{"$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":"D12","name":"Dependency Hygiene","shortDescription":{"text":"Dependency Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/D12"},{"id":"D13","name":"Secret Scanning","shortDescription":{"text":"Secret Scanning"},"helpUri":"https://codehealth.canine.dev/dimensions/D13","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D14","name":"License Compliance","shortDescription":{"text":"License Compliance"},"helpUri":"https://codehealth.canine.dev/dimensions/D14"},{"id":"D15","name":"Churn \u00D7 Complexity Hotspots","shortDescription":{"text":"Churn \u00D7 Complexity Hotspots"},"helpUri":"https://codehealth.canine.dev/dimensions/D15"},{"id":"D16","name":"Bus Factor","shortDescription":{"text":"Bus Factor"},"helpUri":"https://codehealth.canine.dev/dimensions/D16"},{"id":"D17","name":"Explicit Debt","shortDescription":{"text":"Explicit Debt"},"helpUri":"https://codehealth.canine.dev/dimensions/D17"},{"id":"D19","name":"Documentation Quality","shortDescription":{"text":"Documentation Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D19"},{"id":"D21","name":"Naming Consistency","shortDescription":{"text":"Naming Consistency"},"helpUri":"https://codehealth.canine.dev/dimensions/D21"},{"id":"D22","name":"Internal API Consistency","shortDescription":{"text":"Internal API Consistency"},"helpUri":"https://codehealth.canine.dev/dimensions/D22"},{"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":"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":"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":"AXB1","name":"Runtime evidence locked \u2014 no reproducible boot","shortDescription":{"text":"Runtime evidence locked \u2014 no reproducible boot"},"helpUri":"https://codehealth.canine.dev/dimensions/AXB1"},{"id":"AXB2","name":"Runtime readiness","shortDescription":{"text":"Runtime readiness"},"helpUri":"https://codehealth.canine.dev/dimensions/AXB2"},{"id":"ED5","name":"Idempotency","shortDescription":{"text":"Idempotency"},"helpUri":"https://codehealth.canine.dev/dimensions/ED5"},{"id":"M1","name":"Documentation (README)","shortDescription":{"text":"Documentation (README)"},"helpUri":"https://codehealth.canine.dev/dimensions/M1"},{"id":"M2","name":"Architecture documentation","shortDescription":{"text":"Architecture documentation"},"helpUri":"https://codehealth.canine.dev/dimensions/M2"},{"id":"M3","name":"Folder \u0026 project structure","shortDescription":{"text":"Folder \u0026 project structure"},"helpUri":"https://codehealth.canine.dev/dimensions/M3"},{"id":"M4","name":"Documentation accuracy","shortDescription":{"text":"Documentation accuracy"},"helpUri":"https://codehealth.canine.dev/dimensions/M4"},{"id":"P1","name":"CI/CD gates","shortDescription":{"text":"CI/CD gates"},"helpUri":"https://codehealth.canine.dev/dimensions/P1"},{"id":"P10","name":"Library API \u0026 versioning","shortDescription":{"text":"Library API \u0026 versioning"},"helpUri":"https://codehealth.canine.dev/dimensions/P10"},{"id":"P3","name":"Security \u0026 performance tooling","shortDescription":{"text":"Security \u0026 performance tooling"},"helpUri":"https://codehealth.canine.dev/dimensions/P3"},{"id":"P6","name":"Release Hygiene","shortDescription":{"text":"Release Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/P6"},{"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":"D2","level":"warning","message":{"text":"ProtobufConverter.setFeatures (cognitive 26): ProtobufConverter.setFeatures has cognitive complexity 26 (threshold 15). Drivers by points: loops 6 (17 pts), if/else 4 (8 pts), match/switch 1 (nesting depth added 15). This file\u0027s own header attributes it to another copyright holder, so it is code this repository carries rather than code it wrote: restructuring the body in place forks it from upstream and turns every future re-sync into a manual merge. The performable moves are to leave the body as close to its upstream form as possible and keep it behind a narrow interface of your own, and to re-sync it when upstream changes \u2014 or, if it has already diverged far enough that you maintain it here, adopt it deliberately and then split the body into named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/protobuf/ProtobufConverter.scala"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"e380e1fd5b6a88fba3f8e2deecc69e9296bda0fad9c5826889d890b9d9817d31"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: XGBoostSageMakerEstimator: TooManyMethods \u2014 73 methods. The bar is 30 methods; this is 43 over it, 2.43\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/XGBoostSageMakerEstimator.py"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"5885938b3b9de3f11856ab9825a714e715359f905e04ec86d33b30fbdf7385c1"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: LinearLearnerParams: TooManyMethods \u2014 72 methods. The bar is 30 methods; this is 42 over it, 2.40\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py"},"region":{"startLine":15}}}],"partialFingerprints":{"codehealthFindingId/v1":"47cab86fa6caaaeb33a901e3e2a985256b16404b37a216aab1961614e0019e2f"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: FactorizationMachinesParams: TooManyMethods \u2014 50 methods. The bar is 30 methods; this is 20 over it, 1.67\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"c06a5f37e8b1bf874298a8c72b774f66b7fa730703aacd5c3c95650deb182f2f"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: algorithms/LinearLearnerSageMakerEstimator.py: FileTooLong \u2014 766 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 266 over it, 1.53\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"92993370bcec3ed574b640191d243907df291e497675240e7b427db50a572c3a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: LinearLearnerSageMakerEstimator: TooManyMethods \u2014 38 methods. The bar is 30 methods; this is 8 over it, 1.27\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/algorithms/LinearLearnerSageMakerEstimator.scala"},"region":{"startLine":1055}}}],"partialFingerprints":{"codehealthFindingId/v1":"32fc259160d6eccfc4ceb602828f3077cbe7fa660eb81166b98876997c1b4b9a"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: XGBoostSageMakerEstimator: TooManyMethods \u2014 35 methods. The bar is 30 methods; this is 5 over it, 1.17\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/algorithms/XGBoostSageMakerEstimator.scala"},"region":{"startLine":473}}}],"partialFingerprints":{"codehealthFindingId/v1":"1994ecd084f3bc7d17d7727227919c878716806370d52cce7b69ab2160a1c347"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: algorithms/LinearLearnerSageMakerEstimator.scala: FileTooLong \u2014 581 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 81 over it, 1.16\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/algorithms/LinearLearnerSageMakerEstimator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c30f88b9d4b1fa47a04ffc8625d9a9f3b9f7d24c7a3e39bc68999e91ba81f3c1"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: algorithms/XGBoostSageMakerEstimator.py: FileTooLong \u2014 501 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 1 over it, 1.00\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/XGBoostSageMakerEstimator.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"544182881e654f3e5ca8a6f983b3f9a2d3c4a4baf97debe02bd242568f1f3af4"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (10 members, 23 shared lines): sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerEstimator.py:443-477 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py:467-502 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py:648-683 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/KMeansSageMakerEstimator.py:225-257 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LDASageMakerEstimator.py:194-226 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:696-731 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:928-963 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:1133-1168 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/PCASageMakerEstimator.py:186-218 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/XGBoostSageMakerEstimator.py:388-420 \u2014 These 10 members are variants of one another: a block of 23 lines reported below appears in every one of them, and the pairwise near-duplicate rows they would otherwise produce are collapsed into this row. Read them as one construct written 10 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 10 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerEstimator.py"},"region":{"startLine":443}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc90ec72fa042d0ffa0a2a4995ae465b436aaf20f3da229962fd19b48aac92aa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/SageMakerModel.scala:109-122 | sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/SageMakerModel.scala:173-186 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/SageMakerModel.scala:109\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":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/SageMakerModel.scala"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"37942e98e4037d5c91f5f724e8a6a68fc33acbfec0dc6f8fc7d9958240860887"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (64\u201365 lines \u00D7 2): sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerModel.py:154-217 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerModel.py:299-363 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerModel.py"},"region":{"startLine":154}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c8e12c379206284297d27dfdb06270b20a02f9a0d048402182fa866ecaf1aec"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (23 lines \u00D7 10): sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerEstimator.py:447-469 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py:472-494 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py:653-675 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/KMeansSageMakerEstimator.py:227-249 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LDASageMakerEstimator.py:196-218 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:701-723 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:933-955 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py:1138-1160 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/PCASageMakerEstimator.py:188-210 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/XGBoostSageMakerEstimator.py:390-412 \u2014 there are 10 copies across 7 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 10 sites; resolving a subset leaves the remainder to drift apart. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py:495\u0060 calls \u0060Option\u0060 and \u0060sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerEstimator.py:470\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":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/SageMakerEstimator.py"},"region":{"startLine":447}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a9c5b1181a5084649581c6074fa6ab8f3ba363177333bef93e232ba8dfee7ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): sagemaker-pyspark-sdk/docs/conf.py:18-22 | sagemaker-pyspark-sdk/setup.py:18-22 \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":"sagemaker-pyspark-sdk/docs/conf.py"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b3a1a5f615a36acbcf6b4863bdb301f0b19fb7069dde22e661f039fad78e8b3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LDASageMakerEstimator.py:179-191 | sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/XGBoostSageMakerEstimator.py:374-385 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LDASageMakerEstimator.py"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"e6347b01d9721edf27967a59d1eaba811ad7584c0a8cdd850f4d36b83e33f121"}},{"ruleId":"D22","level":"warning","message":{"text":"Redundant Type Hierarchy: The \u0060CustomNamePolicyWithTimeStampSuffix\u0060 class and its corresponding \u0060CustomNamePolicyWithTimeStampSuffixFactory\u0060 appear to be functionally identical to \u0060CustomNamePolicy\u0060 and \u0060CustomNamePolicyFactory\u0060 except for the implicit timestamp suffix behavior. However, the API exposes them as distinct, parallel classes with identical constructor signatures (trainingJobName, modelName, endpointConfigName, endpointName). This forces users to choose between two nearly identical types rather than configuring a single type via a parameter (e.g., \u0060use_timestamp=True\u0060).: Unify into a single \u0060CustomNamePolicy\u0060 class that accepts an optional boolean flag \u0060include_timestamp\u0060 in its constructor. Remove \u0060CustomNamePolicyWithTimeStampSuffix\u0060 and its factory. (signatures: sagemaker_pyspark.NamePolicy.CustomNamePolicyWithTimeStampSuffix | sagemaker_pyspark.NamePolicy.CustomNamePolicyWithTimeStampSuffixFactory)"},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"3d562cdf93bbac5c0f61d792e1cd933930fc35aca267d761f0c0b6a4da313119"}},{"ruleId":"D28","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"18dd76a6b70275018fdcb50acee2d1a58f089ef63b386968365b02de69a24289"},"properties":{"commitSha":"660d627fe0c59210ed348f4cf9e50e47d0a2fd81"}},{"ruleId":"D28","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3cdfd7beb31b791ae18dcb425e21eb157c842e7bbcd522cc330573c1a6538db1"}},{"ruleId":"D34","level":"error","message":{"text":"Orphaned knowledge: No living knowledge remains for this large file \u2014 its last meaningful change has decayed away; if it breaks, no one currently understands it. Schedule a read-through / add characterisation tests before it bites."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"292d7dc639460185543fc325572295b3d1b2b5dbdf87ee72c155b2187670ef4c"}},{"ruleId":"D34","level":"note","message":{"text":"Further orphaned files (smaller): 3 smaller file(s) also have no living knowledge \u2014 folded into the freshness score and metrics rather than raised one row each \u2014 most significant first: sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/transformation/util/RequestBatchIterator.scala, sagemaker-spark-sdk/build.sbt, sagemaker-pyspark-sdk/setup.py (4 orphaned of 4 analysed files in total, counted over production source files of roughly 2,400 bytes or more, excluding vendored, generated and example/demo trees and test files identified by path convention, largest first; 4 of the 9 production source files in this repository met that bar). Attach the read to the next change that touches one of them: have a second person review that change, and leave behind a short comment or test recording what the file is for, so the knowledge comes back at the cost of a change you were making anyway."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"ce861fd78f6935114d3a342cb90ad25870f984e1042954fcbbe27c0e23be3658"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/com/amazonaws/services/sagemaker/sparksdk/transformation/util/RequestBatchIterator.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4c4663cf55b3a6d5823da7d5771f67d095b94a87d38613cce4abe1ffa7450de"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/build.sbt"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e2d08ced69765eea46ebdbd75fb5ef6e8d15f4e2917b9ddd155ec84755550cd"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/setup.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c0ec0cfc99eb677502ff00fdd95a58054af1b447e17b422a8a90c64a241e395b"}},{"ruleId":"AX6","level":"note","message":{"text":"Fat interface: RecordOrBuilder (19 abstract methods): \u0060RecordOrBuilder\u0060 declares 19 abstract methods: \u0060getConfiguration\u0060, \u0060getConfigurationBytes\u0060, \u0060getFeatures\u0060, \u0060getFeaturesCount\u0060, \u0060getFeaturesList\u0060, \u0060getFeaturesOrBuilder\u0060, \u0060getFeaturesOrBuilderList\u0060, \u0060getLabel\u0060, \u0060getLabelCount\u0060, \u0060getLabelList\u0060, \u0060getLabelOrBuilder\u0060, \u0060getLabelOrBuilderList\u0060, \u0060getMetadata\u0060, \u0060getMetadataBytes\u0060, \u0060getUid\u0060, \u0060getUidBytes\u0060, \u0060hasConfiguration\u0060, \u0060hasMetadata\u0060, \u0060hasUid\u0060. Counted over its ABSTRACT methods, once per signature; \u0060default\u0060, \u0060static\u0060 and \u0060private\u0060 methods and constants are not counted, because no implementer is forced to write them. A wide interface forces every implementer and caller to depend on methods they don\u0027t use (the Interface-Segregation \u0027I\u0027 in SOLID). Split it into focused role-interfaces."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-spark-sdk/src/main/scala/aialgorithms/proto2/RecordProto2.java"},"region":{"startLine":5619}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a23db529b57ec388e7d3b962567eac0e21244d6d0ec98a39fa3812bdddc2a58"}},{"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":"M4","level":"note","message":{"text":"README/code drift: README advertises Docker containerisation, but no Dockerfile/compose file exists \u2014 searched for: \u0060dockerfile\u0060, \u0060docker-compose\u0060, \u0060compose.yaml\u0060, \u0060compose.yml\u0060. Each was matched case- and separator-insensitively against file and directory NAMES anywhere in the tree, and against the CONTENTS of manifest and configuration files (package.json and other *.json, *.csproj, *.props, *.sln/*.slnx, *.yml, *.toml, *.config, tool configs such as eslint.config.js, Dockerfile); the README\u0027s own prose never counts, so a claim is never refuted by merely being made. Nothing outside that search was read \u2014 a footprint living only in a submodule, in a file type not listed here, or under a name none of those terms matches is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"README.md"},"region":{"startLine":11}}}],"partialFingerprints":{"codehealthFindingId/v1":"343bbbd51ceb8de7a9ff88d79f7c797abf9b5921f8727b67b4d0f4f8a22c5e49"}},{"ruleId":"P1","level":"warning","message":{"text":"No CI pipeline: No CI workflow found (.github/workflows, azure-pipelines.yml, .gitlab-ci.yml, \u2026) \u2014 changes aren\u0027t gated by an automated build/test."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"44f01af96e50474fba2df84d95ddf4f7e1d34c29c307830b9efc9057daa6b670"}},{"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\u0027javaObject\u0027 in kwargs and kwargs[\u0027javaObject\u0027] is not None\u0060 appears character-identically in 2 files \u2014 sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py, sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/FactorizationMachinesSageMakerEstimator.py"},"region":{"startLine":467}}}],"partialFingerprints":{"codehealthFindingId/v1":"191fe13634ee5cf7f9e50b10b0f81bc6d409aab39e24d74f73d00f80c32ab8fd"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(value, numbers.Real) and value \u003C 1\u0060 appears character-identically in 2 files \u2014 sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/KMeansSageMakerEstimator.py, sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/LinearLearnerSageMakerEstimator.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/KMeansSageMakerEstimator.py"},"region":{"startLine":319}}}],"partialFingerprints":{"codehealthFindingId/v1":"adbdbffff397301bcecd23fe328e67decf2259b0bd340d599f43743f011c452f"}},{"ruleId":"X5","level":"note","message":{"text":"Scala\u0027s null is not held to the type system everywhere: No build over this repository\u0027s 34 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-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-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-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":"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/"}]}],"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":2,"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."]}]}