{"$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":"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":"D11","name":"Test Reliability","shortDescription":{"text":"Test Reliability"},"helpUri":"https://codehealth.canine.dev/dimensions/D11"},{"id":"D12","name":"Dependency Hygiene","shortDescription":{"text":"Dependency Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/D12"},{"id":"D13","name":"Secret Scanning","shortDescription":{"text":"Secret Scanning"},"helpUri":"https://codehealth.canine.dev/dimensions/D13","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D14","name":"License Compliance","shortDescription":{"text":"License Compliance"},"helpUri":"https://codehealth.canine.dev/dimensions/D14"},{"id":"D15","name":"Churn \u00D7 Complexity Hotspots","shortDescription":{"text":"Churn \u00D7 Complexity Hotspots"},"helpUri":"https://codehealth.canine.dev/dimensions/D15"},{"id":"D16","name":"Bus Factor","shortDescription":{"text":"Bus Factor"},"helpUri":"https://codehealth.canine.dev/dimensions/D16"},{"id":"D17","name":"Explicit Debt","shortDescription":{"text":"Explicit Debt"},"helpUri":"https://codehealth.canine.dev/dimensions/D17"},{"id":"D19","name":"Documentation Quality","shortDescription":{"text":"Documentation Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D19"},{"id":"D20","name":"ADR Quality","shortDescription":{"text":"ADR Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D20"},{"id":"D21","name":"Naming Consistency","shortDescription":{"text":"Naming Consistency"},"helpUri":"https://codehealth.canine.dev/dimensions/D21"},{"id":"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":"D36","name":"Supply-chain Provenance \u0026 Signing","shortDescription":{"text":"Supply-chain Provenance \u0026 Signing"},"helpUri":"https://codehealth.canine.dev/dimensions/D36","relationships":[{"target":{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1357","CWE-494"],"owasp":"A03:2025"}},{"id":"D37","name":"Vulnerability-disclosure Policy","shortDescription":{"text":"Vulnerability-disclosure Policy"},"helpUri":"https://codehealth.canine.dev/dimensions/D37","relationships":[{"target":{"id":"CWE-1059","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1059"],"owasp":"A02:2025"}},{"id":"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":"AX5","name":"Architecture \u0026 structure","shortDescription":{"text":"Architecture \u0026 structure"},"helpUri":"https://codehealth.canine.dev/dimensions/AX5"},{"id":"AX7","name":"Slice cohesion","shortDescription":{"text":"Slice cohesion"},"helpUri":"https://codehealth.canine.dev/dimensions/AX7"},{"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":"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":"P6","name":"Release Hygiene","shortDescription":{"text":"Release Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/P6"},{"id":"PF1","name":"Benchmark discipline","shortDescription":{"text":"Benchmark discipline"},"helpUri":"https://codehealth.canine.dev/dimensions/PF1"},{"id":"PF3","name":"Async \u0026 latency hygiene","shortDescription":{"text":"Async \u0026 latency hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/PF3"},{"id":"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":"X17","name":"Uncapped recursion over a caller-supplied document","shortDescription":{"text":"Uncapped recursion over a caller-supplied document"},"helpUri":"https://codehealth.canine.dev/dimensions/X17"},{"id":"X19","name":"Unrestored process-global state","shortDescription":{"text":"Unrestored process-global state"},"helpUri":"https://codehealth.canine.dev/dimensions/X19"},{"id":"X20","name":"Mistyped argument guard","shortDescription":{"text":"Mistyped argument guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X20"},{"id":"X21","name":"Side-effecting pattern guard","shortDescription":{"text":"Side-effecting pattern guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X21"},{"id":"X22","name":"Contradicted release guard","shortDescription":{"text":"Contradicted release guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X22"},{"id":"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":"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":"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":"features._cast_to_python_objects (cyclomatic 67): features._cast_to_python_objects has cyclomatic complexity 67 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c26fc0e09d620ac3c830658c48cdf697ff4310828b15f2aca089d9417d7cad8"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.map (cyclomatic 61): Dataset.map has cyclomatic complexity 61 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":3205}}}],"partialFingerprints":{"codehealthFindingId/v1":"0378ecea086362e03588097a77d716e4466f8c5e4143a52993435c8e51a70845"}},{"ruleId":"D1","level":"warning","message":{"text":"TypedSequence._arrow_array (cyclomatic 55): TypedSequence._arrow_array has cyclomatic complexity 55 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"166f6e606353b235fb64441d162d77cc3eaa2ba5782e5fd1edf985b5f7e9e4c9"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.train_test_split (cyclomatic 50): Dataset.train_test_split has cyclomatic complexity 50 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4967}}}],"partialFingerprints":{"codehealthFindingId/v1":"103194e7a7a830888f77d6e11c602e77e259fdaf5f62e1993dd21d53c9b355bb"}},{"ruleId":"D1","level":"warning","message":{"text":"Json._generate_tables (cyclomatic 50): Json._generate_tables has cyclomatic complexity 50 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/json/json.py"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"426d88490442ea37af73ae9e1039bc663ef1ca42f2923cf59856a09f177de380"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset._map_single (cyclomatic 46): Dataset._map_single has cyclomatic complexity 46 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":3660}}}],"partialFingerprints":{"codehealthFindingId/v1":"2aa134e901bcb715c8856cf0a656c3140880997f0c9fb3f25b845be5a7661e67"}},{"ruleId":"D1","level":"warning","message":{"text":"load.dataset_module_factory (cyclomatic 39): load.dataset_module_factory has cyclomatic complexity 39 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":957}}}],"partialFingerprints":{"codehealthFindingId/v1":"ceed07a17c193694927ee168d1cf0dabf5371db8d24839987505d922593ecffb"}},{"ruleId":"D1","level":"warning","message":{"text":"TensorflowDatasetMixin.to_tf_dataset (cyclomatic 37): TensorflowDatasetMixin.to_tf_dataset has cyclomatic complexity 37 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":336}}}],"partialFingerprints":{"codehealthFindingId/v1":"37204181f2022022bce29b2cf91a5980206740861d7461057896164500cc1ce3"}},{"ruleId":"D1","level":"warning","message":{"text":"arrow_dataset._get_updated_dataset_card (cyclomatic 34): arrow_dataset._get_updated_dataset_card has cyclomatic complexity 34 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6887}}}],"partialFingerprints":{"codehealthFindingId/v1":"e72d743bcc2aa8a07c444a47d6e604ecb2fe3483d4f4576834b08bceede6877a"}},{"ruleId":"D1","level":"warning","message":{"text":"RebatchedArrowExamplesIterable._iter_arrow (cyclomatic 33): RebatchedArrowExamplesIterable._iter_arrow has cyclomatic complexity 33 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e338b6fd900f3f087b1d803e684cc98a79e47761ba441228b90197b126328fb"}},{"ruleId":"D1","level":"warning","message":{"text":"arrow_dataset._interleave_map_style_datasets (cyclomatic 28): arrow_dataset._interleave_map_style_datasets 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":7135}}}],"partialFingerprints":{"codehealthFindingId/v1":"948b7209dfb63a87ec873e98352a12008622cc0425a5e02e3d6639c5c14177fc"}},{"ruleId":"D1","level":"warning","message":{"text":"DatasetBuilder.download_and_prepare (cyclomatic 28): DatasetBuilder.download_and_prepare has cyclomatic complexity 28 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":702}}}],"partialFingerprints":{"codehealthFindingId/v1":"68a104089f9842d1c2a86e151c05f9e57fbe61e5261bafadfef334f4da8cd370"}},{"ruleId":"D1","level":"warning","message":{"text":"MappedExamplesIterable._iter_arrow (cyclomatic 28): MappedExamplesIterable._iter_arrow 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":1678}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f238d3c6f4db7ecb9d7975bf9570a6665950e48bdf72b8cadc92c9f566e26db"}},{"ruleId":"D1","level":"warning","message":{"text":"table.array_cast (cyclomatic 28): table.array_cast 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":"src/datasets/table.py"},"region":{"startLine":1907}}}],"partialFingerprints":{"codehealthFindingId/v1":"becfd4009e7fa36880b9cb99f2a123151f2e68141466aab96f2539b4c72d9cb4"}},{"ruleId":"D1","level":"warning","message":{"text":"py_utils.map_nested (cyclomatic 28): py_utils.map_nested 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":"src/datasets/utils/py_utils.py"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"817d8c9116c8226565db1715b41be3c0703dcfe643a974655fb8635b03a2cf17"}},{"ruleId":"D1","level":"warning","message":{"text":"DatasetBuilder._create_builder_config (cyclomatic 27): DatasetBuilder._create_builder_config 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":"src/datasets/builder.py"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"e907a09dddb06c7511312d6c7fd386cecc85d6e6347e3861c012eb14d6d27857"}},{"ruleId":"D1","level":"warning","message":{"text":"table.cast_array_to_feature (cyclomatic 26): table.cast_array_to_feature has cyclomatic complexity 26 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":2020}}}],"partialFingerprints":{"codehealthFindingId/v1":"11ab9658b26f37044b378911335989daac59cf5c14ecf9c976afb5da47ae563b"}},{"ruleId":"D1","level":"warning","message":{"text":"DatasetBuilder.__init__ (cyclomatic 25): DatasetBuilder.__init__ has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"04452451df67ebcbb3d9d737258c1e7366dfe01769d17327e220c6ee9ccddb02"}},{"ruleId":"D1","level":"warning","message":{"text":"NumpyArrowExtractor._arrow_array_to_numpy (cyclomatic 25): NumpyArrowExtractor._arrow_array_to_numpy has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/formatting.py"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"238c05396f0cd83a27dcd352e01cef25bfbc41521b4e5ecdaf5dc04e6c449505"}},{"ruleId":"D1","level":"warning","message":{"text":"FolderBasedBuilder._split_generators (cyclomatic 24): FolderBasedBuilder._split_generators has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"ced3604905c7cfb4c17f05229432df8a84ce6439102ddbff5bb906c1403b672b"}},{"ruleId":"D1","level":"warning","message":{"text":"TsFile._read_device_from_file (cyclomatic 24): TsFile._read_device_from_file has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":537}}}],"partialFingerprints":{"codehealthFindingId/v1":"31f3adef76ed446ab49a2d29a716bad260036971f23f1ff13838725ee3c62881"}},{"ruleId":"D1","level":"warning","message":{"text":"FolderBasedBuilder._read_metadata (cyclomatic 23): FolderBasedBuilder._read_metadata 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":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"9c7d17f5115dbe4fff60b263c383772fce5eb755b3114b5f4c22ddd5bcd1993a"}},{"ruleId":"D1","level":"warning","message":{"text":"Lance._split_generators (cyclomatic 23): Lance._split_generators 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":"src/datasets/packaged_modules/lance/lance.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"1623a5af245e759c39cd730db54b528523d8b52a19579a0670fa50b9f1e56bee"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDataset._prepare_ex_iterable_for_iteration (cyclomatic 22): IterableDataset._prepare_ex_iterable_for_iteration has cyclomatic complexity 22 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2958}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c57f2890f333ce0740f1de82fd3f99d1e681810fff66e9e04913d8afa7b34b2"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDataset._push_parquet_shards_to_hub (cyclomatic 22): IterableDataset._push_parquet_shards_to_hub has cyclomatic complexity 22 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5188}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1562cb47036689144087eedcd5484841c30eb74b535b1e472ec73d307ef2ba9"}},{"ruleId":"D1","level":"warning","message":{"text":"data_files.resolve_pattern (cyclomatic 21): data_files.resolve_pattern 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":"src/datasets/data_files.py"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9768dfe58134dd1271247961a3376799e39cdb280adf75064cd9089015dd031"}},{"ruleId":"D1","level":"warning","message":{"text":"TsFile._scan_metadata (cyclomatic 21): TsFile._scan_metadata has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"76e6bfca3cfbb998e070cb9f92a031753a7f6fb4922d676484b5c2a84b3b92ed"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.save_to_disk (cyclomatic 20): Dataset.save_to_disk has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":1781}}}],"partialFingerprints":{"codehealthFindingId/v1":"436109598984e86109a90eed8425dd633d4445e1fdc7677eab4cc4766238e0ae"}},{"ruleId":"D1","level":"warning","message":{"text":"features.string_to_arrow (cyclomatic 20): features.string_to_arrow has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: features._arrow_to_datasets_dtype (cyclomatic 32) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"e471b4f2b69daddab765ccd66942ae43b26c6a7e79f80bf40d76039143cdb828"}},{"ruleId":"D1","level":"warning","message":{"text":"JaxFormatter._tensorize (cyclomatic 20): JaxFormatter._tensorize has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfab2a510ad55f89c23f3d7f22fe52672178828f26aa17479a566d1a98d55d7f"}},{"ruleId":"D1","level":"warning","message":{"text":"TorchFormatter._tensorize (cyclomatic 20): TorchFormatter._tensorize has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/torch_formatter.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"592fc457b522c67ebe137272b3307386cf0b0a45c9535f5f12c8e108d5b0e41b"}},{"ruleId":"D1","level":"warning","message":{"text":"CyclingMultiSourcesExamplesIterable._iter_arrow (cyclomatic 20): CyclingMultiSourcesExamplesIterable._iter_arrow has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (CyclingMultiSourcesExamplesIterable.__iter__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":828}}}],"partialFingerprints":{"codehealthFindingId/v1":"f0d4c10e10a6010d72694ab7a08b683b2407bb341446def4d6b7ddb380e63c29"}},{"ruleId":"D1","level":"warning","message":{"text":"CyclingMultiSourcesExamplesIterable.__iter__ (cyclomatic 20): CyclingMultiSourcesExamplesIterable.__iter__ has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This shape REPEATS in the file: one other method here (CyclingMultiSourcesExamplesIterable._iter_arrow) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":903}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a2435d6a1fc7dbc57abbe293f61c7afb78f579b7ba1e558f403df41244082aa"}},{"ruleId":"D1","level":"warning","message":{"text":"HubDatasetModuleFactory.get_module (cyclomatic 20): HubDatasetModuleFactory.get_module has cyclomatic complexity 20 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":577}}}],"partialFingerprints":{"codehealthFindingId/v1":"88e2c5b919e9d076ffb426a2bb53b7a6a20b362cc9e1e3445cd7fa27ad451d84"}},{"ruleId":"D1","level":"warning","message":{"text":"Fastq._parse_fastq (cyclomatic 20): Fastq._parse_fastq has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fastq/fastq.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"86eb63b3c6f8e9007f943831ee40a6f0ab2e6957ff7a4464d9647c6815900c11"}},{"ruleId":"D1","level":"warning","message":{"text":"TensorflowDatasetMixin._get_output_signature (cyclomatic 19): TensorflowDatasetMixin._get_output_signature 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"c55c541b880429182d96dcf80d30aea990e25971af4cdc8a6911ced6d42884d9"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.shuffle (cyclomatic 19): Dataset.shuffle 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":4827}}}],"partialFingerprints":{"codehealthFindingId/v1":"dce89dffb122d8f66c5f7bdf95bf3cace4e769f1fc45f3049e4f8d776b0e6a4e"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowWriter._write_batch (cyclomatic 19): ArrowWriter._write_batch 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":"src/datasets/arrow_writer.py"},"region":{"startLine":759}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f509a90dce649df317a3a326e7fd09158c3888cb59f65c9162e4f0892fafc6e"}},{"ruleId":"D1","level":"warning","message":{"text":"features.decode_nested_example (cyclomatic 19): features.decode_nested_example has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top. This is NOT this file\u0027s highest cyclomatic complexity: features._arrow_to_datasets_dtype (cyclomatic 32) is higher and carries no row of its own \u2014 it was excluded as a flat dispatcher (a long switch/match over independent cases: many branches, almost no nesting), which this dimension does not treat as a refactor obligation. It is named here so the ranking you see in this file is not mistaken for the whole of it; the excluded method is counted neither in this dimension\u0027s figures nor in its score."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":1546}}}],"partialFingerprints":{"codehealthFindingId/v1":"8b474127fc26f5c7c1ca76fa1a4bafe41b2d0fcb326ca531507d40010e00f51d"}},{"ruleId":"D1","level":"warning","message":{"text":"NumpyFormatter._tensorize (cyclomatic 19): NumpyFormatter._tensorize has cyclomatic complexity 19 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/np_formatter.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"e314ad8c230dcc12ab7d6d7120789c048471253be757b74c2301b17200219a70"}},{"ruleId":"D1","level":"warning","message":{"text":"FaissIndex.add_vectors (cyclomatic 19): FaissIndex.add_vectors 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":"src/datasets/search.py"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a41b18b90c2b44ccdcd3de7823e57e531a0e7c5d3a6a74177caa92cf6031c38"}},{"ruleId":"D1","level":"warning","message":{"text":"file_utils.cached_path (cyclomatic 19): file_utils.cached_path 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":"src/datasets/utils/file_utils.py"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"f083cfb7888dd9a752448223f625682e76c810330003705e937267094289a3da"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.sort (cyclomatic 18): Dataset.sort has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4697}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ca052e542caf15a589b46851bd5208c715708a672e7ea0eb316778ab4f3a298"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset._push_parquet_shards_to_hub (cyclomatic 18): Dataset._push_parquet_shards_to_hub has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":5960}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a194a053f23836e5448e44753a7b4b7a33c7aa1741ddbe404f5e9bf70798558"}},{"ruleId":"D1","level":"warning","message":{"text":"dataset_dict._push_to_repo (cyclomatic 18): dataset_dict._push_to_repo has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":2515}}}],"partialFingerprints":{"codehealthFindingId/v1":"f93669f6aea37fd9c788c3bc8f7764c3ed3f2390bc37c4b45857f80db8486a8f"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDataset._map (cyclomatic 18): IterableDataset._map has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":3771}}}],"partialFingerprints":{"codehealthFindingId/v1":"7a7ea5da8b81633c6b00815100ce3f41a0c561f8ab4a8b59e4286948c3958c23"}},{"ruleId":"D1","level":"warning","message":{"text":"cache._find_hash_in_cache (cyclomatic 18): cache._find_hash_in_cache has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/cache/cache.py"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"682d30b4817ed55be5100db4792c8b60c48f4bd69e0b5037da710f10cbb7485a"}},{"ruleId":"D1","level":"warning","message":{"text":"_dill._save_transformersPreTrainedTokenizerBase (cyclomatic 18): _dill._save_transformersPreTrainedTokenizerBase has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/_dill.py"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"d455bdb71c109fffceb7f5c69a1cce294ac3d494786bf96d7dde88863943199e"}},{"ruleId":"D1","level":"warning","message":{"text":"file_utils._prepare_single_hop_path_and_storage_options (cyclomatic 18): file_utils._prepare_single_hop_path_and_storage_options has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":886}}}],"partialFingerprints":{"codehealthFindingId/v1":"d1b48d6e95b9024157294ece0030535ecd4d4868db9519c50ff7a41dd7a9f915"}},{"ruleId":"D1","level":"warning","message":{"text":"arrow_dataset._concatenate_map_style_datasets (cyclomatic 17): arrow_dataset._concatenate_map_style_datasets 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":7021}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a961e0525b9ca873e213f86aa310fd16511bcd9985088cbcbdf99388e684614"}},{"ruleId":"D1","level":"warning","message":{"text":"arrow_reader.make_file_instructions (cyclomatic 17): arrow_reader.make_file_instructions 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":"src/datasets/arrow_reader.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"4af526ec3bfe041aee7b55fddc85541e69cd51d1e6845dda156f793843f6f1fc"}},{"ruleId":"D1","level":"warning","message":{"text":"GeneratorBasedBuilder._prepare_split (cyclomatic 17): GeneratorBasedBuilder._prepare_split 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":"src/datasets/builder.py"},"region":{"startLine":1352}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ed1abf650f4ff73299d6d1cb430a97fd8b378ea66f378ffe76169e2351bebcb"}},{"ruleId":"D1","level":"warning","message":{"text":"ArrowBasedBuilder._prepare_split (cyclomatic 17): ArrowBasedBuilder._prepare_split 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":"src/datasets/builder.py"},"region":{"startLine":1654}}}],"partialFingerprints":{"codehealthFindingId/v1":"9b5505de44742c32bf65cea370674132a4677b5ce19e99b245c9ee1d3a67154b"}},{"ruleId":"D1","level":"warning","message":{"text":"Audio.encode_example (cyclomatic 17): Audio.encode_example has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"51cba02a9cc84248879429a9b120fd1ddb1f0b146a0e50c665ea1c5e9bd720a8"}},{"ruleId":"D1","level":"warning","message":{"text":"MappedExamplesIterable._iter (cyclomatic 17): MappedExamplesIterable._iter 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":1467}}}],"partialFingerprints":{"codehealthFindingId/v1":"9cb0edf9452c40b46b2d8b259e9cf3455001e8378305f7ba04dac3a01348aeb1"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDataset.push_to_hub (cyclomatic 17): IterableDataset.push_to_hub 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":5320}}}],"partialFingerprints":{"codehealthFindingId/v1":"8da059e1f101d62308773eefd9255652562f5892d8ca794db647e15b851a9050"}},{"ruleId":"D1","level":"warning","message":{"text":"Conll._generate_tables (cyclomatic 17): Conll._generate_tables 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":"src/datasets/packaged_modules/conll/conll.py"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ceaab6f5c9fbc13fa6e6759aa07653285156b9a340069cd5b94041b6bdce71c"}},{"ruleId":"D1","level":"warning","message":{"text":"FolderBasedBuilder._generate_examples (cyclomatic 17): FolderBasedBuilder._generate_examples 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":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d6b11a4905113683970b6c4de8f68eda8a63bcb730eff4ee50db11c43685d9f"}},{"ruleId":"D1","level":"warning","message":{"text":"GenBank._handle_features_line (cyclomatic 17): GenBank._handle_features_line 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":"src/datasets/packaged_modules/genbank/genbank.py"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3197094c367a32337ddd281db7bf92276c8fc6880ba08add365628d49aec52f"}},{"ruleId":"D1","level":"warning","message":{"text":"json.find_mixed_struct_types_field_paths (cyclomatic 17): json.find_mixed_struct_types_field_paths 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":"src/datasets/utils/json.py"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"a9a6afe14105c70fc7338b4cf2640479476c49b6fccd7daa63216f1ae4d3c67e"}},{"ruleId":"D1","level":"warning","message":{"text":"py_utils.convert_file_size_to_int (cyclomatic 17): py_utils.convert_file_size_to_int has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"929bbd3a3da4707fd258b5072bcbcba7178dac5a240a5f621ab51ac9e343b720"}},{"ruleId":"D1","level":"warning","message":{"text":"Dataset.__init__ (cyclomatic 16): Dataset.__init__ has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":712}}}],"partialFingerprints":{"codehealthFindingId/v1":"76f36e7ba87c9e01211585bd57be514619001b4372c6801e401468621801babc"}},{"ruleId":"D1","level":"warning","message":{"text":"arrow_dataset._push_to_repo (cyclomatic 16): arrow_dataset._push_to_repo has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6656}}}],"partialFingerprints":{"codehealthFindingId/v1":"a3124915569a31d493b22c4397db2c6b61b7f395533840651efe244d1878edff"}},{"ruleId":"D1","level":"warning","message":{"text":"DatasetDict.push_to_hub (cyclomatic 16): DatasetDict.push_to_hub has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":1623}}}],"partialFingerprints":{"codehealthFindingId/v1":"61f6fb2ba10db5e9fb6d4a545e46e19a01de57d6d73685a62d4b060f815558a8"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDatasetDict.push_to_hub (cyclomatic 16): IterableDatasetDict.push_to_hub has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":2327}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9fd74f434cad0e1cdc5f6a2dd222a4c43a566e4abb6ad131a52caf92bdaec8c"}},{"ruleId":"D1","level":"warning","message":{"text":"TFFormatter._tensorize (cyclomatic 16): TFFormatter._tensorize has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/tf_formatter.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"dceb3e1ff11be8b8ac6091ffa64fa0c580d0d419ff47cf9054fe5abed68a688c"}},{"ruleId":"D1","level":"warning","message":{"text":"IterableDataset._write_parquet_shards (cyclomatic 16): IterableDataset._write_parquet_shards has cyclomatic complexity 16 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5033}}}],"partialFingerprints":{"codehealthFindingId/v1":"34f235274c48f44c34a3192a1125cd571b6c632d7e1f97628161b7cd6c0fab2a"}},{"ruleId":"D1","level":"warning","message":{"text":"GenBank._handle_header_line (cyclomatic 16): GenBank._handle_header_line has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/genbank/genbank.py"},"region":{"startLine":408}}}],"partialFingerprints":{"codehealthFindingId/v1":"c00f12821c2dd1aabc636a303a1ae597a3566e4b2b1f2cc83f500fbce6b395cf"}},{"ruleId":"D1","level":"warning","message":{"text":"py_utils._single_map_nested (cyclomatic 16): py_utils._single_map_nested has cyclomatic complexity 16 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"e004c6caf9deea077b6ba26778680527483f3bf9a34407af0265ce677cb1cae6"}},{"ruleId":"D2","level":"warning","message":{"text":"Json._generate_tables (cognitive 202): Json._generate_tables has cognitive complexity 202 (threshold 15). Drivers by points: if/else 26 (100 pts), error handling 7 (41 pts), loops 7 (27 pts), ternaries 5 (27 pts), boolean chains 7 (nesting depth added 150). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/json/json.py"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"3190ed5aee1f7c81995ec5ecec218fe72c4c8d60fbf367c06b892c20f6c5b0e8"}},{"ruleId":"D2","level":"warning","message":{"text":"TypedSequence._arrow_array (cognitive 99): TypedSequence._arrow_array has cognitive complexity 99 (threshold 15). Drivers by points: if/else 28 (60 pts), boolean chains 14, error handling 4 (13 pts), loops 2 (8 pts), ternaries 3 (4 pts) (nesting depth added 48). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":323}}}],"partialFingerprints":{"codehealthFindingId/v1":"e0cb1fde219ee2726cfd2b998284e82cc0b293aba78b67b252e002d37b584c0d"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset._map_single (cognitive 96): Dataset._map_single has cognitive complexity 96 (threshold 15). Drivers by points: if/else 34 (72 pts), boolean chains 9, loops 3 (7 pts), error handling 3 (6 pts), ternaries 1 (2 pts) (nesting depth added 46). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":3660}}}],"partialFingerprints":{"codehealthFindingId/v1":"0679b67cc524ea4e3e52b5ea457baa3e6ddf356a6b49a7532e6c276d1885d8fb"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.map (cognitive 93): Dataset.map has cognitive complexity 93 (threshold 15). Drivers by points: if/else 46 (61 pts), loops 6 (15 pts), boolean chains 11, ternaries 3 (4 pts), error handling 1 (2 pts) (nesting depth added 26). 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":3205}}}],"partialFingerprints":{"codehealthFindingId/v1":"e864beeba1d527b0eb4a5ff364c10a8c00f517cce769a82978728a1b52513cf6"}},{"ruleId":"D2","level":"warning","message":{"text":"features._cast_to_python_objects (cognitive 68): features._cast_to_python_objects has cognitive complexity 68 (threshold 15). Drivers by points: if/else 26 (38 pts), boolean chains 23, loops 2 (5 pts), ternaries 1 (2 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":286}}}],"partialFingerprints":{"codehealthFindingId/v1":"20f5abfaa1bf6f8b37ec6fcb5777e5618254a28e9151fed1969a64d89982c96e"}},{"ruleId":"D2","level":"warning","message":{"text":"load.dataset_module_factory (cognitive 66): load.dataset_module_factory has cognitive complexity 66 (threshold 15). Drivers by points: if/else 16 (34 pts), error handling 13 (27 pts), boolean chains 5 (nesting depth added 32). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":957}}}],"partialFingerprints":{"codehealthFindingId/v1":"22bd4044e0302e5800477d8b618bbffc7e75078d7f925d0e3ff5d1869616121e"}},{"ruleId":"D2","level":"warning","message":{"text":"Lance._split_generators (cognitive 64): Lance._split_generators has cognitive complexity 64 (threshold 15). Drivers by points: if/else 15 (43 pts), loops 4 (12 pts), error handling 1 (6 pts), boolean chains 3 (nesting depth added 41). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/lance/lance.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"17df06f10f63657c8f1d51ed06abef1cba3eb652b924a2f317a4d2624d856440"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.train_test_split (cognitive 62): Dataset.train_test_split has cognitive complexity 62 (threshold 15). Drivers by points: if/else 27 (39 pts), boolean chains 17, ternaries 2 (4 pts), error handling 1 (2 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4967}}}],"partialFingerprints":{"codehealthFindingId/v1":"a174538f8a112e47136db66bdcb9cc2b83e6de46be644752485fd66a2fc3b899"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset._get_updated_dataset_card (cognitive 57): arrow_dataset._get_updated_dataset_card has cognitive complexity 57 (threshold 15). Drivers by points: if/else 19 (33 pts), boolean chains 9, loops 4 (7 pts), ternaries 4 (6 pts), error handling 2 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6887}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e064ab02df18153de487f13bb95347c0d31d0f2dc1c555709a0f5ab5088659c"}},{"ruleId":"D2","level":"warning","message":{"text":"MappedExamplesIterable._iter_arrow (cognitive 57): MappedExamplesIterable._iter_arrow has cognitive complexity 57 (threshold 15). Drivers by points: if/else 20 (40 pts), loops 3 (7 pts), ternaries 4 (6 pts), boolean chains 4 (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":1678}}}],"partialFingerprints":{"codehealthFindingId/v1":"50789b96c4e3e476e9c47b7722fb0eeb3c75f2b1430804b19594035d19ad0b44"}},{"ruleId":"D2","level":"warning","message":{"text":"table.cast_array_to_feature (cognitive 55): table.cast_array_to_feature has cognitive complexity 55 (threshold 15). Drivers by points: if/else 21 (48 pts), boolean chains 4, ternaries 1 (3 pts) (nesting depth added 29). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":2020}}}],"partialFingerprints":{"codehealthFindingId/v1":"b76f5fea375a7fa0d90e29c749332c37e247d4861004c3fef87e6cc16162ac86"}},{"ruleId":"D2","level":"warning","message":{"text":"FolderBasedBuilder._read_metadata (cognitive 54): FolderBasedBuilder._read_metadata has cognitive complexity 54 (threshold 15). Drivers by points: if/else 13 (28 pts), loops 4 (9 pts), ternaries 4 (8 pts), error handling 2 (7 pts), boolean chains 2 (nesting depth added 29). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"87e0839e82564000c0d07d53bdcc622eb5a51d42b956e1bbe06888171f4f907b"}},{"ruleId":"D2","level":"warning","message":{"text":"RebatchedArrowExamplesIterable._iter_arrow (cognitive 53): RebatchedArrowExamplesIterable._iter_arrow has cognitive complexity 53 (threshold 15). Drivers by points: if/else 19 (41 pts), boolean chains 7, loops 2 (3 pts), ternaries 2 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":529}}}],"partialFingerprints":{"codehealthFindingId/v1":"bbb6c28c55b413b3db6161704d0d969e0346032ee6a7847bb5135ce9db51f2a5"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset._interleave_map_style_datasets (cognitive 51): arrow_dataset._interleave_map_style_datasets has cognitive complexity 51 (threshold 15). Drivers by points: if/else 14 (33 pts), loops 5 (10 pts), boolean chains 4, ternaries 2 (4 pts) (nesting depth added 26). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":7135}}}],"partialFingerprints":{"codehealthFindingId/v1":"7711a9b90ab6b1246f067c55ef6b7842c2f33b4f2ab46775b4ac44c30ea33910"}},{"ruleId":"D2","level":"warning","message":{"text":"FolderBasedBuilder._split_generators (cognitive 51): FolderBasedBuilder._split_generators has cognitive complexity 51 (threshold 15). Drivers by points: if/else 16 (31 pts), loops 5 (12 pts), boolean chains 4, ternaries 1 (4 pts) (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"62f41bbe449e74719f49eff7e451b4889c8d11ea8cb9c5799035f895676fe216"}},{"ruleId":"D2","level":"warning","message":{"text":"TensorflowDatasetMixin.to_tf_dataset (cognitive 49): TensorflowDatasetMixin.to_tf_dataset has cognitive complexity 49 (threshold 15). Drivers by points: if/else 27 (38 pts), boolean chains 8, loops 2, ternaries 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":336}}}],"partialFingerprints":{"codehealthFindingId/v1":"d14f2d00247b79f30e661652c531c81cd641ac39c35db21a58e6aaa68695491e"}},{"ruleId":"D2","level":"warning","message":{"text":"FolderBasedBuilder._generate_examples (cognitive 48): FolderBasedBuilder._generate_examples has cognitive complexity 48 (threshold 15). Drivers by points: if/else 9 (24 pts), loops 6 (19 pts), ternaries 1 (3 pts), boolean chains 2 (nesting depth added 30). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"24150d8b64d5346e08f220c93aa299aafdfdb8c055c104f911b00e0cec256964"}},{"ruleId":"D2","level":"warning","message":{"text":"features.decode_nested_example (cognitive 47): features.decode_nested_example has cognitive complexity 47 (threshold 15). Drivers by points: if/else 12 (34 pts), loops 2 (8 pts), ternaries 2 (4 pts), boolean chains 1 (nesting depth added 30). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":1546}}}],"partialFingerprints":{"codehealthFindingId/v1":"055894cc700d0178699d7df8bcc7dc596d02065ea978dfa387956bace422ddd9"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_reader.make_file_instructions (cognitive 45): arrow_reader.make_file_instructions has cognitive complexity 45 (threshold 15). Drivers by points: ternaries 5 (19 pts), if/else 7 (18 pts), loops 3 (7 pts), boolean chains 1 (nesting depth added 29). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_reader.py"},"region":{"startLine":92}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2b5712876565076817e74734f68bdf7624cf4549881fa4399ac517f5eb8510a"}},{"ruleId":"D2","level":"warning","message":{"text":"TsFile._scan_metadata (cognitive 45): TsFile._scan_metadata has cognitive complexity 45 (threshold 15). Drivers by points: if/else 13 (29 pts), ternaries 3 (7 pts), loops 3 (5 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":302}}}],"partialFingerprints":{"codehealthFindingId/v1":"67384903e8ed089e7fcd1a53af0570f5bc74ca1d4a58dd67266e746ccc6bfa70"}},{"ruleId":"D2","level":"warning","message":{"text":"Conll._generate_tables (cognitive 44): Conll._generate_tables has cognitive complexity 44 (threshold 15). Drivers by points: if/else 8 (28 pts), loops 4 (10 pts), ternaries 1 (4 pts), boolean chains 2 (nesting depth added 29). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/conll/conll.py"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"334b6477532db4c13f7ea113a86dbd716314bc6a6aa3a8bb2a524010914b5054"}},{"ruleId":"D2","level":"warning","message":{"text":"table.array_cast (cognitive 44): table.array_cast has cognitive complexity 44 (threshold 15). Drivers by points: if/else 17 (39 pts), boolean chains 5 (nesting depth added 22). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":1907}}}],"partialFingerprints":{"codehealthFindingId/v1":"d7de5ae30906b9d73d1ca4ed9961852dcecba5507a5b3aa6ec516a9c8a514763"}},{"ruleId":"D2","level":"warning","message":{"text":"py_utils.map_nested (cognitive 43): py_utils.map_nested has cognitive complexity 43 (threshold 15). Drivers by points: if/else 19 (36 pts), boolean chains 6, ternaries 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":416}}}],"partialFingerprints":{"codehealthFindingId/v1":"98d08bb5908db5ceef7051bb2aed8432cc39028bafa5b079430aa2c84b116d3d"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetBuilder._create_builder_config (cognitive 42): DatasetBuilder._create_builder_config has cognitive complexity 42 (threshold 15). Drivers by points: if/else 18 (31 pts), boolean chains 7, loops 1 (2 pts), ternaries 1 (2 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":514}}}],"partialFingerprints":{"codehealthFindingId/v1":"16880afd56ef19e1bbeeca1ab7e5bdfc6b10885c26de3b221a720095445d3fac"}},{"ruleId":"D2","level":"warning","message":{"text":"Fastq._parse_fastq (cognitive 42): Fastq._parse_fastq has cognitive complexity 42 (threshold 15). Drivers by points: if/else 11 (29 pts), ternaries 3 (6 pts), loops 3 (5 pts), boolean chains 2 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fastq/fastq.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"960aa7f08b381cf420b41403833984d412cb2ba5aedc1bb2353f938ce69bcbd2"}},{"ruleId":"D2","level":"warning","message":{"text":"NumpyArrowExtractor._arrow_array_to_numpy (cognitive 40): NumpyArrowExtractor._arrow_array_to_numpy has cognitive complexity 40 (threshold 15). Drivers by points: if/else 12 (25 pts), boolean chains 13, loops 1 (2 pts) (nesting depth added 14). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/formatting.py"},"region":{"startLine":166}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6d406bc63df842c242d29f95d748caf52679e556e90cc76b5b704a93b10daea"}},{"ruleId":"D2","level":"warning","message":{"text":"Text._generate_tables (cognitive 39): Text._generate_tables has cognitive complexity 39 (threshold 15). Drivers by points: if/else 6 (27 pts), loops 4 (11 pts), ternaries 1 (nesting depth added 28). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/text/text.py"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a46cc34b4f9b64b9b5bf2f44e1877c1933a59492752b8cec09f2c00f77278fd"}},{"ruleId":"D2","level":"warning","message":{"text":"CyclingMultiSourcesExamplesIterable._iter_arrow (cognitive 38): CyclingMultiSourcesExamplesIterable._iter_arrow has cognitive complexity 38 (threshold 15). Drivers by points: if/else 14 (31 pts), loops 4 (5 pts), boolean chains 1, ternaries 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (CyclingMultiSourcesExamplesIterable.__iter__) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":828}}}],"partialFingerprints":{"codehealthFindingId/v1":"a993a6c6953c8396686f41e51385aa25964c4c11d670d6d0f40d372dd667aa04"}},{"ruleId":"D2","level":"warning","message":{"text":"CyclingMultiSourcesExamplesIterable.__iter__ (cognitive 38): CyclingMultiSourcesExamplesIterable.__iter__ has cognitive complexity 38 (threshold 15). Drivers by points: if/else 14 (31 pts), loops 4 (5 pts), boolean chains 1, ternaries 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (CyclingMultiSourcesExamplesIterable._iter_arrow) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":903}}}],"partialFingerprints":{"codehealthFindingId/v1":"df032b1464a8a1474f0d746c5328396d09310122e1585b394efe68a6ba590345"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset._concatenate_map_style_datasets (cognitive 37): arrow_dataset._concatenate_map_style_datasets has cognitive complexity 37 (threshold 15). Drivers by points: if/else 18 (28 pts), loops 3 (9 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":7021}}}],"partialFingerprints":{"codehealthFindingId/v1":"06e5a06fcdd436b73051b0b2d043728acfae49270b1e300320ec4ed01695b87e"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetBuilder.__init__ (cognitive 37): DatasetBuilder.__init__ has cognitive complexity 37 (threshold 15). Drivers by points: if/else 13 (22 pts), boolean chains 6, loops 2 (5 pts), ternaries 4 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":308}}}],"partialFingerprints":{"codehealthFindingId/v1":"23c99b395752e7bf0c9882dddfde640fe2863d6aa112d61d9216cd11391eaf67"}},{"ruleId":"D2","level":"warning","message":{"text":"dataset_dict._push_to_repo (cognitive 37): dataset_dict._push_to_repo has cognitive complexity 37 (threshold 15). Drivers by points: if/else 8 (16 pts), loops 4 (7 pts), error handling 2 (6 pts), boolean chains 4, ternaries 2 (4 pts) (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":2515}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbf6fb92b1ebe28c3efb722ef8bbdf17548c1e94f9bcc31748cf5909fa825b6f"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset._prepare_ex_iterable_for_iteration (cognitive 37): IterableDataset._prepare_ex_iterable_for_iteration has cognitive complexity 37 (threshold 15). Drivers by points: if/else 12 (24 pts), boolean chains 7, ternaries 1 (4 pts), error handling 1 (2 pts) (nesting depth added 16). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2958}}}],"partialFingerprints":{"codehealthFindingId/v1":"943ccbcc1057842119933ae04b76323d0f05ed2f0de2f6850f9ceeeeb725821e"}},{"ruleId":"D2","level":"warning","message":{"text":"features.string_to_arrow (cognitive 36): features.string_to_arrow has cognitive complexity 36 (threshold 15). Drivers by points: if/else 24 (36 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"e473e104584a235f3e0513d4d02d83341d25689e50eeb0d1230d4d6be95aec02"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset._push_to_repo (cognitive 35): arrow_dataset._push_to_repo has cognitive complexity 35 (threshold 15). Drivers by points: if/else 8 (16 pts), error handling 2 (6 pts), loops 3 (6 pts), ternaries 2 (4 pts), boolean chains 3 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6656}}}],"partialFingerprints":{"codehealthFindingId/v1":"4ec8e5953347a6f6f97dc3f33e16cde7950d1efb22c3bded9158f63362212fd9"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset.get_indices_from_mask_function (cognitive 35): arrow_dataset.get_indices_from_mask_function has cognitive complexity 35 (threshold 15). Drivers by points: if/else 13 (29 pts), loops 2 (6 pts) (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (arrow_dataset.async_get_indices_from_mask_function) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":7370}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a138cf56185cac5b78f7ba2a4c45c73662da66d6b0e53acbfaf48fc930a6089"}},{"ruleId":"D2","level":"warning","message":{"text":"arrow_dataset.async_get_indices_from_mask_function (cognitive 35): arrow_dataset.async_get_indices_from_mask_function has cognitive complexity 35 (threshold 15). Drivers by points: if/else 13 (29 pts), loops 2 (6 pts) (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body. This shape REPEATS in the file: one other method here (arrow_dataset.get_indices_from_mask_function) has the same decision points, in the same order, at the same nesting depths \u2014 so this is one pattern written twice rather than two separate problems. Splitting this body alone leaves the other exactly as it is. Where these are variations on one operation, the change that clears both is the shared one: lift the common shape into a single routine the variants call, parameterised by whatever genuinely differs between them, and keep in each method only the part that is not shared."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":7428}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a7c6eb024d652e5888f431f9de9e9bb6fb5cfbdc5529470e7d46edb4f7bee4f"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset._write_parquet_shards (cognitive 34): IterableDataset._write_parquet_shards has cognitive complexity 34 (threshold 15). Drivers by points: loops 8 (17 pts), if/else 4 (11 pts), error handling 2 (5 pts), boolean chains 1 (nesting depth added 19). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5033}}}],"partialFingerprints":{"codehealthFindingId/v1":"eca680d3c8d7e3aa2383867da5e00d9dae32bd99dd01a79ae4b4e5cae68f28e8"}},{"ruleId":"D2","level":"warning","message":{"text":"TsFile._read_device_from_file (cognitive 34): TsFile._read_device_from_file has cognitive complexity 34 (threshold 15). Drivers by points: if/else 14 (21 pts), ternaries 5 (8 pts), loops 3 (4 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":537}}}],"partialFingerprints":{"codehealthFindingId/v1":"0136175f99d86b0042b1b58c0907eba5f3ca6329defe0ab19cbdba69a31cf1d4"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.save_to_disk (cognitive 33): Dataset.save_to_disk has cognitive complexity 33 (threshold 15). Drivers by points: if/else 11 (17 pts), loops 4 (8 pts), boolean chains 5, error handling 1 (2 pts), ternaries 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":1781}}}],"partialFingerprints":{"codehealthFindingId/v1":"6b0e1a00077dbb1a823f9d506e666b8a00ed06c690431ea2ed1deb6c3118f0fe"}},{"ruleId":"D2","level":"warning","message":{"text":"Fasta._parse_fasta (cognitive 33): Fasta._parse_fasta has cognitive complexity 33 (threshold 15). Drivers by points: if/else 8 (21 pts), loops 3 (6 pts), ternaries 3 (6 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a64dd39467b859f3340a0894d703125ec13deddd60558aec8523df039c98916"}},{"ruleId":"D2","level":"warning","message":{"text":"Pickler.save (cognitive 33): Pickler.save has cognitive complexity 33 (threshold 15). Drivers by points: if/else 14 (33 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/_dill.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1c3031dd401d6067dae7a93d1135ba78ce772f66ede219ce6ff468d3cba00c3"}},{"ruleId":"D2","level":"warning","message":{"text":"json.find_mixed_struct_types_field_paths (cognitive 33): json.find_mixed_struct_types_field_paths has cognitive complexity 33 (threshold 15). Drivers by points: if/else 9 (24 pts), loops 2 (5 pts), boolean chains 4 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/json.py"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"f43a074e19a650b9a1eeb1e78cd2381c4ea484b6236fe9c1b51c3024479487dc"}},{"ruleId":"D2","level":"warning","message":{"text":"RandomlyCyclingMultiSourcesExamplesIterable._get_indices_iterator (cognitive 32): RandomlyCyclingMultiSourcesExamplesIterable._get_indices_iterator has cognitive complexity 32 (threshold 15). Drivers by points: if/else 7 (21 pts), loops 4 (10 pts), ternaries 1 (nesting depth added 20). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":1271}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa6a99a885f01378a3529f41bb47ed6d71b6efbf3487ab2cd00cb7fc22551f39"}},{"ruleId":"D2","level":"warning","message":{"text":"file_utils.cached_path (cognitive 32): file_utils.cached_path has cognitive complexity 32 (threshold 15). Drivers by points: if/else 14 (21 pts), ternaries 1 (5 pts), boolean chains 3, error handling 1 (3 pts) (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":129}}}],"partialFingerprints":{"codehealthFindingId/v1":"5d3c27818067d4fed8dd3e55e5ab808546f950cdfbc9cd323b1ba6f51a580936"}},{"ruleId":"D2","level":"warning","message":{"text":"TensorflowDatasetMixin._get_output_signature (cognitive 31): TensorflowDatasetMixin._get_output_signature has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (24 pts), loops 4 (6 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":239}}}],"partialFingerprints":{"codehealthFindingId/v1":"64cb248e608f34136c992bb7f65fa860253d60ae460350b9b4fc8b016994fb0b"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetBuilder.download_and_prepare (cognitive 31): DatasetBuilder.download_and_prepare has cognitive complexity 31 (threshold 15). Drivers by points: if/else 14 (16 pts), boolean chains 9, ternaries 5 (6 pts) (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":702}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf75dd81107e41cf88fd7664a5b57b303c320741f06259c82b208c48d54d0dfe"}},{"ruleId":"D2","level":"warning","message":{"text":"features.encode_nested_example (cognitive 31): features.encode_nested_example has cognitive complexity 31 (threshold 15). Drivers by points: if/else 7 (18 pts), error handling 1 (4 pts), loops 1 (4 pts), ternaries 2 (4 pts), boolean chains 1 (nesting depth added 19). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":1506}}}],"partialFingerprints":{"codehealthFindingId/v1":"a104c086d4da864f4467303cb60ffc47e0faf77da20e51c0945353ca0d7744df"}},{"ruleId":"D2","level":"warning","message":{"text":"data_files._get_data_files_patterns (cognitive 30): data_files._get_data_files_patterns has cognitive complexity 30 (threshold 15). Drivers by points: if/else 5 (14 pts), loops 5 (10 pts), error handling 2 (6 pts) (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/data_files.py"},"region":{"startLine":259}}}],"partialFingerprints":{"codehealthFindingId/v1":"b31f4bc7e2ceadebd69432d4ef7c5f403c1865ef3097f757153b9fcbbf186749"}},{"ruleId":"D2","level":"warning","message":{"text":"Fastq._generate_tables (cognitive 30): Fastq._generate_tables has cognitive complexity 30 (threshold 15). Drivers by points: if/else 9 (26 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fastq/fastq.py"},"region":{"startLine":244}}}],"partialFingerprints":{"codehealthFindingId/v1":"67a530d10c2157056e0289b1dc77f2a684ff6d654f6fbc5107348eaf869a7576"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowWriter._write_batch (cognitive 29): ArrowWriter._write_batch has cognitive complexity 29 (threshold 15). Drivers by points: if/else 8 (12 pts), ternaries 6 (11 pts), boolean chains 5, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":759}}}],"partialFingerprints":{"codehealthFindingId/v1":"5319bf762a8f94038c267079b4644a9a39e85b26b543447736596850cc2f9a5e"}},{"ruleId":"D2","level":"warning","message":{"text":"data_files.resolve_pattern (cognitive 29): data_files.resolve_pattern has cognitive complexity 29 (threshold 15). Drivers by points: if/else 13 (20 pts), ternaries 4 (5 pts), boolean chains 3, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/data_files.py"},"region":{"startLine":303}}}],"partialFingerprints":{"codehealthFindingId/v1":"b417ba63d6e123c9ded99fc41add196f53e79c93de8946714a4dac3f22f2d100"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowExamplesIterable.__iter__ (cognitive 29): ArrowExamplesIterable.__iter__ has cognitive complexity 29 (threshold 15). Drivers by points: if/else 4 (16 pts), loops 4 (10 pts), ternaries 2 (3 pts) (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":413}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39746c823c9a919f87321e6ae45c9839b9c8ef0b0726e61baea5c29c473b05d"}},{"ruleId":"D2","level":"warning","message":{"text":"GenBank._generate_tables (cognitive 29): GenBank._generate_tables has cognitive complexity 29 (threshold 15). Drivers by points: if/else 7 (20 pts), loops 3 (6 pts), boolean chains 3 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/genbank/genbank.py"},"region":{"startLine":651}}}],"partialFingerprints":{"codehealthFindingId/v1":"15f52d3c83a33d598715294199028a06f5b97930828af92721fd757dc09f751c"}},{"ruleId":"D2","level":"warning","message":{"text":"FaissIndex.add_vectors (cognitive 29): FaissIndex.add_vectors has cognitive complexity 29 (threshold 15). Drivers by points: if/else 12 (18 pts), ternaries 3 (6 pts), boolean chains 4, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/search.py"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"5367b2c6c25fe177aee724bb2af13a4fef77e1681e614a25ccc96e8bd21aa3e8"}},{"ruleId":"D2","level":"warning","message":{"text":"MappedExamplesIterable._iter (cognitive 28): MappedExamplesIterable._iter has cognitive complexity 28 (threshold 15). Drivers by points: if/else 10 (13 pts), error handling 3 (6 pts), loops 2 (4 pts), ternaries 2 (3 pts), boolean chains 2 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":1467}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfcfd6b9271245f82849af02c2b45654d6a75491c35d4929578170155c6ac749"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneratorBasedBuilder._prepare_split (cognitive 27): GeneratorBasedBuilder._prepare_split has cognitive complexity 27 (threshold 15). Drivers by points: if/else 14 (19 pts), boolean chains 4, loops 2 (4 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1352}}}],"partialFingerprints":{"codehealthFindingId/v1":"ac68960e8c8043cb404138c8acaab4f734777040990706d03fad9ad65b0c9ac0"}},{"ruleId":"D2","level":"warning","message":{"text":"Nifti.decode_example (cognitive 27): Nifti.decode_example has cognitive complexity 27 (threshold 15). Drivers by points: if/else 12 (18 pts), ternaries 2 (8 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/nifti.py"},"region":{"startLine":150}}}],"partialFingerprints":{"codehealthFindingId/v1":"382f4c736c1e4f0b4f0952dda0a193e7888e25a8d8ce992581444c7779d6cdd8"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset._push_parquet_shards_to_hub (cognitive 27): IterableDataset._push_parquet_shards_to_hub has cognitive complexity 27 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 6, ternaries 5 (6 pts), loops 2 (4 pts) (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5188}}}],"partialFingerprints":{"codehealthFindingId/v1":"888da759eb7113359dbed6a2c04429a9ec39ed69dd7555e61e22c8f36510dcd7"}},{"ruleId":"D2","level":"warning","message":{"text":"Fasta._generate_tables (cognitive 27): Fasta._generate_tables has cognitive complexity 27 (threshold 15). Drivers by points: if/else 8 (23 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":218}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6a25e5f938fe813e5fa009112522d8b059d344e4b5f41e968655110c13af3e4"}},{"ruleId":"D2","level":"warning","message":{"text":"TypedSequence._infer_custom_type_and_encode (cognitive 26): TypedSequence._infer_custom_type_and_encode has cognitive complexity 26 (threshold 15). Drivers by points: ternaries 4 (12 pts), if/else 6 (10 pts), boolean chains 4 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"c6639542204d583bd856d5986c5054afb2af076aceb02327761812f820335a91"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowBasedBuilder._prepare_split (cognitive 26): ArrowBasedBuilder._prepare_split has cognitive complexity 26 (threshold 15). Drivers by points: if/else 12 (17 pts), boolean chains 4, loops 2 (4 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":"src/datasets/builder.py"},"region":{"startLine":1654}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7548e0529bedbff8e51f51fbd7a9fd2ba3098d098f62e816818e6289fe25d54"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset._map (cognitive 26): IterableDataset._map has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (14 pts), ternaries 3 (7 pts), boolean chains 5 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":3771}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b01e3d5e3eec1c39873fcdea9acc888ebf94f654e1e44ac21c87a392b54c6be"}},{"ruleId":"D2","level":"warning","message":{"text":"file_utils._prepare_single_hop_path_and_storage_options (cognitive 26): file_utils._prepare_single_hop_path_and_storage_options has cognitive complexity 26 (threshold 15). Drivers by points: if/else 10 (18 pts), boolean chains 3, loops 1 (3 pts), ternaries 2 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":886}}}],"partialFingerprints":{"codehealthFindingId/v1":"25070e88c601355cf385a8cbdd1bd9b56b310a250b4f6c25b2fe7949eb82ee28"}},{"ruleId":"D2","level":"warning","message":{"text":"HorizontallyConcatenatedMultiSourcesExamplesIterable._iter_arrow (cognitive 25): HorizontallyConcatenatedMultiSourcesExamplesIterable._iter_arrow has cognitive complexity 25 (threshold 15). Drivers by points: if/else 5 (11 pts), loops 4 (11 pts), error handling 1 (3 pts) (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":1190}}}],"partialFingerprints":{"codehealthFindingId/v1":"826f08239027729a3644757a3a1395e69d843fca5f04e746cd704d59e94844b3"}},{"ruleId":"D2","level":"warning","message":{"text":"FormattedExamplesIterable.__iter__ (cognitive 25): FormattedExamplesIterable.__iter__ has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 3 (7 pts), ternaries 3 (6 pts), boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2541}}}],"partialFingerprints":{"codehealthFindingId/v1":"030eb21378e54e9b357cc6555cfea73555c440e7b1aa21b13843f55114717a8e"}},{"ruleId":"D2","level":"warning","message":{"text":"TsFile._build_device_index (cognitive 25): TsFile._build_device_index has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (17 pts), loops 3 (5 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"d6a4671e51a2eaaeeed565d7915f459487ff42ed66a0a5e976df41e09e474f17"}},{"ruleId":"D2","level":"warning","message":{"text":"FilesIterable._iter_from_urlpaths (cognitive 25): FilesIterable._iter_from_urlpaths has cognitive complexity 25 (threshold 15). Drivers by points: if/else 6 (17 pts), loops 3 (8 pts) (nesting depth added 16). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":1438}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4116f417f66fe04c4b337ba5a91df06f63c02aa08817fa392c75144075636f3"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.shuffle (cognitive 24): Dataset.shuffle has cognitive complexity 24 (threshold 15). Drivers by points: if/else 12 (15 pts), ternaries 3 (5 pts), boolean chains 4 (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":"src/datasets/arrow_dataset.py"},"region":{"startLine":4827}}}],"partialFingerprints":{"codehealthFindingId/v1":"cb3f22d6239fdab1bd87da8ccdcc99dd1c8f3a2148904eba4ee7b7fbfc532802"}},{"ruleId":"D2","level":"warning","message":{"text":"TorchFormatter._tensorize (cognitive 24): TorchFormatter._tensorize has cognitive complexity 24 (threshold 15). Drivers by points: if/else 10 (16 pts), boolean chains 6, error handling 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/torch_formatter.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c10b18a04d612767dc5894123b1afa5f5d9e71bdc97d8f11b3aaec3bd15150c"}},{"ruleId":"D2","level":"warning","message":{"text":"TsFile._iter_device_batches (cognitive 24): TsFile._iter_device_batches has cognitive complexity 24 (threshold 15). Drivers by points: if/else 6 (15 pts), loops 3 (6 pts), error handling 1 (3 pts) (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":503}}}],"partialFingerprints":{"codehealthFindingId/v1":"85ab22f7bb5af630b700218685b07ab64b70fa920eda6385056184b718ff583b"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.sort (cognitive 23): Dataset.sort has cognitive complexity 23 (threshold 15). Drivers by points: if/else 13 (18 pts), boolean chains 2, ternaries 2, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4697}}}],"partialFingerprints":{"codehealthFindingId/v1":"b6af6469fcc164a12ff84fd9d9e0fa356f46f9c6245c6d54f122fbd53940a5a1"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowBasedBuilder._prepare_split_single (cognitive 23): ArrowBasedBuilder._prepare_split_single has cognitive complexity 23 (threshold 15). Drivers by points: if/else 8 (15 pts), error handling 2 (3 pts), boolean chains 2, ternaries 2, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1811}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd94a8b49f07abd95c965dd5bb9024c8db1a7e400f0ad5a6dae95986be48ab22"}},{"ruleId":"D2","level":"warning","message":{"text":"JaxFormatter._tensorize (cognitive 23): JaxFormatter._tensorize has cognitive complexity 23 (threshold 15). Drivers by points: if/else 11 (15 pts), boolean chains 6, error handling 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"d65b4094271c34b0081b07814085753916b0931e52cd7f3b99355bb39a3e45ac"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset.push_to_hub (cognitive 23): IterableDataset.push_to_hub has cognitive complexity 23 (threshold 15). Drivers by points: if/else 10 (12 pts), error handling 2 (4 pts), ternaries 2 (4 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5320}}}],"partialFingerprints":{"codehealthFindingId/v1":"92b131abcf87972e1ee7e9ee9c89d77a458bb501f0b767a616b4ea45c7c6ad79"}},{"ruleId":"D2","level":"warning","message":{"text":"Parquet._split_generators (cognitive 23): Parquet._split_generators has cognitive complexity 23 (threshold 15). Drivers by points: if/else 7 (14 pts), error handling 1 (4 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"1db87e910b41f577e948fa6cf2317d1213a6496e1e3d706f5eb87c1aa1684f6b"}},{"ruleId":"D2","level":"warning","message":{"text":"Parquet._generate_tables (cognitive 23): Parquet._generate_tables has cognitive complexity 23 (threshold 15). Drivers by points: if/else 7 (13 pts), loops 2 (4 pts), boolean chains 3, error handling 1 (2 pts), ternaries 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":185}}}],"partialFingerprints":{"codehealthFindingId/v1":"d289a0e82825432d600b514b0b8940eb521d10de77fa7afaf12a0e7cbfd42317"}},{"ruleId":"D2","level":"warning","message":{"text":"TsFile._finalize_device (cognitive 23): TsFile._finalize_device has cognitive complexity 23 (threshold 15). Drivers by points: if/else 7 (13 pts), ternaries 3 (5 pts), loops 3 (4 pts), boolean chains 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":627}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ce33312965951a46f5c30900bc18ea7af79ed64485de709442aea4d55d7667f"}},{"ruleId":"D2","level":"warning","message":{"text":"patch_submodule.__enter__ (cognitive 23): patch_submodule.__enter__ has cognitive complexity 23 (threshold 15). Drivers by points: loops 4 (9 pts), if/else 4 (8 pts), error handling 2 (4 pts), boolean chains 2 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/patching.py"},"region":{"startLine":48}}}],"partialFingerprints":{"codehealthFindingId/v1":"a46768304c90ca5abeb06d5f1d904c3c148356449c61d532e4bb44e38239c2c4"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.from_dict (cognitive 22): Dataset.from_dict has cognitive complexity 22 (threshold 15). Drivers by points: ternaries 6 (13 pts), if/else 6 (7 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":983}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5b3a6d023f2a83e90c5b3834d2a8a47148b33644455f40df12413db7700861f"}},{"ruleId":"D2","level":"warning","message":{"text":"fingerprint.format_kwargs_for_fingerprint (cognitive 22): fingerprint.format_kwargs_for_fingerprint has cognitive complexity 22 (threshold 15). Drivers by points: if/else 11 (16 pts), ternaries 1 (3 pts), boolean chains 2, loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/fingerprint.py"},"region":{"startLine":333}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7642d98ccf23ece1b28e48f8dbe70b4b769c3b3f27133efd4a7c339466456fb"}},{"ruleId":"D2","level":"warning","message":{"text":"HubDatasetModuleFactory.get_module (cognitive 22): HubDatasetModuleFactory.get_module has cognitive complexity 22 (threshold 15). Drivers by points: if/else 13, error handling 4 (5 pts), boolean chains 4 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":577}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a68284a92668b2475a3d973f562d73cc6714869f9856efe787f879be3aaa8e2"}},{"ruleId":"D2","level":"warning","message":{"text":"_dill._save_transformersPreTrainedTokenizerBase (cognitive 22): _dill._save_transformersPreTrainedTokenizerBase has cognitive complexity 22 (threshold 15). Drivers by points: if/else 8 (12 pts), boolean chains 7, error handling 2 (3 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/_dill.py"},"region":{"startLine":246}}}],"partialFingerprints":{"codehealthFindingId/v1":"09f039cc32221cd2e5f92d657c9580762ad7db81946c44ad12ee3655cbd9625c"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.push_to_hub (cognitive 21): Dataset.push_to_hub has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (11 pts), error handling 2 (4 pts), ternaries 2 (4 pts), boolean chains 2 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6070}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e7ae398306c5f810587d0f2f4481d0bb91d69951f7062c4c1805a03c52ffd47"}},{"ruleId":"D2","level":"warning","message":{"text":"data_files.sanitize_patterns (cognitive 21): data_files.sanitize_patterns has cognitive complexity 21 (threshold 15). Drivers by points: if/else 6 (12 pts), ternaries 2 (5 pts), loops 1 (3 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/data_files.py"},"region":{"startLine":123}}}],"partialFingerprints":{"codehealthFindingId/v1":"1b4820781c7fdb752edeae39b3c63759240d38f4aed2bfec88d570a70e7c4b18"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetDict.push_to_hub (cognitive 21): DatasetDict.push_to_hub has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (12 pts), error handling 2 (4 pts), boolean chains 2, ternaries 1 (2 pts), loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":1623}}}],"partialFingerprints":{"codehealthFindingId/v1":"8ecbfadd6d16457260ceedd46251da569ecf8e468880c7277f2c7ebc97f282ed"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDatasetDict.push_to_hub (cognitive 21): IterableDatasetDict.push_to_hub has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (12 pts), error handling 2 (4 pts), boolean chains 2, ternaries 1 (2 pts), loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":2327}}}],"partialFingerprints":{"codehealthFindingId/v1":"8975dd6b72e7c01268b93c98a0930584df948e771c3c559f9dc1511166c7e448"}},{"ruleId":"D2","level":"warning","message":{"text":"cache._find_hash_in_cache (cognitive 21): cache._find_hash_in_cache has cognitive complexity 21 (threshold 15). Drivers by points: boolean chains 9, if/else 7 (8 pts), ternaries 2 (4 pts) (nesting depth added 3). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/cache/cache.py"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a580ec8db61c6e226e967631741f0ec6fc0844e5e42855a7b58454ec535268a"}},{"ruleId":"D2","level":"warning","message":{"text":"WebDataset._generate_examples (cognitive 21): WebDataset._generate_examples has cognitive complexity 21 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 4 (9 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/webdataset/webdataset.py"},"region":{"startLine":116}}}],"partialFingerprints":{"codehealthFindingId/v1":"f1f485745bb3fbc93e6d174e357e44d5bbe188c717d27265607b1132191d9c0e"}},{"ruleId":"D2","level":"warning","message":{"text":"py_utils.convert_file_size_to_int (cognitive 21): py_utils.convert_file_size_to_int has cognitive complexity 21 (threshold 15). Drivers by points: if/else 11, ternaries 5 (10 pts) (nesting depth added 5). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":95}}}],"partialFingerprints":{"codehealthFindingId/v1":"8620999898f20bd40fc8c1734862c74c5ddffcf4b831683a04e6fff4e764c130"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset._select_with_indices_mapping (cognitive 20): Dataset._select_with_indices_mapping has cognitive complexity 20 (threshold 15). Drivers by points: if/else 13 (16 pts), boolean chains 2, error handling 1, ternaries 1 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4505}}}],"partialFingerprints":{"codehealthFindingId/v1":"041026a3624a0e9cbcd41858ed467b5c36a0fa7907ee116a5ae29285214d572e"}},{"ruleId":"D2","level":"warning","message":{"text":"fingerprint.update_fingerprint (cognitive 20): fingerprint.update_fingerprint has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (16 pts), error handling 2 (3 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/fingerprint.py"},"region":{"startLine":253}}}],"partialFingerprints":{"codehealthFindingId/v1":"a83089607c9d568ce0a50e47e97d988feae48886c2b05509b6dcff8ff7457ee0"}},{"ruleId":"D2","level":"warning","message":{"text":"file_utils.xopen (cognitive 20): file_utils.xopen has cognitive complexity 20 (threshold 15). Drivers by points: if/else 6 (11 pts), error handling 3 (6 pts), boolean chains 2, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":939}}}],"partialFingerprints":{"codehealthFindingId/v1":"35b9ee07e7ba7f7b59c4c88c095f0e910cf5d3f738e10781a9dd7413b9c92c5c"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.__init__ (cognitive 19): Dataset.__init__ has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (13 pts), boolean chains 2, error handling 1 (2 pts), ternaries 2 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":712}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e949edb83ae8d2958e6ebbfd3641834ef164faa97ca1f5e7e7c94448105c3cc"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowWriter._build_schema (cognitive 19): ArrowWriter._build_schema has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (16 pts), loops 1 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":599}}}],"partialFingerprints":{"codehealthFindingId/v1":"287176aece18b8948d164e5e133ad203f77eb61b90a9b6487f8c424e11dde941"}},{"ruleId":"D2","level":"warning","message":{"text":"combine.interleave_datasets (cognitive 19): combine.interleave_datasets has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (15 pts), ternaries 1 (3 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/combine.py"},"region":{"startLine":18}}}],"partialFingerprints":{"codehealthFindingId/v1":"536b43650829f0857fe81a9f21ceb8b4a7b0d6770b7a56a4010660eae424c678"}},{"ruleId":"D2","level":"warning","message":{"text":"Audio.encode_example (cognitive 19): Audio.encode_example has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (15 pts), boolean chains 3, error handling 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":96}}}],"partialFingerprints":{"codehealthFindingId/v1":"85ab1a006d7e5461f7e76205097c72b17abe78ae67cb9a85c0c130b63c661294"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrayExtensionArray.to_numpy (cognitive 19): ArrayExtensionArray.to_numpy has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 3 (8 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":806}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ee8a4c8687955f1f090e4f4b2280a7747ec36ef555a07e4498b6edcb30c5268"}},{"ruleId":"D2","level":"warning","message":{"text":"Image.decode_example (cognitive 19): Image.decode_example has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (12 pts), ternaries 2 (6 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":"src/datasets/features/image.py"},"region":{"startLine":139}}}],"partialFingerprints":{"codehealthFindingId/v1":"e778ead7ef736258ee4dfb2e985374f9fbb813f679fd6ae2e5738b0e1e7c064c"}},{"ruleId":"D2","level":"warning","message":{"text":"formatting.format_table (cognitive 19): formatting.format_table has cognitive complexity 19 (threshold 15). Drivers by points: if/else 11 (19 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/formatting.py"},"region":{"startLine":637}}}],"partialFingerprints":{"codehealthFindingId/v1":"1d2e304d6610a0b6c7ec92521302ca6076742ebc2241fae4129cf6a305723e5d"}},{"ruleId":"D2","level":"warning","message":{"text":"NumpyFormatter._tensorize (cognitive 19): NumpyFormatter._tensorize has cognitive complexity 19 (threshold 15). Drivers by points: if/else 8 (11 pts), boolean chains 6, error handling 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/np_formatter.py"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"5eff67b0bf7e26c6f50f169aa246fbaa63f7833e8ff3f96d882e066fc3e908aa"}},{"ruleId":"D2","level":"warning","message":{"text":"IterableDataset._iter_pytorch (cognitive 19): IterableDataset._iter_pytorch has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (8 pts), loops 2 (6 pts), boolean chains 4, ternaries 1 (nesting depth added 6). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2889}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a9cc76c34623edbc7d80027f702d0c25710c74832e4f4da2430b89c447308f3"}},{"ruleId":"D2","level":"warning","message":{"text":"WebDataset._split_generators (cognitive 19): WebDataset._split_generators has cognitive complexity 19 (threshold 15). Drivers by points: if/else 7 (16 pts), loops 2 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/webdataset/webdataset.py"},"region":{"startLine":65}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f205d9c28c3ea5a5b365bea3e13e120ae95cb70d4340fbefbec9ae2a7f51d90"}},{"ruleId":"D2","level":"warning","message":{"text":"ZipExtractor.is_extractable (cognitive 19): ZipExtractor.is_extractable has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (16 pts), boolean chains 2, error handling 1 (nesting depth added 10). To reduce it, flatten the nesting: this score is depth rather than breadth \u2014 most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language\u0027s equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/extract.py"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"daca2f29b32279cab66167ee7366498a3f081cdd63a9e2c0ad5589db5451c7a8"}},{"ruleId":"D2","level":"warning","message":{"text":"py_utils.temp_seed (cognitive 19): py_utils.temp_seed has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (15 pts), boolean chains 4 (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":"src/datasets/utils/py_utils.py"},"region":{"startLine":243}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b8693dda0305c49365564a4d719d650635c2361c1e09119543d7b4611dad622"}},{"ruleId":"D2","level":"warning","message":{"text":"py_utils._single_map_nested (cognitive 19): py_utils._single_map_nested has cognitive complexity 19 (threshold 15). Drivers by points: if/else 10 (12 pts), boolean chains 4, ternaries 3 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":372}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a6095741b4f64c0657ecbfa4123b51e9a182b023a15684fecf9c1e9ee02d6c7"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.select (cognitive 18): Dataset.select has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (14 pts), boolean chains 2, error handling 1 (2 pts) (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":4359}}}],"partialFingerprints":{"codehealthFindingId/v1":"43f0f9118ec4c9f892b7bb039b494020ec21303184bdfe3632a7f2defbde2a8f"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset._push_parquet_shards_to_hub (cognitive 18): Dataset._push_parquet_shards_to_hub has cognitive complexity 18 (threshold 15). Drivers by points: boolean chains 7, if/else 5 (6 pts), ternaries 4, loops 1 (nesting depth added 1). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":5960}}}],"partialFingerprints":{"codehealthFindingId/v1":"1e57fc7c03a69531cf9aa03737f8e5dace1c2ee834c42308b656937b36a13dcf"}},{"ruleId":"D2","level":"warning","message":{"text":"BuilderConfig.create_config_id (cognitive 18): BuilderConfig.create_config_id has cognitive complexity 18 (threshold 15). Drivers by points: if/else 12 (18 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"1181ea1d78d1f10ce8d545138fe844a445fe47358a0b06b168f3fd482a9945d6"}},{"ruleId":"D2","level":"warning","message":{"text":"combine.concatenate_datasets (cognitive 18): combine.concatenate_datasets has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (14 pts), ternaries 1 (3 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/combine.py"},"region":{"startLine":168}}}],"partialFingerprints":{"codehealthFindingId/v1":"7da52422990f5f131000114254b2d448d02f130cef7cda58292999f34c9a1b29"}},{"ruleId":"D2","level":"warning","message":{"text":"Mesh.decode_example (cognitive 18): Mesh.decode_example has cognitive complexity 18 (threshold 15). Drivers by points: if/else 10 (14 pts), ternaries 2 (4 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/mesh.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5c61507a70de79d8662088ee46a55fd83d3e43a210f2eccecfa22440eaa675b"}},{"ruleId":"D2","level":"warning","message":{"text":"TFFormatter._tensorize (cognitive 18): TFFormatter._tensorize has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (11 pts), boolean chains 5, error handling 1 (2 pts) (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/tf_formatter.py"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fd7c54f17e30118572fa5c8893e422b4942a091d945f4043bad8f923d7935a1"}},{"ruleId":"D2","level":"warning","message":{"text":"load.load_dataset_builder (cognitive 18): load.load_dataset_builder has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (9 pts), ternaries 3 (5 pts), boolean chains 4 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":1187}}}],"partialFingerprints":{"codehealthFindingId/v1":"57b42801b2d34b7aef07e11c6392a0886c7e8dd5ce521c908a05a01b1588364f"}},{"ruleId":"D2","level":"warning","message":{"text":"Fasta._get_columns (cognitive 18): Fasta._get_columns has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (14 pts), loops 1 (2 pts), boolean chains 1, ternaries 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":176}}}],"partialFingerprints":{"codehealthFindingId/v1":"3fff25afb353f2b44ee1df377fa0c130fda35d726ecd72504f1eeea9eee04c21"}},{"ruleId":"D2","level":"warning","message":{"text":"Fastq._get_columns (cognitive 18): Fastq._get_columns has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (14 pts), loops 1 (2 pts), boolean chains 1, ternaries 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fastq/fastq.py"},"region":{"startLine":202}}}],"partialFingerprints":{"codehealthFindingId/v1":"19b08f393b8c877196b977706a194c1da3cf9cf818c4ae7bbb70efb4302147ad"}},{"ruleId":"D2","level":"warning","message":{"text":"GenBank._handle_features_line (cognitive 18): GenBank._handle_features_line has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (12 pts), boolean chains 6 (nesting depth added 4). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/genbank/genbank.py"},"region":{"startLine":481}}}],"partialFingerprints":{"codehealthFindingId/v1":"294d1bc8711b19e1c2938d6988cb398841b8e17b49a52dabcc6eaf548070e84c"}},{"ruleId":"D2","level":"warning","message":{"text":"json.parse_traces_info (cognitive 18): json.parse_traces_info has cognitive complexity 18 (threshold 15). Drivers by points: if/else 6 (15 pts), boolean chains 2, loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/json/json.py"},"region":{"startLine":438}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb96b79f73c9007da8577a5cd0215aa7b0337e459960e31a132da76a8745d407"}},{"ruleId":"D2","level":"warning","message":{"text":"NumpyMultiprocessingGenerator.__iter__ (cognitive 18): NumpyMultiprocessingGenerator.__iter__ has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (9 pts), loops 5 (8 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/tf_utils.py"},"region":{"startLine":298}}}],"partialFingerprints":{"codehealthFindingId/v1":"7e38b3179ea2ece6129d421fa414d21e6b7529714d93173ed836db75f0fe8d55"}},{"ruleId":"D2","level":"warning","message":{"text":"ReadInstruction.to_spec (cognitive 17): ReadInstruction.to_spec has cognitive complexity 17 (threshold 15). Drivers by points: ternaries 4 (12 pts), boolean chains 2, if/else 1 (2 pts), loops 1 (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_reader.py"},"region":{"startLine":567}}}],"partialFingerprints":{"codehealthFindingId/v1":"b99038670c870d64efd22975b0ce0b03abb28446fabc10a65386486dae0d7cab"}},{"ruleId":"D2","level":"warning","message":{"text":"ArrowWriter.write_examples_on_file (cognitive 17): ArrowWriter.write_examples_on_file has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (10 pts), ternaries 2 (6 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":651}}}],"partialFingerprints":{"codehealthFindingId/v1":"2d99f6c1e844c33cc19615d8993c4a837f287b544a9d3cd6f495ff9f1324511e"}},{"ruleId":"D2","level":"warning","message":{"text":"GeneratorBasedBuilder._prepare_split_single (cognitive 17): GeneratorBasedBuilder._prepare_split_single has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (10 pts), ternaries 2 (3 pts), boolean chains 2, error handling 1, loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1510}}}],"partialFingerprints":{"codehealthFindingId/v1":"6295f0b595422c0e3ec01919959fcdbe53995f1cfa799e92cf50e2a16f38cda9"}},{"ruleId":"D2","level":"warning","message":{"text":"image.encode_np_array (cognitive 17): image.encode_np_array has cognitive complexity 17 (threshold 15). Drivers by points: if/else 9 (14 pts), loops 1 (2 pts), ternaries 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/image.py"},"region":{"startLine":379}}}],"partialFingerprints":{"codehealthFindingId/v1":"001e9f82ce112087f2e189479df2b6e6a4566d64495c254862d07c835fb18ab6"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetInfosDict.to_dataset_card_data (cognitive 17): DatasetInfosDict.to_dataset_card_data has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 2 (5 pts), boolean chains 2 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/info.py"},"region":{"startLine":405}}}],"partialFingerprints":{"codehealthFindingId/v1":"22a1b461ccabb6bb68ca1afa8d7a611d83efd00a58a5c1cc52b03be9ee191b58"}},{"ruleId":"D2","level":"warning","message":{"text":"HubBucketDatasetModuleFactory.get_module (cognitive 17): HubBucketDatasetModuleFactory.get_module has cognitive complexity 17 (threshold 15). Drivers by points: if/else 10 (12 pts), boolean chains 3, error handling 2 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":857}}}],"partialFingerprints":{"codehealthFindingId/v1":"06fb9ea735b6ddd13b377c1ca9bd5c217ee60572764aeda8f04befb7c1b70b5e"}},{"ruleId":"D2","level":"warning","message":{"text":"load.create_builder_configs_from_metadata_configs (cognitive 17): load.create_builder_configs_from_metadata_configs has cognitive complexity 17 (threshold 15). Drivers by points: if/else 3 (6 pts), ternaries 4 (6 pts), boolean chains 2, error handling 1 (2 pts), loops 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":313}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb045ff638623da1f26932bfb17146959a99fddf8cf5bd030e4298d25def385f"}},{"ruleId":"D2","level":"warning","message":{"text":"hdf5._recursive_load_arrays (cognitive 17): hdf5._recursive_load_arrays has cognitive complexity 17 (threshold 15). Drivers by points: if/else 7 (12 pts), loops 2 (3 pts), ternaries 1 (2 pts) (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/hdf5/hdf5.py"},"region":{"startLine":261}}}],"partialFingerprints":{"codehealthFindingId/v1":"959b0be2ce479baac0377f653029c9b346aa166fbe6c00ee337a11ca74da7e9e"}},{"ruleId":"D2","level":"warning","message":{"text":"Json._cast_table (cognitive 17): Json._cast_table has cognitive complexity 17 (threshold 15). Drivers by points: if/else 3 (8 pts), loops 2 (4 pts), ternaries 1 (4 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/json/json.py"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"aa5da37e956c7fdf0902cad058bfc200149dd1341afab9b5cecf7270e7da3921"}},{"ruleId":"D2","level":"warning","message":{"text":"json.get_user_prompt (cognitive 17): json.get_user_prompt has cognitive complexity 17 (threshold 15). Drivers by points: if/else 8 (14 pts), boolean chains 3 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/json/json.py"},"region":{"startLine":487}}}],"partialFingerprints":{"codehealthFindingId/v1":"e719d1d220334b0d0cc5622adb6d4ef949dfc4500a49faa76a3cde2cf9284437"}},{"ruleId":"D2","level":"warning","message":{"text":"Vortex._split_generators (cognitive 17): Vortex._split_generators has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (8 pts), error handling 1 (4 pts), loops 2 (4 pts), boolean chains 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/vortex/vortex.py"},"region":{"startLine":255}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a540071fb33e15bb7ab2e4342dce0c13662bfcba8c178f308ea92d49974107a"}},{"ruleId":"D2","level":"warning","message":{"text":"Dataset.load_from_disk (cognitive 16): Dataset.load_from_disk has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (10 pts), boolean chains 3, ternaries 3 (nesting depth added 3). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":1978}}}],"partialFingerprints":{"codehealthFindingId/v1":"79a3676d701c82a4bc02c6e04c5110bc76be8f36ace035bd48d4dc244d5c19d8"}},{"ruleId":"D2","level":"warning","message":{"text":"DatasetInfo.__post_init__ (cognitive 16): DatasetInfo.__post_init__ has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9 (11 pts), boolean chains 5 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/info.py"},"region":{"startLine":167}}}],"partialFingerprints":{"codehealthFindingId/v1":"61db5f9a0e86ad3f2dfcc57f7d040a6954e064a0eabcaea3888f7a1f16bbfdfe"}},{"ruleId":"D2","level":"warning","message":{"text":"LocalDatasetModuleFactory.get_module (cognitive 16): LocalDatasetModuleFactory.get_module has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10 (12 pts), boolean chains 3, ternaries 1 (nesting depth added 2). To reduce it, split the body: most of this score is breadth rather than depth \u2014 checks laid out side by side rather than stacked \u2014 so group the statements between the checks into named steps and move each step into its own function. Some of it IS depth: where a check sits inside another whose only job is to reach it, merge the two into one condition, and where an else follows a branch that already returns, drop the trailing else and let the rest of the body continue at one level."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":422}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7455b06298b49ed938bb4e39c9f26d311f1de52fc7939b074f5ffc5d329d114"}},{"ruleId":"D2","level":"warning","message":{"text":"GenBank._get_columns (cognitive 16): GenBank._get_columns has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (12 pts), loops 1 (2 pts), boolean chains 1, ternaries 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/genbank/genbank.py"},"region":{"startLine":600}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc77fa7621ec82341b7f2f6bec529aee611a174bc8104ce2834e30024b8fc5f2"}},{"ruleId":"D2","level":"warning","message":{"text":"table._batch_accumulate_arrow_table_by_columns (cognitive 16): table._batch_accumulate_arrow_table_by_columns has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (9 pts), loops 3 (5 pts), boolean chains 2 (nesting depth added 4). To reduce it, split the body: this score is breadth rather than depth \u2014 many checks laid out side by side rather than nested inside one another, so inverting conditions into early returns has nothing left to flatten. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f75db41b83f608eeea8f6b24fc43f0a9ea0b75a6b9e34d492547ab2654a67ff"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/arrow_dataset.py: FileTooLong \u2014 3666 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 3166 over it, 7.33\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"dbe3b4ecc840e4a6d82b9374a8d81e4e55c72d60d5e319d3618e2c56aa025197"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/iterable_dataset.py: FileTooLong \u2014 3366 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 2866 over it, 6.73\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"15beee921255fd6861d1c4f09a6d73a895cf6f81a4d5e7932e7df079c71bb639"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Dataset: TooManyMethods \u2014 87 methods. The bar is 30 methods; this is 57 over it, 2.90\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":709}}}],"partialFingerprints":{"codehealthFindingId/v1":"89d6f991296bc5cbf75c033d14eb4eaed87a8f8fe9561f08ff2fbfe56ff7a5bf"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: features/features.py: FileTooLong \u2014 1426 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 926 over it, 2.85\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"70b4adeb7d69c67a6414ef0dfdee7278483b8212e515d4fab7c9c79f27127063"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/builder.py: FileTooLong \u2014 1145 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 645 over it, 2.29\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"95caae2151166ba8dfb2a5472be835c4dfdafac735446ee6376b514161896e79"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/load.py: FileTooLong \u2014 1072 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 572 over it, 2.14\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a84490558cd07ce4a7d2d10e67d60a9bde41060b7e8d6936d07ec7257f8abfa"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/dataset_dict.py: FileTooLong \u2014 976 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 476 over it, 1.95\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/dataset_dict.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"06d913a88ec1e132b0dee5a596fca7c6f9bbb68d35f47d31d9db2cec2622fb26"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/table.py: FileTooLong \u2014 972 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 472 over it, 1.94\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":"src/datasets/table.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5632958fa2d6f3fcf6c6c917beeb75b60a73b5da2a655e1fb920222b264aeb5"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: IterableDataset: TooManyMethods \u2014 58 methods. The bar is 30 methods; this is 28 over it, 1.93\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2690}}}],"partialFingerprints":{"codehealthFindingId/v1":"0112411d27af96e2c4710a3e312d046d65cbd5a09df20e28c74091ccdbdfaff2"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: utils/file_utils.py: FileTooLong \u2014 856 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 356 over it, 1.71\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/file_utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"1f22f882f90c89df950c8be3be71d5105d78e03f99fd518224e64db800e9e698"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: datasets/arrow_writer.py: FileTooLong \u2014 591 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 91 over it, 1.18\u00D7 the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"efad42244c8d9959d79f25c7eb25c285a727e8df123077cc5eed03ac97d57765"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: DatasetDict: 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":"src/datasets/dataset_dict.py"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"30f5d8a763f63416cee8055b82e795758a579706a0b0ece8f60ad50c62805586"}},{"ruleId":"D3","level":"warning","message":{"text":"TooManyMethods: Table: TooManyMethods \u2014 31 methods. The bar is 30 methods; this is 1 over it, 1.03\u00D7 the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"f9623f39dd9766c3fbf1592d1a8785909c42a6d757a5af34a61824edd64475f5"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (5 members, 15 shared lines): src/datasets/features/audio.py:238-281 | src/datasets/features/bio_sequence.py:243-264 | src/datasets/features/nifti.py:299-332 | src/datasets/features/pdf.py:184-218 | src/datasets/features/video.py:243-292 \u2014 These 5 members are variants of one another: a block of 15 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 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":"src/datasets/features/audio.py"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"78ffa56be1a584790ad21c64a1c52669a2ddd8dbd0409481e23f9826082363c3"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 57 shared lines): src/datasets/arrow_dataset.py:6088-6260 | src/datasets/dataset_dict.py:1640-1807 | src/datasets/dataset_dict.py:2344-2512 | src/datasets/iterable_dataset.py:5338-5512 \u2014 These 4 members are variants of one another: a block of 57 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6088}}}],"partialFingerprints":{"codehealthFindingId/v1":"70c022453255358fb6c986ca3ff5c933f5ac073da5853f4413f211e60342ee20"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (4 members, 18 shared lines): src/datasets/features/audio.py:238-281 | src/datasets/features/image.py:217-276 | src/datasets/features/mesh.py:163-213 | src/datasets/features/video.py:243-292 \u2014 These 4 members are variants of one another: a block of 18 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":"src/datasets/features/audio.py"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"3eebbbc38425f75138a3b74a1f94a0ac883cfcb7296c74a62e0a4f8cc5758fbc"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member family (3 members, 33 shared lines): src/datasets/packaged_modules/fasta/fasta.py:219-289 | src/datasets/packaged_modules/fastq/fastq.py:245-313 | src/datasets/packaged_modules/genbank/genbank.py:652-722 \u2014 These 3 members are variants of one another: a block of 33 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 3 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 3 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"d53a110900631514a90e67e6abfeb090c3aafd4dd35e78aeafa88e017a9f57dd"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (74 shared lines): src/datasets/load.py:423-508 | src/datasets/load.py:858-954 \u2014 These two members are variants of one another: 74 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":"src/datasets/load.py"},"region":{"startLine":423}}}],"partialFingerprints":{"codehealthFindingId/v1":"7ed8ffb8f455f6379dc73ecd851c5e7474ff320d82707aae218b7865ef01c9a1"}},{"ruleId":"D4","level":"warning","message":{"text":"Near-duplicate member pair (35 shared lines): src/datasets/arrow_dataset.py:7380-7425 | src/datasets/arrow_dataset.py:7438-7484 \u2014 These two members are variants of one another: 35 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":7380}}}],"partialFingerprints":{"codehealthFindingId/v1":"c4f26ec334faf15341bb62309e1bbd4b1ae87401b6fe6cafaecbf8fe2acaa717"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (7 members, 50\u002B identical tokens): src/datasets/features/bio_sequence.py:100-130 | src/datasets/features/bio_structure.py:106-136 | src/datasets/features/image.py:99-137 | src/datasets/features/mesh.py:58-89 | src/datasets/features/nifti.py:111-148 | src/datasets/features/pdf.py:79-111 | src/datasets/features/video.py:106-151 \u2014 These 7 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 7 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 7 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/bio_sequence.py"},"region":{"startLine":100}}}],"partialFingerprints":{"codehealthFindingId/v1":"6f07ec1992f57b5719260eb7dffe84ee66f63ae1b4372a53be5d0cfa49c7c665"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (6 members, 50\u002B identical tokens): src/datasets/features/audio.py:97-162 | src/datasets/features/bio_sequence.py:100-130 | src/datasets/features/bio_structure.py:106-136 | src/datasets/features/image.py:99-137 | src/datasets/features/nifti.py:111-148 | src/datasets/features/pdf.py:79-111 \u2014 These 6 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 6 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 6 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":97}}}],"partialFingerprints":{"codehealthFindingId/v1":"9983beab4ad9e41c503f0aa6d1fc17527908f946221b5e7d5e6dc3a4598ae14c"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (5 members, 50\u002B identical tokens): src/datasets/packaged_modules/conll/conll.py:76-99 | src/datasets/packaged_modules/csv/csv.py:152-167 | src/datasets/packaged_modules/eval/eval.py:22-51 | src/datasets/packaged_modules/json/json.py:80-107 | src/datasets/packaged_modules/text/text.py:52-71 \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":"src/datasets/packaged_modules/conll/conll.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"a729292102ac0407bf145595f86309235d6fea1bc67f9966275b1061b2f0d57d"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/datasets/arrow_dataset.py:873-932 | src/datasets/arrow_dataset.py:942-980 | src/datasets/arrow_dataset.py:991-1146 | src/datasets/iterable_dataset.py:3273-3314 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":873}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4145c3eb8d97af605cc3cd2ad6fec62fb7fbae7e121baf6daf8fb13e0f201e2"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/datasets/formatting/jax_formatter.py:84-132 | src/datasets/formatting/np_formatter.py:50-83 | src/datasets/formatting/tf_formatter.py:56-87 | src/datasets/formatting/torch_formatter.py:50-93 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"56137ea3ad5954948750134d67ed641ce995de9f33ea6a49dea6a2dd8c1ce902"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/datasets/io/csv.py:47-64 | src/datasets/io/json.py:53-70 | src/datasets/io/parquet.py:56-73 | src/datasets/io/text.py:41-58 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/io/csv.py"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"55a7eb33d60419d7d0bdcefc2331900a718d183c61720b314ae0feb81d9e1625"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/datasets/packaged_modules/fasta/fasta.py:85-103 | src/datasets/packaged_modules/fastq/fastq.py:85-103 | src/datasets/packaged_modules/genbank/genbank.py:245-263 | src/datasets/packaged_modules/xml/xml.py:30-45 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"ee24b7904f66a8a32908a0d523ca4dc35fe149df64540cb389cf922500ef26ba"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/datasets/utils/extract.py:93-129 | src/datasets/utils/extract.py:195-227 | src/datasets/utils/extract.py:252-289 | src/datasets/utils/extract.py:332-369 \u2014 These 4 members share a duplicated core: a run of at least 50 identical tokens appears in every one of them. That run is NOT broken out as duplicated-block rows below \u2014 it is what admitted this row, and the blocks below cover only the part of it that clears the block floor, so they understate the correspondence. Read the members as one construct written 4 times. The repair is at the members\u0027 grain \u2014 factor the shared implementation out once and have all of them call it with their differences as parameters or as an injected step, or, where the difference is systematic, generate them from one template. Extracting the individual blocks below is not the same fix: it leaves every body in place and the next edit still has to be made 4 times."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/extract.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a10e320c76dab86056962d57beb367aac4425acc5a2ae70118cef9e942666ef"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (107\u2013108 lines \u00D7 2): src/datasets/builder.py:1364-1471 | src/datasets/builder.py:1666-1772 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/builder.py"},"region":{"startLine":1364}}}],"partialFingerprints":{"codehealthFindingId/v1":"e9d928cd25ae6e37a8d555eab06cb975cb1c082d7e5c21f5b10e57f505fe5398"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (61\u201363 lines \u00D7 2): src/datasets/arrow_dataset.py:6688-6750 | src/datasets/dataset_dict.py:2560-2620 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 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 \u0060src/datasets/arrow_dataset.py:6688\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6688}}}],"partialFingerprints":{"codehealthFindingId/v1":"51bb59b5d5f4a6c76cfa37b5092b62484d6c3f6a31dc62ba0f02dd4f9650ddb3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (48 lines \u00D7 2): src/datasets/iterable_dataset.py:840-887 | src/datasets/iterable_dataset.py:915-962 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":840}}}],"partialFingerprints":{"codehealthFindingId/v1":"5b614d5c9e0d8bc730e5145f272ef93256df39e05832f3cc7af22b7b025cd195"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (47 lines \u00D7 2): src/datasets/arrow_dataset.py:873-919 | src/datasets/arrow_dataset.py:991-1118 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":873}}}],"partialFingerprints":{"codehealthFindingId/v1":"117b1f8677ae26ed51ff6233dc93a7c278aa25d737790743ef8a22a28ff48d39"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (42 lines \u00D7 2): src/datasets/arrow_dataset.py:6774-6815 | src/datasets/dataset_dict.py:2643-2684 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 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 \u0060src/datasets/arrow_dataset.py:6774\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6774}}}],"partialFingerprints":{"codehealthFindingId/v1":"434fca0c773230fecfa0c2eeade02e959164ac53479b7161b8e2c8fbfa1a8aaa"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (36 lines \u00D7 6): src/datasets/features/audio.py:315-350 | src/datasets/features/image.py:310-345 | src/datasets/features/mesh.py:243-278 | src/datasets/features/nifti.py:248-283 | src/datasets/features/pdf.py:252-287 | src/datasets/features/video.py:326-361 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 6 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/audio.py:315\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. 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":"src/datasets/features/audio.py"},"region":{"startLine":315}}}],"partialFingerprints":{"codehealthFindingId/v1":"fc4256193cd4f6c3d4cdeb50458f9f63e8d42d98cd2d4280d7f7d3223e1b56cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (36 lines \u00D7 2): src/datasets/builder.py:1520-1555 | src/datasets/builder.py:1816-1851 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/builder.py"},"region":{"startLine":1520}}}],"partialFingerprints":{"codehealthFindingId/v1":"18298d43ea9cab456ff9c7ecc164d41f7e9f54ce0e387f6918450c908979892f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (35 lines \u00D7 2): src/datasets/load.py:444-478 | src/datasets/load.py:890-924 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":444}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a50f99c2281842e10c1a2dceee25e540c5d5a6f0bda9c456d4371d947c6fbf8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (33 lines \u00D7 4): src/datasets/arrow_dataset.py:6226-6258 | src/datasets/dataset_dict.py:1774-1806 | src/datasets/dataset_dict.py:2479-2511 | src/datasets/iterable_dataset.py:5478-5510 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 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 \u0060src/datasets/arrow_dataset.py:6226\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060src/datasets/dataset_dict.py:2478\u0060 calls \u0060get\u0060 and \u0060src/datasets/arrow_dataset.py:6225\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6226}}}],"partialFingerprints":{"codehealthFindingId/v1":"2fe17e7168f36bac31c62383fe21caaafa29b6d6baa1a8505201e99e44c64ab8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31\u201333 lines \u00D7 2): src/datasets/packaged_modules/fasta/fasta.py:251-281 | src/datasets/packaged_modules/fastq/fastq.py:273-305 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":251}}}],"partialFingerprints":{"codehealthFindingId/v1":"b599d0dc97ba3cd0e4be3ad18b3a1b4af31bb2c13124bfae453394329fc0e5c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (27\u201331 lines \u00D7 2): src/datasets/arrow_dataset.py:942-968 | src/datasets/iterable_dataset.py:3273-3303 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":942}}}],"partialFingerprints":{"codehealthFindingId/v1":"d414427fd72429b77532fda1d075f543339651af5c76c50baa669cd97398dc41"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (31 lines \u00D7 2): src/datasets/utils/_dataset_viewer.py:29-59 | src/datasets/utils/_dataset_viewer.py:65-95 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/utils/_dataset_viewer.py"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf322699d7a8589dcc1c7c795a1d39bef3714284fee9027a5aed31a1607c8097"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (3\u201330 lines \u00D7 3): src/datasets/builder.py:1479-1508 | src/datasets/builder.py:1780-1809 | src/datasets/packaged_modules/spark/spark.py:342-344 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/builder.py:1479\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1479}}}],"partialFingerprints":{"codehealthFindingId/v1":"c031e37492333c9f241f61f0f7a9a53daf45fdd207e1cc94b44b74f634a54ca3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29\u201330 lines \u00D7 2): src/datasets/features/image.py:217-246 | src/datasets/features/mesh.py:163-191 \u2014 before extracting anything, compare \u0060src/datasets/features/image.py\u0060 and \u0060src/datasets/features/mesh.py\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 124 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060storage\u0060 to \u0060Union[pa.StringArray, pa.StructArray, pa.ListArray]\u0060 in one and \u0060Union[pa.StringArray, pa.StructArray]\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/image.py"},"region":{"startLine":217}}}],"partialFingerprints":{"codehealthFindingId/v1":"5590d926aa5a5538d74c99743deb2ea7f354172b0294deb5c619bb99db40bd46"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): src/datasets/arrow_dataset.py:6021-6049 | src/datasets/iterable_dataset.py:5265-5293 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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 \u0060src/datasets/arrow_dataset.py:6021\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6021}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b78dab522d07af76860f040e27c3e6a386a1402481a66c264035d0e43034064"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (25 lines \u00D7 2): src/datasets/combine.py:126-150 | src/datasets/combine.py:204-228 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/combine.py"},"region":{"startLine":126}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e7c065c2e399459f06bb1cac3bca16a70d5ee725d23d3dabb34673cebbdbf1e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21\u201325 lines \u00D7 2): src/datasets/packaged_modules/fasta/fasta.py:219-243 | src/datasets/packaged_modules/fastq/fastq.py:245-265 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":219}}}],"partialFingerprints":{"codehealthFindingId/v1":"0d0579b4db795080485d22374094a0058bcf523abc0245582e9843fe1442b450"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 4): src/datasets/arrow_dataset.py:6200-6223 | src/datasets/dataset_dict.py:1749-1772 | src/datasets/dataset_dict.py:2454-2477 | src/datasets/iterable_dataset.py:5452-5475 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 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 \u0060src/datasets/arrow_dataset.py:6200\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060src/datasets/dataset_dict.py:2478\u0060 calls \u0060get\u0060 and \u0060src/datasets/arrow_dataset.py:6224\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6200}}}],"partialFingerprints":{"codehealthFindingId/v1":"86986df3fe9f573e0418fd4009f881369b608c61699cdaaddb17c7bf941d82d3"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (24 lines \u00D7 2): src/datasets/load.py:485-508 | src/datasets/load.py:931-954 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/load.py:485\u0060 it runs out through the closing brace of the declaration holding it and carries on into the declaration that follows \u2014 the window is the tail of one member plus the head of the next, so no call can be substituted for those exact lines, and the smallest declaration that contains all of them is the type they sit in. The repeated unit is the member each site sits in: where those members\u0027 bodies are the same, move one whole member to the shared location and have the others delegate to it; where the copies are a run of near-identical overloads or wrappers that differ only in their signatures, the repetition IS the run \u2014 a one-line delegation has no helper inside it to lift \u2014 so generate the run from the set it enumerates, or accept it and keep each member\u0027s own documentation with it. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":485}}}],"partialFingerprints":{"codehealthFindingId/v1":"f04b4325622abee296e6efa32d073adfa9ce5837884c64c6fabd212bbfdcb8a4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (20\u201322 lines \u00D7 4): src/datasets/utils/extract.py:93-112 | src/datasets/utils/extract.py:195-216 | src/datasets/utils/extract.py:252-273 | src/datasets/utils/extract.py:332-353 \u2014 all 4 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060src/datasets/utils/extract.py:114\u0060 calls \u0060badlink\u0060, \u0060resolved\u0060, \u0060join\u0060 and \u0060src/datasets/utils/extract.py:218\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":"src/datasets/utils/extract.py"},"region":{"startLine":93}}}],"partialFingerprints":{"codehealthFindingId/v1":"0737532a5df68c70ee25ff8f8caebf68fdf4d89ea16d0b7cae6eb014ac8b9097"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (21 lines \u00D7 2): src/datasets/packaged_modules/fasta/fasta.py:179-199 | src/datasets/packaged_modules/fastq/fastq.py:205-225 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. The 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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a2fb19b12bc0ef3bcfdc15f5c02ace6853957d17d249a6e904b6da443f2cf8d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (16\u201319 lines \u00D7 4): src/datasets/packaged_modules/fasta/fasta.py:85-103 | src/datasets/packaged_modules/fastq/fastq.py:85-103 | src/datasets/packaged_modules/genbank/genbank.py:245-263 | src/datasets/packaged_modules/xml/xml.py:30-45 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"e67ed47a03246c6f24576ad9687eafb8b8eee3893460d559e4be8f893d991971"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201318 lines \u00D7 5): src/datasets/packaged_modules/conll/conll.py:76-93 | src/datasets/packaged_modules/csv/csv.py:152-163 | src/datasets/packaged_modules/eval/eval.py:22-34 | src/datasets/packaged_modules/json/json.py:80-92 | src/datasets/packaged_modules/text/text.py:52-67 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 5 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 5 times. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/packaged_modules/conll/conll.py:76\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. 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":"src/datasets/packaged_modules/conll/conll.py"},"region":{"startLine":76}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e0664304cb5448a372bff41ac36109a882b9b3d2c707bd1e40d9fb106f27779"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 4): src/datasets/io/csv.py:47-64 | src/datasets/io/json.py:53-70 | src/datasets/io/parquet.py:56-73 | src/datasets/io/text.py:41-58 \u2014 before extracting anything, compare \u0060src/datasets/io/csv.py\u0060 and \u0060src/datasets/io/json.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 36 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"src/datasets/io/csv.py"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"6376cf12383f9431e6a6a936cc97afc7bdb4b41d17a548a0ebe956513c8ed452"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (18 lines \u00D7 2): src/datasets/arrow_dataset.py:7389-7406 | src/datasets/arrow_dataset.py:7448-7465 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":7389}}}],"partialFingerprints":{"codehealthFindingId/v1":"1da319c1044ed13de0e4508320d585a56daed7260ee721bce9e5c9c9b84d04ae"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13\u201318 lines \u00D7 2): src/datasets/iterable_dataset.py:5590-5602 | src/datasets/iterable_dataset.py:5670-5687 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/iterable_dataset.py:5590\u0060 it does not close everything it opens, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5590}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f5b3e1c0c6efff2672e8aa6c288b4e3c180b65948d0cc4f37efb7d7306b13cc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14\u201317 lines \u00D7 2): src/datasets/arrow_dataset.py:6758-6774 | src/datasets/arrow_dataset.py:6858-6871 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/arrow_dataset.py:6758\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6758}}}],"partialFingerprints":{"codehealthFindingId/v1":"454b2761a30b254e9abcf2ad6af7649375032f4f07d0c2497aabd1347190c646"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): src/datasets/builder.py:1562-1578 | src/datasets/builder.py:1868-1884 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060src/datasets/builder.py:1885\u0060 calls \u0060isinstance\u0060 and \u0060src/datasets/builder.py:1579\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":"src/datasets/builder.py"},"region":{"startLine":1562}}}],"partialFingerprints":{"codehealthFindingId/v1":"ca96b4bc46063bf31b1d39c55a842dd7033330cae042d4fc863221c18e1b2b47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): src/datasets/formatting/jax_formatter.py:104-118 | src/datasets/formatting/tf_formatter.py:68-82 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/tf_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"eb065f99064feb1cefc351d00c753f37a7f561e636d6a0644dd786f2c60c412b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): src/datasets/packaged_modules/parquet/parquet.py:98-112 | src/datasets/packaged_modules/vortex/vortex.py:230-244 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. 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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":98}}}],"partialFingerprints":{"codehealthFindingId/v1":"dc35997964ff510b8d7c4e75aec7db7cb27cd8ffd293aa491633f969b33d8628"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 3): src/datasets/packaged_modules/fasta/fasta.py:276-289 | src/datasets/packaged_modules/fastq/fastq.py:300-313 | src/datasets/packaged_modules/genbank/genbank.py:709-722 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"b88249d9b316abf5270d0d13e6fcb00c58b11691010a0a22feb87a5c7c657226"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): src/datasets/arrow_dataset.py:6871-6884 | src/datasets/dataset_dict.py:2749-2762 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 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 \u0060src/datasets/arrow_dataset.py:6871\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6871}}}],"partialFingerprints":{"codehealthFindingId/v1":"461c263acd176698279c0b747c29dac3266eb147959704cf7a2a02cff1bf635f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): src/datasets/dataset_dict.py:954-967 | src/datasets/dataset_dict.py:1990-2003 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/dataset_dict.py:954\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":"src/datasets/dataset_dict.py"},"region":{"startLine":954}}}],"partialFingerprints":{"codehealthFindingId/v1":"3c33e3ee67ac119e4b139fd036223f3e2700174158274b6f485aa6b2bc82a6b1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 4): src/datasets/formatting/jax_formatter.py:109-121 | src/datasets/formatting/np_formatter.py:69-81 | src/datasets/formatting/tf_formatter.py:73-85 | src/datasets/formatting/torch_formatter.py:79-91 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/tf_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060src/datasets/formatting/torch_formatter.py:78\u0060 calls \u0060transpose\u0060 and \u0060src/datasets/formatting/jax_formatter.py:108\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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"96ae57f17a9d1f01714a58fbc91a8a07f9d3345298f07c1c8276cd6568f5c226"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): src/datasets/features/image.py:163-175 | src/datasets/features/mesh.py:113-125 | src/datasets/features/nifti.py:171-183 \u2014 before extracting anything, compare \u0060src/datasets/features/image.py\u0060 and \u0060src/datasets/features/mesh.py\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 124 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 \u0060src/datasets/features/image.py:163\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/image.py"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9f0d9ae8093ccc7963e4d82bb7fce909e5a22f45ac51b7d33c7383f1546883e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 3): src/datasets/iterable_dataset.py:1768-1780 | src/datasets/iterable_dataset.py:1786-1798 | src/datasets/iterable_dataset.py:1803-1815 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/iterable_dataset.py:1768\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":"src/datasets/iterable_dataset.py"},"region":{"startLine":1768}}}],"partialFingerprints":{"codehealthFindingId/v1":"f05cbaeae67647ec436c67866163d3549cb523840eec364aa13ed8bb7ba3987c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): src/datasets/arrow_dataset.py:6008-6020 | src/datasets/iterable_dataset.py:5244-5256 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":6008}}}],"partialFingerprints":{"codehealthFindingId/v1":"bcaae97cb82a0a704521a0a13953dc8a22f248be4b12c566111b23cb2ff5a018"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12\u201313 lines \u00D7 2): src/datasets/iterable_dataset.py:1169-1180 | src/datasets/iterable_dataset.py:1192-1204 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/iterable_dataset.py:1192\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":"src/datasets/iterable_dataset.py"},"region":{"startLine":1169}}}],"partialFingerprints":{"codehealthFindingId/v1":"4078412a14bfe72fb5216161a7a99bc7ee55e0e12f6caaef62acd31d005efb11"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): src/datasets/features/image.py:179-190 | src/datasets/features/nifti.py:190-201 | src/datasets/features/pdf.py:150-161 \u2014 before extracting anything, compare \u0060src/datasets/features/image.py\u0060 and \u0060src/datasets/features/nifti.py\u0060 as WHOLE FILES: this scan already matched 9 separate duplicated blocks between them, totalling at least 107 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 \u0060src/datasets/features/image.py:179\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/image.py"},"region":{"startLine":179}}}],"partialFingerprints":{"codehealthFindingId/v1":"19c9214c056fa8f356a1e8027c0b8bbefbb4b142b1bd231bbc156de2eda19ced"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): src/datasets/load.py:482-493 | src/datasets/load.py:690-701 | src/datasets/load.py:928-939 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":482}}}],"partialFingerprints":{"codehealthFindingId/v1":"57f41f539512c96715dbec696063ced32a7a293e8b354e9417eb36721256c71f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): src/datasets/arrow_dataset.py:5934-5945 | src/datasets/iterable_dataset.py:5166-5177 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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 \u0060src/datasets/arrow_dataset.py:5934\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":5934}}}],"partialFingerprints":{"codehealthFindingId/v1":"e185483823cd2864697561670d05655070f74d866ca2869ecee3081a72af3b53"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): src/datasets/features/image.py:113-124 | src/datasets/features/video.py:123-134 \u2014 before extracting anything, compare \u0060src/datasets/features/image.py\u0060 and \u0060src/datasets/features/video.py\u0060 as WHOLE FILES: this scan already matched 8 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. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/image.py"},"region":{"startLine":113}}}],"partialFingerprints":{"codehealthFindingId/v1":"17a65a3345adcc3891e177ad4f1af6271687201cfc62d2fae25a1b3a2b056fa4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): src/datasets/iterable_dataset.py:4087-4098 | src/datasets/iterable_dataset.py:4166-4177 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":4087}}}],"partialFingerprints":{"codehealthFindingId/v1":"f8ef4358ebaa62650365b4e5cfd4f3b041ae416ca69553cd0c532d4186f6eab9"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): src/datasets/arrow_dataset.py:7408-7418 | src/datasets/arrow_dataset.py:7467-7477 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/arrow_dataset.py:7408\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":7408}}}],"partialFingerprints":{"codehealthFindingId/v1":"1951ce7735e6d650e83be87cd225f5c72f9639f6aaf06c4d98198d7f6bb5aa5e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9\u201310 lines \u00D7 3): src/datasets/packaged_modules/fasta/fasta.py:238-246 | src/datasets/packaged_modules/fastq/fastq.py:260-268 | src/datasets/packaged_modules/genbank/genbank.py:666-675 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c0a4e1e704fd05f918eb3cafe665f4fcfce3e4d51d49f7129d5da7fef81d11b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 3): src/datasets/packaged_modules/fasta/fasta.py:256-265 | src/datasets/packaged_modules/fastq/fastq.py:278-287 | src/datasets/packaged_modules/genbank/genbank.py:695-704 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":256}}}],"partialFingerprints":{"codehealthFindingId/v1":"e2899e5fd0fd5c2605b90c22079a92f9a89de6ff86ef35ab40809672a1d06163"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): src/datasets/formatting/formatting.py:258-267 | src/datasets/formatting/polars_formatter.py:73-82 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/formatting.py"},"region":{"startLine":258}}}],"partialFingerprints":{"codehealthFindingId/v1":"a464341d5f5e44540dba444213344d8532351667f23be60940b2b2acc902e46a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): src/datasets/formatting/formatting.py:327-336 | src/datasets/formatting/formatting.py:342-351 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/formatting/formatting.py"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a180e5c5f29be670cca3909419126fae3303b1a1585841fcdda0d5a83bff297"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): src/datasets/packaged_modules/csv/csv.py:184-193 | src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py:300-309 \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":"src/datasets/packaged_modules/csv/csv.py"},"region":{"startLine":184}}}],"partialFingerprints":{"codehealthFindingId/v1":"a7735398bf3b9d963a24b0279215103ddf838c9cf522019d83fb9d7bea8c0abd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): src/datasets/packaged_modules/text/text.py:75-84 | src/datasets/packaged_modules/xml/xml.py:49-58 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/text/text.py"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"faca5f3cd49cf2b1e791d622d01d5a7452201920e154b7e3526bd2ca334a3a53"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 7): src/datasets/features/audio.py:270-278 | src/datasets/features/bio_sequence.py:254-261 | src/datasets/features/image.py:257-264 | src/datasets/features/mesh.py:202-209 | src/datasets/features/nifti.py:322-329 | src/datasets/features/pdf.py:208-215 | src/datasets/features/video.py:273-280 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 7 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/audio.py:270\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":"src/datasets/features/audio.py"},"region":{"startLine":270}}}],"partialFingerprints":{"codehealthFindingId/v1":"032ef9200245503373f3aef5fab0a0a0c7304d49058f8f81bf52ede375a2c546"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8\u20139 lines \u00D7 3): src/datasets/arrow_dataset.py:915-923 | src/datasets/arrow_dataset.py:964-972 | src/datasets/iterable_dataset.py:3299-3306 \u2014 there are 3 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Note 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":915}}}],"partialFingerprints":{"codehealthFindingId/v1":"046ca53ef10228ccf50861a7aaf97a705133f25b09cce072a273c9407c084bbd"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20139 lines \u00D7 3): src/datasets/packaged_modules/conll/conll.py:102-108 | src/datasets/packaged_modules/text/text.py:74-82 | src/datasets/packaged_modules/xml/xml.py:48-56 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere all 3 call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made 3 times. 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. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just after the matched lines, \u0060src/datasets/packaged_modules/text/text.py:84\u0060 calls \u0060cast\u0060, \u0060schema\u0060 and \u0060src/datasets/packaged_modules/conll/conll.py:110\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":"src/datasets/packaged_modules/conll/conll.py"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b7ba8930d6034e644112e528fdf69d19d2dc0b46789254501a316e24189a23a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): src/datasets/arrow_dataset.py:4024-4032 | src/datasets/iterable_dataset.py:1668-1676 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":4024}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d82b73f48644b899bfb89d066454ab437ebfdb6bd03214c635ae495d1ef8add"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (3\u20139 lines \u00D7 6): src/datasets/features/audio.py:279-281 | src/datasets/features/image.py:267-275 | src/datasets/features/mesh.py:210-213 | src/datasets/features/nifti.py:330-332 | src/datasets/features/pdf.py:216-218 | src/datasets/features/video.py:283-291 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 6 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/image.py:267\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060src/datasets/features/image.py:266\u0060 calls \u0060from_arrays\u0060, \u0060is_null\u0060, \u0060is_list\u0060 and \u0060src/datasets/features/nifti.py:330\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":"src/datasets/features/audio.py"},"region":{"startLine":279}}}],"partialFingerprints":{"codehealthFindingId/v1":"18f166421c011920edc61aa9eff8843bd0f4f083458ece45dd9bc0a61b9ed586"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): src/datasets/io/csv.py:77-85 | src/datasets/io/json.py:83-91 \u2014 before extracting anything, compare \u0060src/datasets/io/csv.py\u0060 and \u0060src/datasets/io/json.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 36 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/io/csv.py"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"535ab80dc6d0f8ca2828acd32633934f0c0135d8c9790547ea896f7043da883b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): src/datasets/io/csv.py:135-143 | src/datasets/io/json.py:182-190 \u2014 before extracting anything, compare \u0060src/datasets/io/csv.py\u0060 and \u0060src/datasets/io/json.py\u0060 as WHOLE FILES: this scan already matched 3 separate duplicated blocks between them, totalling at least 36 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/io/csv.py:135\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/io/csv.py"},"region":{"startLine":135}}}],"partialFingerprints":{"codehealthFindingId/v1":"900bf5304b290b3c37ac9f75360925163f57c8591e54ae48c38cf7182fde209e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 2): src/datasets/packaged_modules/arrow/arrow.py:32-40 | src/datasets/packaged_modules/hdf5/hdf5.py:49-57 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/arrow/arrow.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"89619e376daef4d3c9c10021ea4bba76549296230c34d7731c3e2708e382ce77"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (3\u20139 lines \u00D7 3): src/datasets/packaged_modules/fasta/fasta.py:71-79 | src/datasets/packaged_modules/fastq/fastq.py:71-79 | src/datasets/packaged_modules/genbank/genbank.py:238-240 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. Note 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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":71}}}],"partialFingerprints":{"codehealthFindingId/v1":"82eaaa944a19b1fd6ff1281a3f4008098c66b447ee498229efa65a60a43149c1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7\u20138 lines \u00D7 8): src/datasets/features/audio.py:205-212 | src/datasets/features/audio.py:312-318 | src/datasets/features/image.py:307-313 | src/datasets/features/mesh.py:131-137 | src/datasets/features/mesh.py:240-246 | src/datasets/features/nifti.py:245-251 | src/datasets/features/pdf.py:249-255 | src/datasets/features/video.py:323-329 \u2014 there are 8 copies across 6 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 8 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":205}}}],"partialFingerprints":{"codehealthFindingId/v1":"b3631c528860251ead8755c8043affa6dcaba6775cefc0e268f280194ce4cb2b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 5): src/datasets/features/bio_sequence.py:111-118 | src/datasets/features/bio_structure.py:117-124 | src/datasets/features/mesh.py:69-76 | src/datasets/features/nifti.py:122-129 | src/datasets/features/pdf.py:90-97 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 5 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/bio_sequence.py:111\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/bio_sequence.py"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"ad4e96f3218cecd4911e63296f1642b62dca9fa8a8ef510fa34afecedd527b47"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): src/datasets/formatting/jax_formatter.py:87-94 | src/datasets/formatting/torch_formatter.py:52-59 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/torch_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 38 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5933bd50238ea3aa416f44c8df3393608d95cfa0970339787c62dc1c890efef"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): src/datasets/packaged_modules/csv/csv.py:171-178 | src/datasets/packaged_modules/sql/sql.py:103-110 \u2014 the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach \u2014 a location they all depend on today, or a new shared one if there is none \u2014 and call it from each site; until then, every change has to be made twice. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/csv/csv.py"},"region":{"startLine":171}}}],"partialFingerprints":{"codehealthFindingId/v1":"1c342aa9272f6404f9551b8f978edc7746a22db4589c7f9a1817b048ad2d2fcb"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 5): src/datasets/features/audio.py:238-256 | src/datasets/features/bio_sequence.py:243-249 | src/datasets/features/nifti.py:299-317 | src/datasets/features/pdf.py:184-203 | src/datasets/features/video.py:243-262 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 5 call sites, so a change lands once. Note first that the copies are not typed on the same thing: the declarations holding them bind \u0060storage\u0060 to \u0060Union[pa.StringArray, pa.StructArray]\u0060 in one and \u0060Union[pa.StringArray, pa.StructArray, pa.BinaryArray]\u0060 in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH \u2014 their common supertype where they have one, or a new abstraction over them where they do not \u2014 and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":238}}}],"partialFingerprints":{"codehealthFindingId/v1":"88d9f6808ff9b168d88104c2fe1507304bdb874237d846fef39f96c55f277619"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 4): src/datasets/arrow_dataset.py:914-920 | src/datasets/arrow_dataset.py:963-969 | src/datasets/arrow_dataset.py:1113-1119 | src/datasets/iterable_dataset.py:3298-3304 \u2014 there are 4 copies across 2 file(s) \u2014 more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":914}}}],"partialFingerprints":{"codehealthFindingId/v1":"3473a01b2c7f8be26cb90b0075d29ea12bc476ff973cde310f11f9711e54f16e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/arrow_dataset.py:1903-1910 | src/datasets/arrow_dataset.py:1915-1921 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/arrow_dataset.py:1903\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":"src/datasets/arrow_dataset.py"},"region":{"startLine":1903}}}],"partialFingerprints":{"codehealthFindingId/v1":"14ed6471fdb29e47eb5d6dabe5bbbe31b1b9674e96026bd92ca5a94ef87b60cf"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/arrow_writer.py:414-422 | src/datasets/arrow_writer.py:435-441 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_writer.py"},"region":{"startLine":414}}}],"partialFingerprints":{"codehealthFindingId/v1":"a82e6abeb1413d291ab2803884d69e838faf0acc5c9c79e72944b66cb7c3f249"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/load.py:428-434 | src/datasets/load.py:874-880 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/load.py"},"region":{"startLine":428}}}],"partialFingerprints":{"codehealthFindingId/v1":"a52cc2ed1f330dd3ebaefb95808f293639009ac9eb3ffcc9a3a436f5f1991f85"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/packaged_modules/spark/spark.py:230-236 | src/datasets/packaged_modules/spark/spark.py:248-254 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/packaged_modules/spark/spark.py:230\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":"src/datasets/packaged_modules/spark/spark.py"},"region":{"startLine":230}}}],"partialFingerprints":{"codehealthFindingId/v1":"47d0cb81f122ee2d3472fcf8c9a08adce828e3f4f60d6a2ddb463ebf4085a2de"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 6): src/datasets/features/audio.py:156-162 | src/datasets/features/bio_sequence.py:125-130 | src/datasets/features/bio_structure.py:131-136 | src/datasets/features/image.py:131-137 | src/datasets/features/nifti.py:138-144 | src/datasets/features/pdf.py:105-111 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 6 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/audio.py:156\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"104877d288e706480807d13fc3851500b677b3e93a61b6e10da1822eff51890f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): src/datasets/features/audio.py:257-262 | src/datasets/features/image.py:247-252 | src/datasets/features/mesh.py:192-197 | src/datasets/features/video.py:263-268 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 4 call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"d3e339f4ebaec56e099b54b6a8fe412af86560ab2ebf60b5f2f57669ca0d403a"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 3): src/datasets/formatting/jax_formatter.py:144-149 | src/datasets/formatting/tf_formatter.py:99-104 | src/datasets/formatting/torch_formatter.py:100-105 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/tf_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"328d18d02c68b32b6acb1448558e8d7abb31a8f2cd38b2b89fd33e9e7fc07ab0"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): src/datasets/arrow_dataset.py:7420-7425 | src/datasets/arrow_dataset.py:7479-7484 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":7420}}}],"partialFingerprints":{"codehealthFindingId/v1":"b2887d3af9623a3db90bc902420ca8b0e1eeda89b6d2bd09b1e7ee0984e88d15"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): src/datasets/packaged_modules/fasta/fasta.py:211-216 | src/datasets/packaged_modules/fastq/fastq.py:237-242 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"34bac6e8697e5d3d761c3d275b1f682dd830bf44bd1ce873e4031b86ff74171c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 2): src/datasets/utils/file_utils.py:1020-1025 | src/datasets/utils/file_utils.py:1073-1078 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/utils/file_utils.py:1020\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":"src/datasets/utils/file_utils.py"},"region":{"startLine":1020}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5960d8196720f784c236d3ba9ab73457e7db0ab85e62d7e734892e5b014d038"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 7): src/datasets/features/audio.py:342-349 | src/datasets/features/bio_sequence.py:298-302 | src/datasets/features/image.py:337-344 | src/datasets/features/mesh.py:270-277 | src/datasets/features/nifti.py:275-282 | src/datasets/features/pdf.py:279-286 | src/datasets/features/video.py:353-360 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 7 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/datasets/features/audio.py:342\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":"src/datasets/features/audio.py"},"region":{"startLine":342}}}],"partialFingerprints":{"codehealthFindingId/v1":"96b958c7bdcd947c2ea10d41e4a0dcd72682da0edf11abb84a21c21825554afc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 7): src/datasets/features/bio_sequence.py:114-118 | src/datasets/features/bio_structure.py:120-124 | src/datasets/features/image.py:116-120 | src/datasets/features/mesh.py:72-76 | src/datasets/features/nifti.py:125-129 | src/datasets/features/pdf.py:93-97 | src/datasets/features/video.py:126-130 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 7 call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. \u2605 These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, \u0060src/datasets/features/video.py:123\u0060 calls \u0060isinstance\u0060, \u0060array\u0060 and \u0060src/datasets/features/bio_sequence.py:112\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":"src/datasets/features/bio_sequence.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fb9b7c5d20f4c570f7de1ced9cbb1091ff5354fc35a3d59c2efdfc4a5333c18"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 3): src/datasets/load.py:438-442 | src/datasets/load.py:635-639 | src/datasets/load.py:884-888 \u2014 all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites \u2014 resolving only two of them leaves the rest to drift apart the first time one is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":438}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e0e0a613be31908c27fef6aa115699a468cdbb9f31bd79e9dc7dd3250631c80"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/iterable_dataset.py:830-834 | src/datasets/iterable_dataset.py:905-909 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/iterable_dataset.py"},"region":{"startLine":830}}}],"partialFingerprints":{"codehealthFindingId/v1":"08f10bbec656ec19f43e8adc865ffd7a1575134f40a162e5fbe288e3263520df"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/arrow_dataset.py:620-624 | src/datasets/iterable_dataset.py:1111-1117 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names \u2014 the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":620}}}],"partialFingerprints":{"codehealthFindingId/v1":"ab62779d3a81fe2916004280f6e43ad7a0a2338ad5b311892b4a33c099a7f8c8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 4): src/datasets/formatting/jax_formatter.py:162-166 | src/datasets/formatting/np_formatter.py:111-115 | src/datasets/formatting/tf_formatter.py:117-121 | src/datasets/formatting/torch_formatter.py:118-122 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/tf_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":162}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3834f1f0cdec5325e6456383d042758e1c12918040d768c7f207bf1379384d4"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (6 lines \u00D7 4): src/datasets/formatting/jax_formatter.py:169-174 | src/datasets/formatting/np_formatter.py:118-123 | src/datasets/formatting/tf_formatter.py:124-129 | src/datasets/formatting/torch_formatter.py:125-130 \u2014 before extracting anything, compare \u0060src/datasets/formatting/jax_formatter.py\u0060 and \u0060src/datasets/formatting/tf_formatter.py\u0060 as WHOLE FILES: this scan already matched 5 separate duplicated blocks between them, totalling at least 45 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. 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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":169}}}],"partialFingerprints":{"codehealthFindingId/v1":"0052873305f1e90609ba96f7b811385f51e9e69fdb669575ba9d5b3248e5765d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (8 lines \u00D7 2): src/datasets/info.py:327-334 | src/datasets/splits.py:59-66 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. 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":"src/datasets/info.py"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"c52ae4d303cfcd9972a733223abef569df968f8701b5070cf3092635ae55bdc6"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): src/datasets/packaged_modules/fasta/fasta.py:106-115 | src/datasets/packaged_modules/fastq/fastq.py:106-115 \u2014 \u0060src/datasets/packaged_modules/fasta/fasta.py\u0060 and \u0060src/datasets/packaged_modules/fastq/fastq.py\u0060 are one unit implemented once per sibling directory, so they are most likely parallel implementations of one contract rather than a copy of each other \u2014 this scan matched 10 separate duplicated blocks between them, totalling at least 157 lines. If both are selected at run time, neither can be retired in favour of the other, and the lines that DIFFER between them are the reason both exist. The move that pays here is to hoist the identical part into a shared location the whole family can reach and give what differs a parameter or a seam, so a change lands once instead of once per sibling; extracting one helper per block leaves every sibling to drift on its own. The 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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"61f26840d5f27b19b89bdc032b88d67eeac8d93b6a4f5778cf50adbad4de7c29"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/arrow_dataset.py:6833-6837 | src/datasets/dataset_dict.py:2700-2704 \u2014 before extracting anything, compare \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/dataset_dict.py\u0060 as WHOLE FILES: this scan already matched 6 separate duplicated blocks between them, totalling at least 181 lines, which is the signature of one file having been copied from the other rather than of a helper waiting to be extracted. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6833}}}],"partialFingerprints":{"codehealthFindingId/v1":"13d8b6fee6cdeec543192a1ff835a29e195edf664ae1a741a8708c1b17905c7f"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/dataset_dict.py:63-67 | src/datasets/dataset_dict.py:1818-1822 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/dataset_dict.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"585dbee9601dc5b6697cc29b6b53060276bb0136340f02ac8137296c2c847ea5"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/iterable_dataset.py:415-419 | src/datasets/iterable_dataset.py:436-440 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":415}}}],"partialFingerprints":{"codehealthFindingId/v1":"d5accd944dcd2c2bbe31e826b79ca7f7677fa12d8830e5a6b92282ab6673fb9e"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/packaged_modules/parquet/parquet.py:130-136 | src/datasets/packaged_modules/parquet/parquet.py:228-234 \u2014 both copies are in the same file, so extract the block 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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"6e22e7a92f7bc43b119f41a7e404616420dc77a306d96bb67b25f40d5dd34d76"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): src/datasets/packaged_modules/parquet/parquet.py:144-150 | src/datasets/packaged_modules/vortex/vortex.py:286-292 \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 \u0060src/datasets/packaged_modules/parquet/parquet.py:144\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8c96ce25244b304014980def01dc41df00e51aa7b51e9d44141410a4ae8cbc1"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/packaged_modules/parquet/parquet.py:186-190 | src/datasets/packaged_modules/vortex/vortex.py:346-350 \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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"71ad0be8f39ddab8af77fdb399fff1c4acbe7619a35e6f47948848a4426ab526"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/datasets/table.py:2139-2143 | src/datasets/table.py:2235-2239 \u2014 both copies are in the same file, so extract the block into one function there and call it from each site \u2014 the copies drift apart the first time only one of them is edited. The \u0060return\u0060 at the foot of the matched lines is the enclosing body\u0027s own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that \u0060return\u0060 occupied \u2014 no decision has to be handed back and re-acted on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/table.py"},"region":{"startLine":2139}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3b2d9127148b477c404bac45cec36136327e69b7cb6629403ab8cc58bb77f39"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: src/datasets/iterable_dataset.py: src/datasets/iterable_dataset.py changed 26 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 22 in IterableDataset._prepare_ex_iterable_for_iteration at line 2958. 12 of those changes were fix/bug commits, and the other 14 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 2026-07-21..2026-10-19, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-07-21 20:07:31 \u002B02:00\u0027 --until=\u00272026-10-19 20:07:31 \u002B02:00\u0027 --full-history --no-merges -- src/datasets/iterable_dataset.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":2958}}}],"partialFingerprints":{"codehealthFindingId/v1":"404167fd0e84647cce201658f59e3f071cde10184818ecd93b267e35a9111649"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: src/datasets/arrow_dataset.py: src/datasets/arrow_dataset.py changed 10 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 34 in arrow_dataset._get_updated_dataset_card at line 6887. 5 of those changes were fix/bug commits, and the other 5 changed it for other reasons \u2014 this file is under both repair and feature pressure. Before the next change lands here, make sure the area it touches is under test, then split that area out of the file so the following change is smaller than this one \u2014 a file this often edited pays the complexity back every time. Counted over 2026-07-21..2026-10-19, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-07-21 20:07:31 \u002B02:00\u0027 --until=\u00272026-10-19 20:07:31 \u002B02:00\u0027 --full-history --no-merges -- src/datasets/arrow_dataset.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":6887}}}],"partialFingerprints":{"codehealthFindingId/v1":"6498fc4ff871e4431bac8c0a7d3b08bfc6738597089b1d53b514391ff7c6d747"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: src/datasets/load.py: src/datasets/load.py changed 6 times in last 90 days, and the most complex body those changes touched has cyclomatic complexity 15 in HubBucketDatasetModuleFactory.get_module at line 857. 4 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 2026-07-21..2026-10-19, the 90 days ending at the analysed commit. Reproduce with \u0060git log --since=\u00272026-07-21 20:07:31 \u002B02:00\u0027 --until=\u00272026-10-19 20:07:31 \u002B02:00\u0027 --full-history --no-merges -- src/datasets/load.py\u0060: merges are excluded because a merge re-states changes already counted at their own commits, and history is NOT path-simplified because a change that reached the file through a merged branch is still a change to it. That command counts raw commits and can read HIGHER than this row, which counts a cherry-picked re-land, and a revert together with the commit it undoes, once each \u2014 a difference of several commits on a file whose history was re-landed or reverted inside the window."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":857}}}],"partialFingerprints":{"codehealthFindingId/v1":"4fb44e1fef22b02f3593955bda5cead23e15190a08a4162140220a2146e012d8"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #1: If anonymized user #1 becomes unavailable, 4 significant file(s) lose their only recent owner: src/datasets/packaged_modules/fastq/fastq.py, src/datasets/packaged_modules/fasta/fasta.py, src/datasets/features/bio_sequence.py, src/datasets/features/bio_structure.py. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"9e0f3ab6105b90c5c9e608722a5087b7c73c9abf6a83c820190ff9b0017beccf"}},{"ruleId":"D16","level":"note","message":{"text":"Further sole-owners (lower concentration): 2 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 (7 single-owned of 93 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; 93 of the 163 production source files in this repository met that bar). They are anonymized user #2 (2 file(s)), anonymized user #3 (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: src/datasets/info.py, src/datasets/packaged_modules/parquet/parquet.py, src/datasets/packaged_modules/conll/conll.py."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6eac528f2429e724e1a97ed868f79eefbcf1888dab4af9a9e673429369bb5b2f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): always update the module to add subsequent new authentication without removing old ones \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/streaming.py"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed47d34711188b2894663b042d70f824a1de5c5b9d7f449e622783ef99008a75"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(epot): Check that the number of examples per shard % 100 == 0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/splits.py"},"region":{"startLine":499}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef17fe06f5bf598f81d13e8b7a0e7a28c240aa6e313b5a715c294294998e5307"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(epot): If a split is already added but there is no overlap between \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/splits.py"},"region":{"startLine":507}}}],"partialFingerprints":{"codehealthFindingId/v1":"c150829f6ba7b724b8fcff854c843d1223822659c12b7ec0ee881ed3d0802244"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): add format_kwargs \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":3664}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b4d1d625daa2bd384d27ee96e8bfb04b61b47d1e4cb642e9090ff7997599c69"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): add format_columns and return_all_columns \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":3665}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b71a9401cb30b3cc0350c1ac83744edb985b1e4157b67c5b144c9270a11ed4f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): add pandas format \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":3666}}}],"partialFingerprints":{"codehealthFindingId/v1":"e3bc21c5b3617af6de7a34de01191e8c67fb8359cba6538923cbcce3b55ca899"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # max_shard_size: Optional[Union[int, str]] = None,  # TODO(QL): add arg \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5117}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdf5926490ea1a8354276ec6194aea8addb9b8c72baaf5937d6b12401df23b94"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: improve this to account for a mix of ClassLabel and Value for example \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5570}}}],"partialFingerprints":{"codehealthFindingId/v1":"1663d2e9dae5d66587fc41f4169b7169718cd880496640a8ce7b4d5cb9b91d36"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: improve this to account for a mix of ClassLabel and Value for example \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/iterable_dataset.py"},"region":{"startLine":5651}}}],"partialFingerprints":{"codehealthFindingId/v1":"5a61a3223f96e5f76adfe4f77cdf65bec3163297325d36beab049045f49a3930"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(Matt, QL): deprecate the retention of label_ids and label \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":457}}}],"partialFingerprints":{"codehealthFindingId/v1":"afe2e6f338849b906b1564fe30d8a55b51c3814c082763e1c0bdd5e1a40c316a"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(Matt, QL): deprecate returning the dict content when there\u0027s only one key \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":516}}}],"partialFingerprints":{"codehealthFindingId/v1":"9a04409908823b97f2ef7100ea7250f64d408906f0f392badc58ab358b177ae3"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: this assumes the format_spec of rank in suffix_template \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":3514}}}],"partialFingerprints":{"codehealthFindingId/v1":"e5aac9dc30b31a0e64d21bce64f94497e21095862f638b0d61ecee4f65c3ffc5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL, MS): ideally the behavior should be the same even if the dataset is formatted (may require major 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":"src/datasets/arrow_dataset.py"},"region":{"startLine":3830}}}],"partialFingerprints":{"codehealthFindingId/v1":"8bf53efbe3e054b9e09055b4e44d9f76a420f49e551a11e7bff925dda05ae3dc"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to torch tensors ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/torch_formatter.py"},"region":{"startLine":84}}}],"partialFingerprints":{"codehealthFindingId/v1":"a15c5f92f71cc66fdad08126f645cba8c069863e227ef8870d161e5d3d557dd7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to jax arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/torch_formatter.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a45372049ffca84ac5d686b7252d987b271582efb8369cbf9b5d3177dbb02e5"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to jax arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/tf_formatter.py"},"region":{"startLine":85}}}],"partialFingerprints":{"codehealthFindingId/v1":"d889dc896f85f77e6979cbe2bb7828255f6dbb66f53842271148682e9fe22f4e"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to jax arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"e13b98b51f8e41b7627f053e0a72ebbbdfe98ee6df8689d0128e857fba9f957f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to jax arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":121}}}],"partialFingerprints":{"codehealthFindingId/v1":"4f4e3bc688aa06c47bbcf9fca32744d6004939810d693a91d9ccaafb92790387"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to tf tensors ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/tf_formatter.py"},"region":{"startLine":78}}}],"partialFingerprints":{"codehealthFindingId/v1":"167c1d471d8a9c2257b976284dfeec35449338bdda40ab32fcac504079ba0968"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to np arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/np_formatter.py"},"region":{"startLine":74}}}],"partialFingerprints":{"codehealthFindingId/v1":"9da6cc5398e0a03b28a67c9ee4063d43518de89904930022a9879384d7cbb4cf"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(QL): set output to np arrays ? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/np_formatter.py"},"region":{"startLine":81}}}],"partialFingerprints":{"codehealthFindingId/v1":"8910b24c8b79f0e917f4730322ed08ec5cc9e649932eb42d5e43ed5d85f52a3f"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO(kszucs): we may want to persist multiple parameters \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/io/parquet.py"},"region":{"startLine":148}}}],"partialFingerprints":{"codehealthFindingId/v1":"5075930dbf7a9b93d76177ade9ad902807739433aff4d3106d7b769c97de24fe"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: remove once Lance supports HF links with revisions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/lance/lance.py"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf9c3858c4604eaa85d1cfbcfe966d7f83d6ba4fb84e852d1ec38a3d3ca067f9"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: remove once Lance supports symlinks for _version files \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/lance/lance.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c70f14204d09c7616c48cc102b4d23feb3693000e7ce802465af2407c66686b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Stream batches to the driver using ArrowCollectSerializer instead of throwing an error. \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/spark/spark.py"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"615841f8b224dc33ba0d9175a1cc532142d97b3ad91ab102da771c8f4bcf6a2b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: initial list, we should check the compatibility of other formats \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/videofolder/videofolder.py"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"0a87e90721fb12058bd6c76820e68c0773df5b447cbe0a1eacfcf1ffb65c6701"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: initial list, we should check the compatibility of other formats \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/webdataset/webdataset.py"},"region":{"startLine":281}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb7c5980d2ae8f4aa0de07ad371ef9787f03add14d158fb49c12a07c112fe4b0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: call create_cache_and_write_probe if \u0022download\u0022 in steps \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/parallel/parallel.py"},"region":{"startLine":114}}}],"partialFingerprints":{"codehealthFindingId/v1":"5182b7e8922b4e64d29069372c4ffb41ca6351dbf58b76fe26c2700cb3609a41"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: raise NotImplementedError when Dataset.map etc is called \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/parallel/parallel.py"},"region":{"startLine":115}}}],"partialFingerprints":{"codehealthFindingId/v1":"abe1b4e949b81b712bda8d7a9c84f660903e5d4970ba099db4504c6ff9e18f56"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO Matt: When our minimum Python version is 3.8 or higher, we can delete all of this and move everything \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/tf_utils.py"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd60829ae480f11a817d6a1e8bae0f35d5ac9cb7a0fc74eccb90580945bfb5f8"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # noqa: F401 # imported for backward compatibility. TODO: remove in 3.0.0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/py_utils.py"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"5e76ed6676a70173045d91dce33d0a31730d986010611c649b02332be741a473"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # noqa: F401 # imported for backward compatibility. TODO: remove in 3.0.0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/filelock.py"},"region":{"startLine":11}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c1d3f9efcda427794b608b17058a31b9021bee8ec86a68bfec3554a31dc979b"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # noqa: F401 # imported for backward compatibility TODO: remove in 3.0.0 \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/filelock.py"},"region":{"startLine":3}}}],"partialFingerprints":{"codehealthFindingId/v1":"89aeade8d6e6bdbb0e53a289697a714d71dbdfcfed5b6d68f19c062fe02c7286"}},{"ruleId":"D17","level":"warning","message":{"text":"XxxComment: # XXX: the timeout doesn\u0027t seem to make any difference here \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"tests/utils.py"},"region":{"startLine":591}}}],"partialFingerprints":{"codehealthFindingId/v1":"b1722c39801e8c6403802ec6d80b428149a630d24acdb2d1546dcbec2ee1fdd0"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: add hash consistency tests across sessions \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"tests/test_fingerprint.py"},"region":{"startLine":91}}}],"partialFingerprints":{"codehealthFindingId/v1":"c9c899e5027dc30e701b0f57c7ded96022c6af1a824b0f2096855114e21b75fb"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: with assert_arrow_memory_increases() if in_memory else assert_arrow_memory_doesnt_increase(): \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"tests/test_arrow_dataset.py"},"region":{"startLine":585}}}],"partialFingerprints":{"codehealthFindingId/v1":"642d1cc097b6f5e4b3aff1a53bbd164d9af803c884c29788981ba05f0488c167"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # TODO: Why mapped twice? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"tests/test_arrow_dataset.py"},"region":{"startLine":2186}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a0962311896d355147e4b6c2573424bcfe85bfbc2c2bc49159680b520ff10e7"}},{"ruleId":"D17","level":"warning","message":{"text":"TodoComment: # test_hf_cache_home = tmp_path_factory.mktemp(\u0022cache\u0022)  # TODO: why a cache dir per test function does not work? \u2014 source code is not a task system: move the work to your tracker and leave a reference instead (e.g. \u0060# REF: #123\u0060), so the task is planned where tasks live and the ticket links back to the code."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"tests/conftest.py"},"region":{"startLine":21}}}],"partialFingerprints":{"codehealthFindingId/v1":"cecb2b10fbf1777049b35c2d2ddda32b8023b73923a7acc311e8cda0ba334dcf"}},{"ruleId":"D20","level":"note","message":{"text":"No ADRs found: No ADRs found. No recognised ADR directory (\u0060docs/adr/\u0060, \u0060docs/decisions/\u0060, \u0060adr/\u0060, \u0060docs/rfcs/\u0060, an \u0060ADR0001/\u0060 folder, or their siblings) exists anywhere in this tree. What was searched, so you can tell an empty log from a search that missed one: every directory under the tree (build output, dependencies and VCS metadata excepted), for a document that is either any non-index page inside a recognised ADR directory, whatever its name and however deeply nested (\u0060docs/adr/use-postgres.md\u0060, \u0060docs/adr/2024/0001-x.md\u0060); or a file anywhere whose name is ADR-shaped (\u00600001-use-postgres.md\u0060, \u0060adr-012-caching.md\u0060); or, when neither turned anything up, a document carrying the decision-record signature (an \u0022Architecture Decision Record\u0022 heading, or Status / Context / Decision / Consequences as section headings). A decision log that clears none of these \u2014 unnumbered files outside any recognised directory, without those headings \u2014 is not seen by this check and this row is then wrong. If that is your case, say so rather than renaming anything; otherwise, consider recording architectural decisions in \u0060docs/adr/\u0060."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"d2bea044ff79d7d275f5a91a6e2f548586178eaf480274c33960ad020c854631"}},{"ruleId":"D26","level":"note","message":{"text":"Projects may be oversized for their cohesion: 1 of 1 project(s) overshoot their size bounds, lowering Project Cohesion to 0.0/10. The most over is \u0060(repository root)\u0060 (43983 LoC, 389 module-visible types across 44 directories). Review these for cohesion \u2014 draw the boundary inside the module first (group each responsibility into its own package or directory and keep the cross-boundary members non-public), since splitting a published package moves types between packages and breaks consumers."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"d5a94650dc74886a0f1f08eb9fb6775f1fc395279ef7e901c970c9d26f767a72"}},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"28847bfb68128ad6c95eb6a19a3df3a0787d1bdadcf090baba24802b8a233364"},"taxa":[{"id":"CWE-732","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A01:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"68b1b7a1c198616ade4487b3db56550d32a2a43a25eaddeb043b026fa699b58e"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d879350c03cd1d2548461b86a9a510ea04ea0d4de9221f854c8c283c63b47392"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"119bd0fa54888c840bac514f111cbb4fd9046a474e9868f69de232774f1107ad"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d77e3e80786a3aeb89fc322241c4bb05d99491d7a29d3d8f80c7fce217692100"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"ed4b05a68f058d634ac19998542543a105c8690f661ecdfa2c6be8063481c146"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"c91f341b23e997f1a3d4c343effca511ca9e7b16003a18b186d33f61c2ac59fb"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"6935dad2e398b6f45c63ed146f4e893467f026c95befc4c4c67fea8a9fb31eb6"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d2a2b11cb50f13e8eb732012bbc587d8b1e20f879a8fd4c8208f614569ff39c1"},"taxa":[{"id":"CWE-214","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-532","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A09:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"b4b84274ded7e6b21af20f24c3c1abbd7c2623cc940e96b12bd49088aeb7e024"},"taxa":[{"id":"CWE-1104","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},{"id":"CICD-SEC-3","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1aeaa6ef068e8b70909d0eb459d7be0c53b43fc480df140fe819fac41c7c2b73"},"taxa":[{"id":"CWE-1104","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},{"id":"CICD-SEC-3","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1bfdb1d3bebaac2d1f5dac9f4e94618ca47fa294397b675d4ae842ea6ca2dbbf"},"taxa":[{"id":"CWE-1104","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-494","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A03:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},{"id":"CICD-SEC-3","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"2f12ba63386e290c6d7bd3cf3c633b93b8af9ccd35b4e112132f66af288d0bf6"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"3f779428d65e9478c391113fee2d8a63be22b04439fc5e50b89b34b1ebd904cb"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"51511ff3e9b1d11611d62d13500ef0c417f456a9602f5cc4bb5c8d2a882de218"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"A02:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}}]},{"ruleId":"D29","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"11d6864455f87158c7a7d0afb84b699d37a30fd375fefb00e3496060f8eaf51a"},"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":"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":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"fed53479a74cad720bab5570d2b9743d8833cdc08c83ec5e257bfced60396560"}},{"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":"src/datasets/utils/tf_utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"65ca7a71b20759e74b963797aa32860d2334e52e5f5a52d9553b16037ab32607"}},{"ruleId":"D34","level":"note","message":{"text":"Further orphaned files (smaller): 16 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: src/datasets/inspect.py, src/datasets/packaged_modules/spark/spark.py, src/datasets/packaged_modules/iceberg/iceberg.py, benchmarks/benchmark_array_xd.py, src/datasets/formatting/polars_formatter.py, src/datasets/parallel/parallel.py, src/datasets/packaged_modules/sql/sql.py, src/datasets/utils/tqdm.py (and 8 more) (18 orphaned of 93 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; 93 of the 163 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":"src/datasets/inspect.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"379728e2f2c6cbeefb548a469dd6bd7f541920acac6d012840917f17f8ae8b54"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/spark/spark.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"8a93cc0d2afa5c17cf6c7cf6fd5d055999c3e09f3f9915821f3bda3f7b3fd70d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/iceberg/iceberg.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ce4695dd3ec01049b1fe06224b2f9637fdfb6c2f9b770b3976a551b4ae349c7c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"benchmarks/benchmark_array_xd.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4ffac9de131eb19a9e7850c9445b6d42d6f1f01e197a2cffe821d66cb2ca634"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/formatting/polars_formatter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"0f5816a9c70c7e3c5ebbf3ad2a8736e0b1448831950b9dc483a7f6ce2e1e3458"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/parallel/parallel.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"be87a0e40f226a24d3af42ad701dea434dc7c12c59f6ff1d6a5db94e055ab51d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/sql/sql.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d39a19478d3bae1ef1c816466e965a07cdda50f8586b89a15382fbf4054e4053"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/tqdm.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"40c3e78f725fd72d15ce759c418cb4844667a64aef133ab82f5d1485d716f376"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/sharding.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"575ae5157cdaede48b757708c4384788d3d576838fe2420edac3a06545285f7c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/stratify.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f584f76c03c6635c2212e14804817cc5c2aec5198aa4cbed31417947e289f6f3"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"utils/release.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"49c98e2110d45935209935b0359b9b0cfd497044fa27760a5280d96ecaff5665"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"benchmarks/benchmark_iterating.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"48d8751fbc26e053d5458681319546f7e6aeeecd3987bc431ce14ef3c46aabb9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/deprecation_utils.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"d56c35552180bee685525199eb5e347f9b3a302554d1ba724dd02c4a61ca4af5"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/version.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"123627a40a27afe567a05f1626bf347c78cedd0e690366e64fbbacd72d9c8de4"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/naming.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cd16221d1c0fa2ff498f00a196bdb0b594a70223228a2a4d6500cbea947f93fb"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"benchmarks/benchmark_map_filter.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a98171a405ea58570bd0f3c0a1420cda28dab2b4670773424375f92a36a5c2ba"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: audio.py \u2194 image.py: \u0060src/datasets/features/audio.py\u0060 and \u0060src/datasets/features/image.py\u0060 change together 70% of the time (21 of the 30 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module \u2014 a sibling reference still needs an import \u2014 so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 21 shared commits counted here, the most recent 3 are \u0060f15c5997\u0060 Infer types from lance blobs (#7966); \u0060072eb549\u0060 Support pathlib.Path for feature input (#7755); \u006011320c3f\u0060 Add \u0060IterableDataset.push_to_hub()\u0060 (#7595) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/audio.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b5cf1e27d337bb6a58b1bd4c383e91ca28abc430a8f24083602ca479a970db99"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: setup.py \u2194 __init__.py: \u0060setup.py\u0060 and \u0060src/datasets/features/__init__.py\u0060 change together 67% of the time (8 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency \u2014 the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE \u2014 the registration is the link, and it is meant not to be an import \u2014 and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 8 shared commits counted here, the most recent 3 are \u0060c75df53d\u0060 feat(features): add BioSequence and BioStructure decodable features (\u2026; \u0060d4284e94\u0060 feat: add 3D mesh support and MeshFolder builder (#8055); \u006051388765\u0060 Add nifti support (#7815) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"setup.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"02ce38c86893391d82804079bf821af00a3a0ee15160f8a68b21ad294b4d7cc7"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: pandas.py \u2194 text.py: \u0060src/datasets/packaged_modules/pandas/pandas.py\u0060 and \u0060src/datasets/packaged_modules/text/text.py\u0060 change together 67% of the time (8 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency \u2014 the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE \u2014 the registration is the link, and it is meant not to be an import \u2014 and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 8 shared commits counted here, the most recent 3 are \u0060dc98f979\u0060 Add _generate_shards (#7943); \u00605bbbf1b1\u0060 Validate config name and data_files in packaged modules (#6915); \u00607feeb564\u0060 Unpack \u0060dl_manager.iter_files\u0060 to allow parallization (#4625) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/pandas/pandas.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ca5fd00ed3a80a3b8078b9329979cf3be336816f235996176f6fe34aa6cde11"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: config.py \u2194 __init__.py: \u0060src/datasets/config.py\u0060 and \u0060src/datasets/features/__init__.py\u0060 change together 50% of the time (6 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency \u2014 the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE \u2014 the registration is the link, and it is meant not to be an import \u2014 and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 6 shared commits counted here, the most recent 3 are \u0060c75df53d\u0060 feat(features): add BioSequence and BioStructure decodable features (\u2026; \u0060d4284e94\u0060 feat: add 3D mesh support and MeshFolder builder (#8055); \u006051388765\u0060 Add nifti support (#7815) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/config.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a471bb846639a8910bea62924445b4d68ca220675b00ff03adacfd2302745a1f"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: arrow_dataset.py \u2194 hub.py: \u0060src/datasets/arrow_dataset.py\u0060 and \u0060src/datasets/utils/hub.py\u0060 change together 50% of the time (5 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency \u2014 the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE \u2014 the registration is the link, and it is meant not to be an import \u2014 and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 5 shared commits counted here, the most recent 3 are \u0060a0c786c7\u0060 Support huggingface_hub v0.x and v1.x (#7783); \u006066d62426\u0060 Remove deprecated code (#6761); \u00603f699ab2\u0060 Replace \u0060list_files_info\u0060 with \u0060list_repo_tree\u0060 in \u0060push_to_hub\u0060 (#6510) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/arrow_dataset.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"4a06490a90f1fd854f7200ad35eee1943a5849dcc122668dc404b1d3f40e6121"}},{"ruleId":"D35","level":"warning","message":{"text":"Change coupling: csv.py \u2194 json.py: \u0060src/datasets/io/csv.py\u0060 and \u0060src/datasets/io/json.py\u0060 change together 50% of the time (5 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well \u2014 a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module \u2014 a sibling reference still needs an import \u2014 so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 5 shared commits counted here, the most recent 3 are \u0060c6fc5cdb\u0060 Preserve nullable integer columns in to_json/to_csv/to_sql (#8366); \u0060e52f4d0c\u0060 Add \u0060fsspec\u0060 support for \u0060to_json\u0060, \u0060to_csv\u0060, and \u0060to_parquet\u0060 (#6096); \u0060b3193829\u0060 Better \u0060tqdm\u0060 wrapper (#6433) \u2014 run \u0060git show\u0060 on any of them."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/io/csv.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3243b428ae02d37294bbae6769edb67075e3fb76c715352f0993cba7658d5cca"}},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"1b213f6eedd4b140d0bc37bdf1496f72811a643f34064f12518b32e9e83bcfc7"},"taxa":[{"id":"CICD-SEC-9","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"0e17f71490e4d120a48b2b2881ab866c93b272bef2febb673a3e8e42b2c288ab"},"taxa":[{"id":"CICD-SEC-9","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"note","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"eb00976a698a5d68999b7ee6d27206fd374e916853e7ff1ead5eed42386f043f"},"taxa":[{"id":"CICD-SEC-9","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"9db5c60d4084fc4489fda2c0b08e0f9f9eadaf1bef38325f94036ff8f23fd5e4"}},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"f75dd61fbc28fd905f770db3d1f7eb0358d9be28694424c2916fc17880d890c5"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"14f87399f93ab64f19861601492d66dc37c75b7d0db6e3fbad8a564d5778afce"},"taxa":[{"id":"CICD-SEC-4","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"fe274ba5adebde25ca0b3db842e44cbb1aaeb7cfecfbb7215cd452596ba1f4c2"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"D36","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d657599f6f99da1927d3377533dfc0888b34c4d84aa7d5579841fd72d0e39bce"},"taxa":[{"id":"CICD-SEC-6","toolComponent":{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35"}}]},{"ruleId":"M2","level":"note","message":{"text":"No ADRs: No Architecture Decision Records found \u2014 no conventional ADR directory, no numbered \u0060NNNN-title\u0060 documents in any markup this check reads, and nothing ADR-shaped by content. Design rationale recorded elsewhere (a design-notes tree, a mailing list, pull-request discussion) is not visible to this check and is not re-findable per decision, so a future maintainer cannot ask why one choice was made and get an answer."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"670b3d6e36a756d63097d0dfbf90afd5fc761308800b9354894a07c3f4e4aa14"}},{"ruleId":"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: docs/source/about_dataset_features.mdx links to \u0060./process#flatten\u0060, but \u0060docs/source/process\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_dataset_features.mdx"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"77b65edbdc42a6352a170a80b40c8b126c15657fbe71cbdb542e27112bb5e1da"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_dataset_load.mdx names \u0060datasets.packaged_modules.csv.Csv\u0060, but no file or folder \u0060datasets.packaged_modules.csv.Csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_dataset_load.mdx"},"region":{"startLine":21}}}],"partialFingerprints":{"codehealthFindingId/v1":"6616fd5e6ef392f19d24ecfb83481556b1ce406b022c9e166ab77b2109a36a29"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_dataset_load.mdx names \u0060datasets.packaged_modules.json.Json\u0060, but no file or folder \u0060datasets.packaged_modules.json.Json\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_dataset_load.mdx"},"region":{"startLine":22}}}],"partialFingerprints":{"codehealthFindingId/v1":"4b0e4d7347e3427847dabfe5601305ee445b3ff9c1a763c4f76ff7b405fae6ad"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_dataset_load.mdx names \u0060datasets.packaged_modules.sql.Sql\u0060, but no file or folder \u0060datasets.packaged_modules.sql.Sql\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_dataset_load.mdx"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"e49b14710a66332a6d708e1a5a248bb3c8f803d3bee35289c5713192a7d3a3c3"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_dataset_load.mdx links to \u0060./upload_dataset\u0060, but \u0060docs/source/upload_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_dataset_load.mdx"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"ed10c55358b85b17464949aad76a9c99c4064238127ed51e4a8bb3d3b5a6e9f4"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./stream\u0060, but \u0060docs/source/stream\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":39}}}],"partialFingerprints":{"codehealthFindingId/v1":"472902282a0ac753170df258c4bf1e89c96613d10e94f7ac905a406fc97d606d"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./tabular_load\u0060, but \u0060docs/source/tabular_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"fcf862aaa6dab6e4c62a69cede139a5a6bd316f853cef24985da87112366deef"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./nlp_load\u0060, but \u0060docs/source/nlp_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"10b4c7e24aa9efa772d9e77f03d0e0c6817fc6f1c0a7a2b9dab8a3dac44086b9"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./image_load\u0060, but \u0060docs/source/image_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"da76b02dbaeb2b93c4cbc44ccee3bbd56bc1d28c39dcabb279be4841e88e5f7f"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./audio_load]\u0060, but \u0060docs/source/audio_load]\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":87}}}],"partialFingerprints":{"codehealthFindingId/v1":"5f7bb152381327c99ee91920114341e2113971987d1238e1e16d35e03b07e3e5"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/about_mapstyle_vs_iterable.mdx links to \u0060./use_with_pytorch#stream-data\u0060, but \u0060docs/source/use_with_pytorch\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/about_mapstyle_vs_iterable.mdx"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"31648c8045ac6b79439e2b969fce20a32df2da7e3b8cffa7c442d7937fd3c8b2"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/access.mdx links to \u0060access/#slicing\u0060, but \u0060docs/source/access\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/access.mdx"},"region":{"startLine":157}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6155f6ab4655aa07f65b509f91f6570afbd57d32938f4cb2a8dec2387d3ccc6"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/access.mdx links to \u0060about_mapstyle_vs_iterable\u0060, but \u0060docs/source/about_mapstyle_vs_iterable\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/access.mdx"},"region":{"startLine":161}}}],"partialFingerprints":{"codehealthFindingId/v1":"066b880166327e5bf613b4b6f7e321b199e2ad8e00eead514c54773e859a4835"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/access.mdx links to \u0060process\u0060, but \u0060docs/source/process\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/access.mdx"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"06100026a91d01c581afed0b1cc321a5ca3b86a50949a5a48dc67e5b552c22ec"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/access.mdx links to \u0060stream\u0060, but \u0060docs/source/stream\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/access.mdx"},"region":{"startLine":163}}}],"partialFingerprints":{"codehealthFindingId/v1":"31905ff7fa13384b3a223a4cb50da9d2f59c8d18e7d8ba618f1f17608610d3df"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/audio_dataset.mdx links to \u0060repository_structure#split-pattern-hierarchy\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/audio_dataset.mdx"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"b25924bf2529e556e49822de7476f9ab80e3b2b27d16cbb9a639530263bb68cd"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/audio_load.mdx links to \u0060./installation#audio\u0060, but \u0060docs/source/installation\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/audio_load.mdx"},"region":{"startLine":9}}}],"partialFingerprints":{"codehealthFindingId/v1":"243f64f5c4d47b303c4403ed262d0dda1ba1de72b13b27889408b3c5b4581e46"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/audio_load.mdx links to \u0060./audio_dataset\u0060, but \u0060docs/source/audio_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/audio_load.mdx"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"c01c63777a3c12fbd389142d7af894c252d1e33db625a9a60f813a16226c68e1"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/cache.mdx documents the environment variable \u0060HF_HUB_CACHE\u0060, but no code, script or configuration file names it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/cache.mdx"},"region":{"startLine":50}}}],"partialFingerprints":{"codehealthFindingId/v1":"38f8c1b31eb623d2d05907d3403911c25159e77177b01c40c3a613daa1f8f2a3"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/cli.mdx links to \u0060repository_structure\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/cli.mdx"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"02a0ee1ecbc925d4a82d4e82e7788f9760c60d969ae9b0fcc606a32526e81839"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/create_dataset.mdx links to \u0060stream\u0060, but \u0060docs/source/stream\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/create_dataset.mdx"},"region":{"startLine":3}}}],"partialFingerprints":{"codehealthFindingId/v1":"e4423839d516cf32d1a00a0bc67e88e383c43e671341db0f2c3edb54486c7019"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/create_dataset.mdx links to \u0060upload_dataset#upload-with-the-hub-ui\u0060, but \u0060docs/source/upload_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/create_dataset.mdx"},"region":{"startLine":3}}}],"partialFingerprints":{"codehealthFindingId/v1":"1760c438cba096812355a29ba4fe1597e42129ea1287d99b19ca512579abb10a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/document_dataset.mdx links to \u0060repository_structure#split-pattern-hierarchy\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/document_dataset.mdx"},"region":{"startLine":13}}}],"partialFingerprints":{"codehealthFindingId/v1":"9ae35467b4bd6cf75dc3105514a32069faa0bdcbe4215b906feeadff9b98f67b"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/document_load.mdx links to \u0060./document_dataset\u0060, but \u0060docs/source/document_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/document_load.mdx"},"region":{"startLine":178}}}],"partialFingerprints":{"codehealthFindingId/v1":"06e96fbd115d235b28e018dc943a533718e928a7ee5f530dce387988d79ad081"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/harbor_load.mdx links to \u0060./installation#harbor\u0060, but \u0060docs/source/installation\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/harbor_load.mdx"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"e95161321a6df8d4aad2712a92d77b2b73eed92bcecfe19eee2fcb873fea58d6"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/harbor_load.mdx names \u0060task.toml\u0060, but no file or folder \u0060task.toml\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/harbor_load.mdx"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"27bef6dfcaa8318e747e6ec75eb87f42b7ffbfc32b73fd1a8a936285052a4f72"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/harbor_load.mdx names \u0060instruction.md\u0060, but no file or folder \u0060instruction.md\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/harbor_load.mdx"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3e09a8bf60ea741fac8b7f706a1382decfe71cec8b97caad029c977d0039f76"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/how_to.md links to \u0060tutorial\u0060, but \u0060docs/source/tutorial\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/how_to.md"},"region":{"startLine":5}}}],"partialFingerprints":{"codehealthFindingId/v1":"6471ea3417674350de4df951bb881080721720137b1e02504049ae071853bb98"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/image_dataset.mdx links to \u0060repository_structure#split-pattern-hierarchy\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/image_dataset.mdx"},"region":{"startLine":17}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c9154cfecd338b4ed9e01de4d1c120d8ad270713879c53ea84fcbfcd21f5fc0"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/image_dataset.mdx links to \u0060upload_dataset#upload-with-python\u0060, but \u0060docs/source/upload_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/image_dataset.mdx"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"3f74d8e727b646bdf1f9f30035bba7a65b1dad68f7bd681d4a0410eee406953d"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/image_load.mdx links to \u0060./installation#vision\u0060, but \u0060docs/source/installation\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/image_load.mdx"},"region":{"startLine":6}}}],"partialFingerprints":{"codehealthFindingId/v1":"c326d1d1aec0265a1448ed15cf1afe7d67ca56184ec4b2152c5b4f875f78694b"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/image_load.mdx links to \u0060./image_dataset\u0060, but \u0060docs/source/image_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/image_load.mdx"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"0cb2b601bf7122b2f67b54e84d8e988c8c10a1555231b068bbf5f8cf088549b2"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx links to \u0060share#create-the-repository\u0060, but \u0060docs/source/share\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":19}}}],"partialFingerprints":{"codehealthFindingId/v1":"a4a3c4044516407a840197c0915ebe9cfb429d5a7058b4b8837125ade235f7be"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx links to \u0060./upload_dataset\u0060, but \u0060docs/source/upload_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":38}}}],"partialFingerprints":{"codehealthFindingId/v1":"00e3e9ff5edf0f72c1b47e8ddc3253181d34c0cd28551f9906f090d6207d6960"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx links to \u0060tabular_load#csv-files\u0060, but \u0060docs/source/tabular_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":83}}}],"partialFingerprints":{"codehealthFindingId/v1":"753a89569fb280e826e8115a8d2e758e91ad8258fb4c3a238d61d9dbf2353078"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx links to \u0060tsfile_load\u0060, but \u0060docs/source/tsfile_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":254}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d5ae8ab21f1b4abcd4c732f746e520e9fe48f714d3aa175c6f72e2a1d74f305"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx names \u0060instruction.md\u0060, but no file or folder \u0060instruction.md\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":260}}}],"partialFingerprints":{"codehealthFindingId/v1":"82fb55b17797d408d46b64262c8592bef4b8de4c11402a94c51df8acebb55f0a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx names \u0060task.toml\u0060, but no file or folder \u0060task.toml\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":262}}}],"partialFingerprints":{"codehealthFindingId/v1":"797e5ec96c68cb624b6ac09780dee76df71f3973f2436b6667b9281d3b5fa12d"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx links to \u0060harbor_load\u0060, but \u0060docs/source/harbor_load\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":273}}}],"partialFingerprints":{"codehealthFindingId/v1":"d0b10e46c42092ca05558e9b8e8d0190f53db48cccfec9eb569036644366f36f"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/loading.mdx names \u0060metadata.csv\u0060, but no file or folder \u0060metadata.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/loading.mdx"},"region":{"startLine":280}}}],"partialFingerprints":{"codehealthFindingId/v1":"368c71542b3858d41465196f524a2000728c106dd4f23441bc404f107646ac9a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/mesh_dataset.mdx links to \u0060repository_structure#split-pattern-hierarchy\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/mesh_dataset.mdx"},"region":{"startLine":42}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f20e499a439285a24ce5e36be404897e9352bc10a410f84f6b1e513e0f334b4"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/mesh_dataset.mdx links to \u0060upload_dataset#upload-with-python\u0060, but \u0060docs/source/upload_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/mesh_dataset.mdx"},"region":{"startLine":155}}}],"partialFingerprints":{"codehealthFindingId/v1":"1ba86411d984fc8e826ce8770c21e6587e69ad7e1509f2020f84827e43e71aaa"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/mesh_load.mdx links to \u0060./installation#mesh\u0060, but \u0060docs/source/installation\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/mesh_load.mdx"},"region":{"startLine":6}}}],"partialFingerprints":{"codehealthFindingId/v1":"0e68abeed52e49b1901139d449b9530212eef6fce8fb98af20dead496cb44e12"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/mesh_load.mdx links to \u0060./mesh_dataset\u0060, but \u0060docs/source/mesh_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/mesh_load.mdx"},"region":{"startLine":111}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ccc71d5441e5f4286fbfc41018d9604c4d4a55f6711acb9f4e3105c8da3d548"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/nifti_dataset.mdx names \u0060metadata.csv\u0060, but no file or folder \u0060metadata.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/nifti_dataset.mdx"},"region":{"startLine":67}}}],"partialFingerprints":{"codehealthFindingId/v1":"b0fd8a95aaf6ad0dac1a387c9e2c785e49ad2f73e29328c004562437adbf9a3a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx names \u0060datasets.config\u0060, but no file or folder \u0060datasets.config\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":541}}}],"partialFingerprints":{"codehealthFindingId/v1":"20b8896b7f518533087e2bca5468f56a36eae251bd47d8b2469e657ac2775cc4"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_numpy\u0060, but \u0060docs/source/use_with_numpy\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":703}}}],"partialFingerprints":{"codehealthFindingId/v1":"9e0437f86307b36a91ece88d0956ec8f67a68210bcf907fc6eb3bbc418c1fa8f"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_pytorch\u0060, but \u0060docs/source/use_with_pytorch\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":704}}}],"partialFingerprints":{"codehealthFindingId/v1":"7b9e848b1584e02e5ff73205b06084fb300550ffc5f9629918861867f270010e"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_tensorflow\u0060, but \u0060docs/source/use_with_tensorflow\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":705}}}],"partialFingerprints":{"codehealthFindingId/v1":"2c0cd1074e7e98ab19409f54706435ce370141f9c135ccab0fc32f6acff344ff"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_jax\u0060, but \u0060docs/source/use_with_jax\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":706}}}],"partialFingerprints":{"codehealthFindingId/v1":"51cbc0d64ef969cacda8c6057e9ea2504abbf82da998fe0547e71570f14cdb76"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_pandas\u0060, but \u0060docs/source/use_with_pandas\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":730}}}],"partialFingerprints":{"codehealthFindingId/v1":"09743c00abcda68119693526697b8e7691020bf668b8af63ae1612fc02fdbfbc"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/process.mdx links to \u0060use_with_polars\u0060, but \u0060docs/source/use_with_polars\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/process.mdx"},"region":{"startLine":731}}}],"partialFingerprints":{"codehealthFindingId/v1":"36c0d3a60980f2f42de531d8fbe268984c8315b633784a6f195602d0512c3bd9"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/quickstart.mdx links to \u0060./how_to\u0060, but \u0060docs/source/how_to\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/quickstart.mdx"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"496d335cdfe05f999bfb078f84fafe6cc7bb2e0e9ebf2300c987376713ad4cbd"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/quickstart.mdx links to \u0060./about_arrow\u0060, but \u0060docs/source/about_arrow\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/quickstart.mdx"},"region":{"startLine":380}}}],"partialFingerprints":{"codehealthFindingId/v1":"0fa2e5992b75ac0e573a2bd5199a2d188d8eb71cd29855668f272c55462e5ace"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060train.csv\u0060, but no file or folder \u0060train.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":10}}}],"partialFingerprints":{"codehealthFindingId/v1":"c153cba8448cb9f7b1f888ed785223b774f7bd0659623c5a652dbef274ea97e2"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060test.csv\u0060, but no file or folder \u0060test.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":10}}}],"partialFingerprints":{"codehealthFindingId/v1":"74fc92c6a9167ff29ed0b1d306930df6a83f348dde2b9ea7bfc35b28dabd029f"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx links to \u0060dataset_card\u0060, but \u0060docs/source/dataset_card\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":12}}}],"partialFingerprints":{"codehealthFindingId/v1":"132983a82935ac844906afc652554739cc68aa77836abdb790c204081bad60f0"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx links to \u0060./package_reference/builder_classes\u0060, but \u0060docs/source/package_reference/builder_classes\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":142}}}],"partialFingerprints":{"codehealthFindingId/v1":"096fc594a4f5b0d71bbd6406e415046269b6775594795499e0264cdbd2b7145b"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060train1.csv\u0060, but no file or folder \u0060train1.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f63b776a01ae10931752229f3d30d0acb958886042a307fb8ffc4bc9252f47e"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060validation.csv\u0060, but no file or folder \u0060validation.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"987f65b09bee1e62b6a2333365b3085cf185893c81eefc65308d39f4df6e7093"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060validation1.csv\u0060, but no file or folder \u0060validation1.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":181}}}],"partialFingerprints":{"codehealthFindingId/v1":"02a731e4267308469ce5bd7f50a7f4cc013ac367430d424c72102e05f1285fa7"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/repository_structure.mdx names \u0060test1.csv\u0060, but no file or folder \u0060test1.csv\u0060 exists. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/repository_structure.mdx"},"region":{"startLine":182}}}],"partialFingerprints":{"codehealthFindingId/v1":"4d2b0d4c31e3b3b10a1465c1ce39b3de19e777f6df549e99b819334c11e7de9e"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/share.mdx links to \u0060./repository_structure\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/share.mdx"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"76349f98f64d858e14a2c9faf3b43020bb94b87b6349535270ceb0b0150e4f8a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/share.mdx links to \u0060./load_hub\u0060, but \u0060docs/source/load_hub\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/share.mdx"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"95026eb886ed189c55971f054d6b40e4304178610ceb1f53e7f130397f171914"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/share.mdx links to \u0060dataset_card\u0060, but \u0060docs/source/dataset_card\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/share.mdx"},"region":{"startLine":211}}}],"partialFingerprints":{"codehealthFindingId/v1":"5272e054d527116f5dc5744f9bba848e3b1f54689cd6faf0b3c01235a484074c"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/stream.mdx links to \u0060./about_mapstyle_vs_iterable\u0060, but \u0060docs/source/about_mapstyle_vs_iterable\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/stream.mdx"},"region":{"startLine":64}}}],"partialFingerprints":{"codehealthFindingId/v1":"fb00e25865fed609c4f8765e10606e6c43038579264f7de06ea280268286d4d3"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/troubleshoot.mdx links to \u0060cache\u0060, but \u0060docs/source/cache\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/troubleshoot.mdx"},"region":{"startLine":79}}}],"partialFingerprints":{"codehealthFindingId/v1":"649e958bcd41ab90599b7a7a9a6eddce98f1010ba9318b7c7c656d02ae753858"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/tutorial.md links to \u0060./quickstart\u0060, but \u0060docs/source/quickstart\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/tutorial.md"},"region":{"startLine":5}}}],"partialFingerprints":{"codehealthFindingId/v1":"9f5ee8e9acac8504baa0986e4865132816ca1ebff5ea8525ff8a8861d18cc0ab"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/upload_dataset.mdx links to \u0060process\u0060, but \u0060docs/source/process\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/upload_dataset.mdx"},"region":{"startLine":130}}}],"partialFingerprints":{"codehealthFindingId/v1":"5605ddfcd834b8681acf8c8b5e8748fb3e13caa83bee921fb3377e6fd1840d9a"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/upload_dataset.mdx links to \u0060repository_structure\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/upload_dataset.mdx"},"region":{"startLine":132}}}],"partialFingerprints":{"codehealthFindingId/v1":"ccbd430248067df493679f451ed621d8e55d6ae023d423f9887ba0b4865a3f85"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/use_with_pytorch.mdx links to \u0060./about_mapstyle_vs_iterable\u0060, but \u0060docs/source/about_mapstyle_vs_iterable\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/use_with_pytorch.mdx"},"region":{"startLine":191}}}],"partialFingerprints":{"codehealthFindingId/v1":"f6e7120e9bae7e610fea4e73148ecb160b5a1989cfe926050f6fd119d048c14c"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/video_dataset.mdx links to \u0060repository_structure#split-pattern-hierarchy\u0060, but \u0060docs/source/repository_structure\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/video_dataset.mdx"},"region":{"startLine":13}}}],"partialFingerprints":{"codehealthFindingId/v1":"32cd96b49258247ac1d78372626d9c0286a7c25bc314fad8565cce18460bb201"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/video_load.mdx links to \u0060./video_dataset\u0060, but \u0060docs/source/video_dataset\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/video_load.mdx"},"region":{"startLine":144}}}],"partialFingerprints":{"codehealthFindingId/v1":"304e84a95c13d5dc240b5d28ce7d298e8900de3c943260c40921f1317bd54d87"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/source/package_reference/utilities.mdx runs \u0060DATASETS_VERBOSITY=error ./myprogram.py\u0060, but \u0060myprogram.py\u0060 does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents\u0027 own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"docs/source/package_reference/utilities.mdx"},"region":{"startLine":17}}}],"partialFingerprints":{"codehealthFindingId/v1":"4dc9b87efe239019972ed2f8eff257bac65fac10461313afdca1acdc91920d11"}},{"ruleId":"P3","level":"note","message":{"text":"No SAST: No static application security testing detected. For this repository\u0027s stack, add bandit, \u0060semgrep --config=p/python\u0060, or CodeQL\u0027s python pack as a CI step. What was searched, so you can tell an absence from a miss: the 10510 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":"P6","level":"note","message":{"text":"No changelog: No CHANGELOG/HISTORY/RELEASES file \u2014 what shipped when isn\u0027t easy to reconstruct for support or audit. (Versioning/tagging makes releases traceable, but a changelog records the what.)"},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"dda5aa5aed8cbb292c3ef2b733bc138f614293ae6426c85e98bf31ef330d9415"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060config.PDFPLUMBER_AVAILABLE and \u0022pdfplumber\u0022 in sys.modules\u0060 appears character-identically in 2 files \u2014 src/datasets/arrow_writer.py, src/datasets/features/features.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":"src/datasets/arrow_writer.py"},"region":{"startLine":305}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc74040376741c901f88354a756cfa148c6d31356a7122b218bb7e103aa9bd75"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060config.PIL_AVAILABLE and \u0022PIL\u0022 in sys.modules\u0060 appears character-identically in 6 files \u2014 src/datasets/arrow_writer.py, src/datasets/features/features.py, src/datasets/formatting/jax_formatter.py, src/datasets/formatting/np_formatter.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":"src/datasets/arrow_writer.py"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"c2025fc426c97b24a2d096877aa0027902a94fce968abc6713d8d5a3cfd22fe6"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060config.TORCHCODEC_AVAILABLE and \u0022torchcodec\u0022 in sys.modules\u0060 appears character-identically in 5 files \u2014 src/datasets/features/features.py, src/datasets/formatting/jax_formatter.py, src/datasets/formatting/np_formatter.py, src/datasets/formatting/tf_formatter.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":"src/datasets/features/features.py"},"region":{"startLine":330}}}],"partialFingerprints":{"codehealthFindingId/v1":"6a222575d19fe4822b341a0dec45a2fdfc3fd0ca3f90b4355960a02025fc5273"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060config.TORCHVISION_AVAILABLE and \u0022torchvision\u0022 in sys.modules\u0060 appears character-identically in 4 files \u2014 src/datasets/formatting/jax_formatter.py, src/datasets/formatting/np_formatter.py, src/datasets/formatting/tf_formatter.py, src/datasets/formatting/torch_formatter.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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":109}}}],"partialFingerprints":{"codehealthFindingId/v1":"95fd2b40f9bd84eff2db160de94e83de073baa3c7e72bf883c98015528258b2e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060config.TORCH_AVAILABLE and \u0022torch\u0022 in sys.modules\u0060 appears character-identically in 4 files \u2014 src/datasets/features/features.py, src/datasets/formatting/jax_formatter.py, src/datasets/formatting/np_formatter.py, src/datasets/formatting/tf_formatter.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":"src/datasets/features/features.py"},"region":{"startLine":311}}}],"partialFingerprints":{"codehealthFindingId/v1":"255668dbd0f4f8a3edaa2b68928399c4784f443e3f9a931d33b66ba1ed6ea027"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060download_mode or DownloadMode.REUSE_DATASET_IF_EXISTS\u0060 appears character-identically in 2 files \u2014 src/datasets/builder.py, src/datasets/load.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":"src/datasets/builder.py"},"region":{"startLine":793}}}],"partialFingerprints":{"codehealthFindingId/v1":"20c232656acffb786c1794d72c9dedc84d4aa52f7583e8ab2fd48662355a0545"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060features is not None and self.config.columns is not None\u0060 appears character-identically in 2 files \u2014 src/datasets/packaged_modules/fasta/fasta.py, src/datasets/packaged_modules/fastq/fastq.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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"bde321c70a5b5ea4d3b67644fa539e96d26535bbab6a393f948313c4aa94a1b5"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(value, (np.character, np.ndarray)) and np.issubdtype(value.dtype, np.character)\u0060 appears character-identically in 3 files \u2014 src/datasets/formatting/jax_formatter.py, src/datasets/formatting/np_formatter.py, src/datasets/formatting/torch_formatter.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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":89}}}],"partialFingerprints":{"codehealthFindingId/v1":"788bd5c6ee8379fcc5278089b53d56a67bf57cb6aeba869b0b17f0f66459585a"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(value, (np.number, np.ndarray)) and np.issubdtype(value.dtype, np.floating)\u0060 appears character-identically in 3 files \u2014 src/datasets/formatting/jax_formatter.py, src/datasets/formatting/tf_formatter.py, src/datasets/formatting/torch_formatter.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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":101}}}],"partialFingerprints":{"codehealthFindingId/v1":"ecb7d68d291386a64ca9b2f1ed405c6d3a497732da4da7b21fa62bc3c20cca16"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060isinstance(value, (np.number, np.ndarray)) and np.issubdtype(value.dtype, np.integer)\u0060 appears character-identically in 3 files \u2014 src/datasets/formatting/jax_formatter.py, src/datasets/formatting/tf_formatter.py, src/datasets/formatting/torch_formatter.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":"src/datasets/formatting/jax_formatter.py"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"83b8bc6fd938216b4cc52f79a956e8c2972359fc0cdb4bf31e63620034e7af9f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060local_files and is_local_path(x[\u0022path\u0022])\u0060 appears character-identically in 6 files \u2014 src/datasets/features/audio.py, src/datasets/features/image.py, src/datasets/features/mesh.py, src/datasets/features/nifti.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":"src/datasets/features/audio.py"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"bf69982cb497e84620849187422dfa3f32c5b152abf3f741e1288aa6d8c04b4f"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060max_batch_bytes is not None and batch_bytes \u003E 0 and batch_bytes \u002B record_bytes \u003E max_batch_bytes\u0060 appears character-identically in 3 files \u2014 src/datasets/packaged_modules/fasta/fasta.py, src/datasets/packaged_modules/fastq/fastq.py, src/datasets/packaged_modules/genbank/genbank.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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":257}}}],"partialFingerprints":{"codehealthFindingId/v1":"48425a39ae7d2410ac4c020b1f4e95197ddbd89463e5f9b70db788c9aa8058df"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060max_shard_size is not None and num_shards is not None\u0060 appears character-identically in 2 files \u2014 src/datasets/dataset_dict.py, src/datasets/iterable_dataset.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":"src/datasets/dataset_dict.py"},"region":{"startLine":2431}}}],"partialFingerprints":{"codehealthFindingId/v1":"d615d0181bb5ee63c6b2fc7b925fba6a373f37aa674103caabca64d8ca9a6d74"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060os.environ.get(\u0022HF_DATASETS_STACK_MULTIPROCESSING_DOWNLOAD_PROGRESS_BARS\u0022) == \u00221\u0022 and multiprocessing.current_process()._identity\u0060 appears character-identically in 2 files \u2014 src/datasets/download/download_manager.py, src/datasets/utils/file_utils.py. It is one line, so the duplication detector\u0027s token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/download/download_manager.py"},"region":{"startLine":212}}}],"partialFingerprints":{"codehealthFindingId/v1":"0b6e03f26d0f93288fa8c0ba7f3ec7a2ec9effdc94cc77748de05632552b9c96"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060path is not None and os.path.isfile(path)\u0060 appears character-identically in 2 files \u2014 src/datasets/features/mesh.py, src/datasets/features/video.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":"src/datasets/features/mesh.py"},"region":{"startLine":295}}}],"partialFingerprints":{"codehealthFindingId/v1":"1926bdd036afbc39f4d57de4166ffbfada9e202a5797e667461ef05cfe7ab84e"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060remote_files and is_remote_url(x[\u0022path\u0022])\u0060 appears character-identically in 6 files \u2014 src/datasets/features/audio.py, src/datasets/features/image.py, src/datasets/features/mesh.py, src/datasets/features/nifti.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":"src/datasets/features/audio.py"},"region":{"startLine":327}}}],"partialFingerprints":{"codehealthFindingId/v1":"54d3918e8e2c5d2d88580ae4de3c4ee22b2ccc5f87e2a656abf095984d30663b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060revision is not None and not revision.startswith(\u0022refs/pr/\u0022)\u0060 appears character-identically in 2 files \u2014 src/datasets/dataset_dict.py, src/datasets/iterable_dataset.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":"src/datasets/dataset_dict.py"},"region":{"startLine":1789}}}],"partialFingerprints":{"codehealthFindingId/v1":"58e1d56cec5c6c93885be5f45d096aee4c5249668bd4845551047c175de8d479"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.config.columns is None and features is not None\u0060 appears character-identically in 3 files \u2014 src/datasets/packaged_modules/fasta/fasta.py, src/datasets/packaged_modules/fastq/fastq.py, src/datasets/packaged_modules/genbank/genbank.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":"src/datasets/packaged_modules/fasta/fasta.py"},"region":{"startLine":180}}}],"partialFingerprints":{"codehealthFindingId/v1":"85f17d074a919ef7987467d46f5eacf16e8315c77d2c6a4363471d0d87d58a25"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.config.columns is not None and self.config.features is not None and set(self.config.columns) != set(self.config.features)\u0060 appears character-identically in 2 files \u2014 src/datasets/packaged_modules/parquet/parquet.py, src/datasets/packaged_modules/vortex/vortex.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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":99}}}],"partialFingerprints":{"codehealthFindingId/v1":"32141eedf42a034db459a1781e3a395da601a235963cd5ab8f66e36c3f9c3831"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.config.columns is not None and set(self.config.columns) != set(self.info.features)\u0060 appears character-identically in 2 files \u2014 src/datasets/packaged_modules/parquet/parquet.py, src/datasets/packaged_modules/vortex/vortex.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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":146}}}],"partialFingerprints":{"codehealthFindingId/v1":"bdc2eeca7c0f8c150dda75ce75e96c5ee2111a9bd342b21278f9fc0f124006e4"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.config.features is not None and self.config.columns is not None\u0060 appears character-identically in 2 files \u2014 src/datasets/packaged_modules/parquet/parquet.py, src/datasets/packaged_modules/vortex/vortex.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":"src/datasets/packaged_modules/parquet/parquet.py"},"region":{"startLine":186}}}],"partialFingerprints":{"codehealthFindingId/v1":"6919a81b8c0c29a9abf96018821bcea5a08b810f5b044211fc2bb7e0566bc0d7"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.features and column_name in self.features and self.features._column_requires_decoding[column_name]\u0060 appears character-identically in 2 files \u2014 src/datasets/formatting/formatting.py, src/datasets/formatting/polars_formatter.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":"src/datasets/formatting/formatting.py"},"region":{"startLine":274}}}],"partialFingerprints":{"codehealthFindingId/v1":"780a47165ec6d49f6f72f904026818eeba2a574d73207b1aaa39ba13f0a8fe42"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060self.num_proc is None or self.num_proc == 1\u0060 appears character-identically in 3 files \u2014 src/datasets/io/csv.py, src/datasets/io/json.py, src/datasets/io/sql.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":"src/datasets/io/csv.py"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"71dca7083e9509e30c9a8999c5557122859dc3d91943bf95968b272fd905bc5b"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060value.get(\u0022bytes\u0022) is not None or value.get(\u0022path\u0022) is not None\u0060 appears character-identically in 7 files \u2014 src/datasets/features/audio.py, src/datasets/features/bio_sequence.py, src/datasets/features/bio_structure.py, src/datasets/features/image.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":"src/datasets/features/audio.py"},"region":{"startLine":156}}}],"partialFingerprints":{"codehealthFindingId/v1":"85cbeafaa39647288ed5add0cde10fad4bb92927d4680d3a09aa7cb013953909"}},{"ruleId":"X10","level":"note","message":{"text":"Duplicated predicate: \u0060value.get(\u0022path\u0022) is not None and os.path.isfile(value[\u0022path\u0022])\u0060 appears character-identically in 6 files \u2014 src/datasets/features/audio.py, src/datasets/features/bio_sequence.py, src/datasets/features/bio_structure.py, src/datasets/features/image.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":"src/datasets/features/audio.py"},"region":{"startLine":136}}}],"partialFingerprints":{"codehealthFindingId/v1":"8e09de3efdb83d4ef2199b597ac07c01ef46dd960efd4c73e0aad3849ddd3704"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060generate_from_dict\u0060 is public and takes \u0060obj: Any\u0060 from its caller, and it calls itself at line 1645 (\u0060generate_from_dict\u0060) with a piece of \u0060obj\u0060 (and at line 1648, line 1658, line 1661, line 1664) \u2014 and nowhere in \u0060generate_from_dict\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060generate_from_dict\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/features/features.py"},"region":{"startLine":1645}}}],"partialFingerprints":{"codehealthFindingId/v1":"f7c8ac80fcc0fccc1ef128c3f0b54284f0b9f08af24804912c4db3c2f2033dee"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060json_encode_field\u0060 is public and takes \u0060example: Any\u0060 from its caller, and it calls itself at line 32 (\u0060json_encode_field\u0060) with a piece of \u0060example\u0060 (and at line 34) \u2014 and nowhere in \u0060json_encode_field\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060json_encode_field\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/json.py"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"858984f65a4e105ff92f44ca84749548c7256600e6946c7b4006ad0a9f2b96a6"}},{"ruleId":"X17","level":"warning","message":{"text":"Recursive walk over a caller-supplied document has no depth cap: \u0060json_decode_field\u0060 is public and takes \u0060example: Any\u0060 from its caller, and it calls itself at line 53 (\u0060json_decode_field\u0060) with a piece of \u0060example\u0060 (and at line 55) \u2014 and nowhere in \u0060json_decode_field\u0060 is there a depth parameter, a descent counter, or any other cap. The walk therefore spends one stack frame per LEVEL of the value it is handed, so the nesting of the caller\u0027s document \u2014 not this code \u2014 decides how deep the stack goes. Python\u0027s parsers accept far more nesting than its stack allows: \u0060json.loads\u0060 turns 3,000 bytes of brackets into 1,500 levels and \u0060xml.etree.ElementTree\u0060 parses tens of thousands, while a walk like this one raises \u0060RecursionError\u0060 once it passes the interpreter\u0027s default limit of 1,000 frames. Wherever that exception lands, the work fails: a request errors, and outside any \u0060try\u0060 the worker or the program exits with it. Raising \u0060sys.setrecursionlimit\u0060 only moves the number the document has to beat. Thread a depth argument through \u0060json_decode_field\u0060 and reject the value past a fixed maximum, or rewrite the descent with an explicit stack."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/json.py"},"region":{"startLine":53}}}],"partialFingerprints":{"codehealthFindingId/v1":"94a73384b1d79e22155fbfdc7bf6796dba77c82b2607c3a1768bd97f91dea9e7"}},{"ruleId":"X23","level":"note","message":{"text":"Diagnostic log message is built whether or not it is wanted: \u0060debug\u0060 at line 1037 is called with an argument built by \u0060\u0022\u2026\u0022.join(self.info.splits)\u0060 (line 1037), whose cost grows with the collection it walks. Python evaluates a call\u0027s arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached \u2014 and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no \u0060isEnabledFor(logging.DEBUG)\u0060 test, no debug flag, no \u0060lambda\u0060 the logger calls only when the level is on."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1037}}}],"partialFingerprints":{"codehealthFindingId/v1":"13804fb47ed32b85558f1b0a21efa9448da5141ec89563a47ab85d5fd184d83a"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/load.py"},"region":{"startLine":198}}}],"partialFingerprints":{"codehealthFindingId/v1":"4477036e256b5caba5246eea89a52fe1910dd3286bb4791a9973e222f3c873d9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/builder.py"},"region":{"startLine":1665}}}],"partialFingerprints":{"codehealthFindingId/v1":"823618e79ffaf9227554f322a979d3f3cbb790b463faa2421999d48424ff652c"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/download/download_manager.py"},"region":{"startLine":200}}}],"partialFingerprints":{"codehealthFindingId/v1":"e983570aec4691937ac74522dc7e1849b9261327de5978d334b3454bcdabfcf9"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/packaged_modules/tsfile/tsfile.py"},"region":{"startLine":420}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c8fb58ea5f0f0741abfd22a5fcaac19366567cce969dfd92a0516c13e3b233b"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/json.py"},"region":{"startLine":61}}}],"partialFingerprints":{"codehealthFindingId/v1":"5956af07b3a39e88f7b76678828505120f1354ea5071628c32ecf5b5697b79ef"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (caught, then discarded): \u0060except Exception\u0060 takes every exception and records none of it \u2014 the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/_dill.py"},"region":{"startLine":276}}}],"partialFingerprints":{"codehealthFindingId/v1":"f3e534627d8da508a8a9331753d0ce2309caf2e7c486f1a4a4962a5393037879"}},{"ruleId":"X3","level":"warning","message":{"text":"Swallowed exception (empty catch): An empty catch block silently discards the error \u2014 failures vanish with no log and no rethrow. Log it, handle it, or don\u0027t catch it."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/_dill.py"},"region":{"startLine":288}}}],"partialFingerprints":{"codehealthFindingId/v1":"91f7e0d301a3250ee9058b2235be66b6eda2983e5b1422f2337998558127d31f"}},{"ruleId":"X4","level":"note","message":{"text":"Interpolated log message defeats structured logging: \u0060warning\u0060 at line 59 is handed an f-string as its message, so the logger receives one finished string \u2014 the values in it cannot be queried, filtered or aggregated as fields, every occurrence reads as a different message, and the string is built even when the record is filtered out. Pass the values beside a constant message instead: \u0060logger.warning(\u0022order %s moved to %s\u0022, order_id, status)\u0060 with the standard library\u0027s \u0060logging\u0060, which keeps the message and its arguments apart on the record, or \u0060log.warning(\u0022order moved\u0022, order_id=order_id, status=status)\u0060 with structlog."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/logging.py"},"region":{"startLine":59}}}],"partialFingerprints":{"codehealthFindingId/v1":"a805ee2b64e36204121b83e4925dfc66fde5b12b8c0ac5c34230fc296767e344"}},{"ruleId":"X7","level":"note","message":{"text":"Silent fallback default on parse failure: \u0060__eq__\u0060 returns \u0060False\u0060 when \u0060(TypeError, ValueError)\u0060 is raised, with no log or raise \u2014 a malformed value silently becomes that default. Log the input or fail validation. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment on the handler or in the docstring, and the row stops firing."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/datasets/utils/version.py"},"region":{"startLine":75}}}],"partialFingerprints":{"codehealthFindingId/v1":"059e3761088bb9c372ee22381a77005204b80545e91ddc8681437369a8fcf7a1"}}],"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-1059","guid":"a2381a08-60f6-9554-a8b8-f3018cfaaca5","name":"Insufficient Technical Documentation","shortDescription":{"text":"Insufficient Technical Documentation"},"helpUri":"https://cwe.mitre.org/data/definitions/1059.html"},{"id":"CWE-1104","guid":"4c918cb5-b2a6-6c55-9963-a44ee464305e","name":"Use of Unmaintained Third Party Components","shortDescription":{"text":"Use of Unmaintained Third Party Components"},"helpUri":"https://cwe.mitre.org/data/definitions/1104.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-214","guid":"b10ad120-fb22-1351-9348-aa23b453e815","name":"CWE-214","shortDescription":{"text":"CWE-214"},"helpUri":"https://cwe.mitre.org/data/definitions/214.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-494","guid":"b8a65e0d-e459-4a55-a931-fc1136482375","name":"Download of Code Without Integrity Check","shortDescription":{"text":"Download of Code Without Integrity Check"},"helpUri":"https://cwe.mitre.org/data/definitions/494.html"},{"id":"CWE-532","guid":"1cd8877a-76e8-ce54-b40b-779af23364a0","name":"Insertion of Sensitive Information into Log File","shortDescription":{"text":"Insertion of Sensitive Information into Log File"},"helpUri":"https://cwe.mitre.org/data/definitions/532.html"},{"id":"CWE-611","guid":"1afbae66-ea29-2d59-aaa2-134e3ae2e85a","name":"Improper Restriction of XML External Entity Reference","shortDescription":{"text":"Improper Restriction of XML External Entity Reference"},"helpUri":"https://cwe.mitre.org/data/definitions/611.html"},{"id":"CWE-732","guid":"1da27e8f-b330-7650-ab63-bd61953eae5d","name":"Incorrect Permission Assignment for Critical Resource","shortDescription":{"text":"Incorrect Permission Assignment for Critical Resource"},"helpUri":"https://cwe.mitre.org/data/definitions/732.html"},{"id":"CWE-77","guid":"332c8ade-6612-9f56-a06b-d8d90b1a8750","name":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/77.html"},{"id":"CWE-78","guid":"2e31ceaf-c7ae-2e5e-9661-cfb1362789cf","name":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/78.html"},{"id":"CWE-79","guid":"fd45580b-e8c4-fc5e-8c2f-aa8fab0b4dbf","name":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)","shortDescription":{"text":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/79.html"},{"id":"CWE-798","guid":"5e8f057d-fee3-995a-a0cb-9fc5b0d174d1","name":"Use of Hard-coded Credentials","shortDescription":{"text":"Use of Hard-coded Credentials"},"helpUri":"https://cwe.mitre.org/data/definitions/798.html"},{"id":"CWE-829","guid":"13c33925-97fb-5a5e-b40c-56d328b8a4d7","name":"Inclusion of Functionality from Untrusted Control Sphere","shortDescription":{"text":"Inclusion of Functionality from Untrusted Control Sphere"},"helpUri":"https://cwe.mitre.org/data/definitions/829.html"},{"id":"CWE-89","guid":"6d08fdad-37eb-c150-bbf0-d7d946863407","name":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/89.html"},{"id":"CWE-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":"A01:2025","guid":"df693558-c822-0452-8f7b-4d53cb6bcc59","name":"Broken Access Control","shortDescription":{"text":"Broken Access Control"},"helpUri":"https://top10.owasp.org/2025/A01_2025-Broken_Access_Control/"},{"id":"A02:2025","guid":"668dee9e-41bc-6354-97d0-fdf8f40c50c1","name":"Security Misconfiguration","shortDescription":{"text":"Security Misconfiguration"},"helpUri":"https://top10.owasp.org/2025/A02_2025-Security_Misconfiguration/"},{"id":"A03:2025","guid":"168e227c-7735-2e57-bc6e-997affe644c5","name":"Software Supply Chain Failures","shortDescription":{"text":"Software Supply Chain Failures"},"helpUri":"https://top10.owasp.org/2025/A03_2025-Software_Supply_Chain_Failures/"},{"id":"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":"A09:2025","guid":"78892bc9-3c98-495d-881c-8af1390d643c","name":"Security Logging \u0026 Alerting Failures","shortDescription":{"text":"Security Logging \u0026 Alerting Failures"},"helpUri":"https://top10.owasp.org/2025/A09_2025-Security_Logging_and_Alerting_Failures/"}]},{"name":"OWASP Top 10 CI/CD Security Risks","guid":"3c9b2a6e-5d14-4f7b-8e02-6a1d9c4b7f35","organization":"OWASP Foundation","informationUri":"https://owasp.org/www-project-top-10-ci-cd-security-risks/","isComprehensive":false,"shortDescription":{"text":"The OWASP Top 10 CI/CD Security Risks."},"taxa":[{"id":"CICD-SEC-3","guid":"458c83a6-ebf7-cf55-8cc3-b4d949bbf271","name":"Dependency Chain Abuse","shortDescription":{"text":"Dependency Chain Abuse"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-03-Dependency-Chain-Abuse"},{"id":"CICD-SEC-4","guid":"c859d8ea-8b24-a157-9406-94929c10397a","name":"Poisoned Pipeline Execution (PPE)","shortDescription":{"text":"Poisoned Pipeline Execution (PPE)"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-04-Poisoned-Pipeline-Execution"},{"id":"CICD-SEC-6","guid":"f2ee2486-b260-2952-a41f-6b67fa713940","name":"Insufficient Credential Hygiene","shortDescription":{"text":"Insufficient Credential Hygiene"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-06-Insufficient-Credential-Hygiene"},{"id":"CICD-SEC-9","guid":"b3d36727-0395-5b51-94c4-5e173d62eab3","name":"Improper Artifact Integrity Validation","shortDescription":{"text":"Improper Artifact Integrity Validation"},"helpUri":"https://owasp.github.io/www-project-top-10-ci-cd-security-risks/CICD-SEC-09-Improper-Artifact-Integrity-Validation"}]}],"properties":{"codehealthPublication":{"public":true,"notice":"This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings \u2014 which rule fired, in which file, on which line, and how to fix it \u2014 are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.","securityFindingsRedacted":24,"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."]}]}