/hbase-spark/src/main/scala/org/apache/hadoop/hbase/spark/HBaseConnectionCache.scala"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e0b48e23a3a3893307ee6fd9e3e1dff70fb09c039bd1504d89ab1f9b1aecc6e"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060debug\u0060 at line 93 is handed a message assembled at the call \u2014 a string concatenated with a value, or \u0060String.format\u0060 \u2014 through SLF4J or log4j 2, so the logger receives one finished string: the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the level is filtered out. Pass a constant pattern and the values beside it instead: \u0060log.debug(\u0022Order {} moved to {}\u0022, orderId, status)\u0060, which keeps the pattern and its arguments apart on the event for a structured encoder (logstash-logback-encoder, log4j 2\u0027s JsonTemplateLayout, OpenTelemetry), or \u0060log.atInfo().addKeyValue(\u0022order_id\u0022, orderId).log(\u0022order moved\u0022)\u0060 with SLF4J 2\u0027s fluent API. An exception goes last, as the throwable argument, not into the text."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/DumpToStringListener.java"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"813ba70a0c458c1914c4f134866e5819436cbff5435a20744f1af15a3e784e65"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060warn\u0060 at line 269 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.warn(\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":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaProxy.java"},"region":{"startLine":269}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9c7a95070936698f81dac637e0fd7d39ce01abca7ff71b101a39857c5a9eb70"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 323 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":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaProxy.java"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"ec6f27ecfc29c366ad32e2d3adfdd2d2588296caf4e3db9eaeceacbaeccafe18"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060info\u0060 at line 329 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":"kafka/hbase-kafka-proxy/src/main/java/org/apache/hadoop/hbase/kafka/KafkaProxy.java"},"region":{"startLine":329}}}],"partialFingerprints":{"codehealthFindingId/v1":"7373ee3cc77032f3cdb1cd45fa41e0644b10c59f0adfc6c7966cf2965f08b933"}},{"ruleId":"X5","level":"note","message":{"text":"Scala\u0027s null is not held to the type system everywhere: No build over this repository\u0027s 80 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"}}],"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-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-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-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-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":"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/"}]}],"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":5,"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."]}]}