{"$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":"D8","name":"Code Coverage","shortDescription":{"text":"Code Coverage"},"helpUri":"https://codehealth.canine.dev/dimensions/D8"},{"id":"D9","name":"Test Distribution","shortDescription":{"text":"Test Distribution"},"helpUri":"https://codehealth.canine.dev/dimensions/D9"},{"id":"D13","name":"Secret Scanning","shortDescription":{"text":"Secret Scanning"},"helpUri":"https://codehealth.canine.dev/dimensions/D13","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D15","name":"Churn \u00D7 Complexity Hotspots","shortDescription":{"text":"Churn \u00D7 Complexity Hotspots"},"helpUri":"https://codehealth.canine.dev/dimensions/D15"},{"id":"D17","name":"Explicit Debt","shortDescription":{"text":"Explicit Debt"},"helpUri":"https://codehealth.canine.dev/dimensions/D17"},{"id":"D19","name":"Documentation Quality","shortDescription":{"text":"Documentation Quality"},"helpUri":"https://codehealth.canine.dev/dimensions/D19"},{"id":"D21","name":"Naming Consistency","shortDescription":{"text":"Naming Consistency"},"helpUri":"https://codehealth.canine.dev/dimensions/D21"},{"id":"D26","name":"Project Cohesion","shortDescription":{"text":"Project Cohesion"},"helpUri":"https://codehealth.canine.dev/dimensions/D26"},{"id":"D28","name":"Secrets (history)","shortDescription":{"text":"Secrets (history)"},"helpUri":"https://codehealth.canine.dev/dimensions/D28","relationships":[{"target":{"id":"CWE-798","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-259","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A07:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-798","CWE-259"],"owasp":"A07:2025"}},{"id":"D29","name":"Static Analysis (SAST)","shortDescription":{"text":"Static Analysis (SAST)"},"helpUri":"https://codehealth.canine.dev/dimensions/D29","relationships":[{"target":{"id":"CWE-79","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-89","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-78","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-94","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-77","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"A05:2025","toolComponent":{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-79","CWE-89","CWE-78","CWE-94","CWE-77"],"owasp":"A05:2025"}},{"id":"D34","name":"Knowledge Freshness","shortDescription":{"text":"Knowledge Freshness"},"helpUri":"https://codehealth.canine.dev/dimensions/D34"},{"id":"D35","name":"Change Coupling","shortDescription":{"text":"Change Coupling"},"helpUri":"https://codehealth.canine.dev/dimensions/D35"},{"id":"D44","name":"Platform End-of-Life","shortDescription":{"text":"Platform End-of-Life"},"helpUri":"https://codehealth.canine.dev/dimensions/D44"},{"id":"AX10","name":"Code composition","shortDescription":{"text":"Code composition"},"helpUri":"https://codehealth.canine.dev/dimensions/AX10"},{"id":"AX3","name":"Project dependency cycles","shortDescription":{"text":"Project dependency cycles"},"helpUri":"https://codehealth.canine.dev/dimensions/AX3"},{"id":"AX4","name":"Dependency direction","shortDescription":{"text":"Dependency direction"},"helpUri":"https://codehealth.canine.dev/dimensions/AX4"},{"id":"AX6","name":"Interface segregation","shortDescription":{"text":"Interface segregation"},"helpUri":"https://codehealth.canine.dev/dimensions/AX6"},{"id":"AXB1","name":"Runtime evidence locked \u2014 no reproducible boot","shortDescription":{"text":"Runtime evidence locked \u2014 no reproducible boot"},"helpUri":"https://codehealth.canine.dev/dimensions/AXB1"},{"id":"ED5","name":"Idempotency","shortDescription":{"text":"Idempotency"},"helpUri":"https://codehealth.canine.dev/dimensions/ED5"},{"id":"GD1","name":"Unfinished \u0026 placeholder code","shortDescription":{"text":"Unfinished \u0026 placeholder code"},"helpUri":"https://codehealth.canine.dev/dimensions/GD1"},{"id":"IC1","name":"Incompleteness \u0026 stubs","shortDescription":{"text":"Incompleteness \u0026 stubs"},"helpUri":"https://codehealth.canine.dev/dimensions/IC1"},{"id":"M1","name":"Documentation (README)","shortDescription":{"text":"Documentation (README)"},"helpUri":"https://codehealth.canine.dev/dimensions/M1"},{"id":"M2","name":"Architecture documentation","shortDescription":{"text":"Architecture documentation"},"helpUri":"https://codehealth.canine.dev/dimensions/M2"},{"id":"M3","name":"Folder \u0026 project structure","shortDescription":{"text":"Folder \u0026 project structure"},"helpUri":"https://codehealth.canine.dev/dimensions/M3"},{"id":"M4","name":"Documentation accuracy","shortDescription":{"text":"Documentation accuracy"},"helpUri":"https://codehealth.canine.dev/dimensions/M4"},{"id":"P1","name":"CI/CD gates","shortDescription":{"text":"CI/CD gates"},"helpUri":"https://codehealth.canine.dev/dimensions/P1"},{"id":"P10","name":"Library API \u0026 versioning","shortDescription":{"text":"Library API \u0026 versioning"},"helpUri":"https://codehealth.canine.dev/dimensions/P10"},{"id":"P3","name":"Security \u0026 performance tooling","shortDescription":{"text":"Security \u0026 performance tooling"},"helpUri":"https://codehealth.canine.dev/dimensions/P3"},{"id":"P6","name":"Release Hygiene","shortDescription":{"text":"Release Hygiene"},"helpUri":"https://codehealth.canine.dev/dimensions/P6"},{"id":"X1","name":"Async correctness","shortDescription":{"text":"Async correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X1"},{"id":"X10","name":"Duplicated predicate","shortDescription":{"text":"Duplicated predicate"},"helpUri":"https://codehealth.canine.dev/dimensions/X10"},{"id":"X12","name":"Unreachable branch","shortDescription":{"text":"Unreachable branch"},"helpUri":"https://codehealth.canine.dev/dimensions/X12"},{"id":"X13","name":"Undrained process stream","shortDescription":{"text":"Undrained process stream"},"helpUri":"https://codehealth.canine.dev/dimensions/X13"},{"id":"X14","name":"Bypassable address classification","shortDescription":{"text":"Bypassable address classification"},"helpUri":"https://codehealth.canine.dev/dimensions/X14"},{"id":"X15","name":"Unvalidated length from an untrusted reader","shortDescription":{"text":"Unvalidated length from an untrusted reader"},"helpUri":"https://codehealth.canine.dev/dimensions/X15"},{"id":"X16","name":"Unfloored truncation loop","shortDescription":{"text":"Unfloored truncation loop"},"helpUri":"https://codehealth.canine.dev/dimensions/X16"},{"id":"X17","name":"Uncapped recursion over a caller-supplied document","shortDescription":{"text":"Uncapped recursion over a caller-supplied document"},"helpUri":"https://codehealth.canine.dev/dimensions/X17"},{"id":"X18","name":"Disposal-pattern correctness","shortDescription":{"text":"Disposal-pattern correctness"},"helpUri":"https://codehealth.canine.dev/dimensions/X18"},{"id":"X19","name":"Unrestored process-global state","shortDescription":{"text":"Unrestored process-global state"},"helpUri":"https://codehealth.canine.dev/dimensions/X19"},{"id":"X20","name":"Mistyped argument guard","shortDescription":{"text":"Mistyped argument guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X20"},{"id":"X21","name":"Side-effecting pattern guard","shortDescription":{"text":"Side-effecting pattern guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X21"},{"id":"X22","name":"Contradicted release guard","shortDescription":{"text":"Contradicted release guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X22"},{"id":"X23","name":"Unguarded diagnostic materialisation","shortDescription":{"text":"Unguarded diagnostic materialisation"},"helpUri":"https://codehealth.canine.dev/dimensions/X23"},{"id":"X24","name":"Document value interpolated into markup unescaped","shortDescription":{"text":"Document value interpolated into markup unescaped"},"helpUri":"https://codehealth.canine.dev/dimensions/X24"},{"id":"X25","name":"Inert configuration knob","shortDescription":{"text":"Inert configuration knob"},"helpUri":"https://codehealth.canine.dev/dimensions/X25"},{"id":"X26","name":"Unsynchronised callback handoff","shortDescription":{"text":"Unsynchronised callback handoff"},"helpUri":"https://codehealth.canine.dev/dimensions/X26"},{"id":"X27","name":"Collection changed while being enumerated","shortDescription":{"text":"Collection changed while being enumerated"},"helpUri":"https://codehealth.canine.dev/dimensions/X27"},{"id":"X28","name":"Index access outside its own emptiness guard","shortDescription":{"text":"Index access outside its own emptiness guard"},"helpUri":"https://codehealth.canine.dev/dimensions/X28"},{"id":"X29","name":"Per-element action decided by a fixed element","shortDescription":{"text":"Per-element action decided by a fixed element"},"helpUri":"https://codehealth.canine.dev/dimensions/X29"},{"id":"X3","name":"Exception handling","shortDescription":{"text":"Exception handling"},"helpUri":"https://codehealth.canine.dev/dimensions/X3"},{"id":"X30","name":"Support guard that admits what it rejects","shortDescription":{"text":"Support guard that admits what it rejects"},"helpUri":"https://codehealth.canine.dev/dimensions/X30"},{"id":"X32","name":"Type resolved by simple name across every loaded assembly","shortDescription":{"text":"Type resolved by simple name across every loaded assembly"},"helpUri":"https://codehealth.canine.dev/dimensions/X32"},{"id":"X4","name":"Structured logging","shortDescription":{"text":"Structured logging"},"helpUri":"https://codehealth.canine.dev/dimensions/X4"},{"id":"X5","name":"Nullable reference types","shortDescription":{"text":"Nullable reference types"},"helpUri":"https://codehealth.canine.dev/dimensions/X5"},{"id":"X6","name":"Hand-rolled structured-format parsing","shortDescription":{"text":"Hand-rolled structured-format parsing"},"helpUri":"https://codehealth.canine.dev/dimensions/X6"},{"id":"X7","name":"Silent fallback defaults","shortDescription":{"text":"Silent fallback defaults"},"helpUri":"https://codehealth.canine.dev/dimensions/X7"},{"id":"X9","name":"Subsumed condition operand","shortDescription":{"text":"Subsumed condition operand"},"helpUri":"https://codehealth.canine.dev/dimensions/X9"}]}},"results":[{"ruleId":"D2","level":"warning","message":{"text":"Enrichable.apply (cognitive 28): Enrichable.apply has cognitive complexity 28 (threshold 15). Drivers by points: if/else 9 (16 pts), match/switch 2 (6 pts), loops 1 (4 pts), boolean chains 2 (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/main/scala/org/archive/webservices/archivespark/model/Enrichable.scala"},"region":{"startLine":159}}}],"partialFingerprints":{"codehealthFindingId/v1":"1db697d939ba75ce565bca51a97f69a0f6ae8cdaad9d1835594f8d4737cc9b29"}},{"ruleId":"D2","level":"warning","message":{"text":"WarcRDD.saveAsWarc (cognitive 25): WarcRDD.saveAsWarc has cognitive complexity 25 (threshold 15). Drivers by points: if/else 16 (23 pts), boolean chains 1, match/switch 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/specific/warc/implicits/WarcRDD.scala"},"region":{"startLine":49}}}],"partialFingerprints":{"codehealthFindingId/v1":"43edf1e86229cd09dc2957b85482f1be22609c95b5aa1d0bd01fcfa0eeb1e79b"}},{"ruleId":"D2","level":"warning","message":{"text":"MultiValueEnrichable.enrich (cognitive 23): MultiValueEnrichable.enrich has cognitive complexity 23 (threshold 15). Drivers by points: if/else 13 (21 pts), boolean chains 2 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala"},"region":{"startLine":47}}}],"partialFingerprints":{"codehealthFindingId/v1":"825585cc751c8249790c4cf5318b226777eea37ff90d65c9272319f466a2482f"}},{"ruleId":"D2","level":"warning","message":{"text":"Enrichable.enrich (cognitive 18): Enrichable.enrich has cognitive complexity 18 (threshold 15). Drivers by points: if/else 7 (10 pts), loops 2 (5 pts), error handling 1 (2 pts), boolean chains 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/Enrichable.scala"},"region":{"startLine":104}}}],"partialFingerprints":{"codehealthFindingId/v1":"0ef34a4853d34438ef12869b28fb74f941927c72747bcb458a1c462a0dabd80e"}},{"ruleId":"D2","level":"warning","message":{"text":"Values.derive (cognitive 17): Values.derive has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (11 pts), boolean chains 3, 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/main/scala/org/archive/webservices/archivespark/functions/Values.scala"},"region":{"startLine":36}}}],"partialFingerprints":{"codehealthFindingId/v1":"846a342f1a3a9345c1e8ff201a62b99a4bea109129793936dd9fadffc87c046f"}},{"ruleId":"D4","level":"warning","message":{"text":"Members sharing a duplicated core (4 members, 50\u002B identical tokens): src/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala:32-45 | src/main/scala/org/archive/webservices/archivespark/model/BoundMultiEnrichFunc.scala:32-45 | src/main/scala/org/archive/webservices/archivespark/model/EnrichFunc.scala:65-78 | src/main/scala/org/archive/webservices/archivespark/model/MultiEnrichFunc.scala:30-43 \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/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala"},"region":{"startLine":32}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5c5ff9d6a486e347a87b810740e6d63d2337d051a25b4c858af71dc765c81bc"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (11 lines \u00D7 2): src/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala:102-112 | src/main/scala/org/archive/webservices/archivespark/model/SingleValueEnrichable.scala:36-46 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala:102\u0060 it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala"},"region":{"startLine":102}}}],"partialFingerprints":{"codehealthFindingId/v1":"55fdead7082d77a615f4a033ca34db5cabe9ee2a60762953196de3992450ed39"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (9 lines \u00D7 3): src/main/scala/org/archive/webservices/archivespark/model/EnrichRoot.scala:55-63 | src/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala:103-111 | src/main/scala/org/archive/webservices/archivespark/model/SingleValueEnrichable.scala:37-45 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from all 3 call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/main/scala/org/archive/webservices/archivespark/model/EnrichRoot.scala:55\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/EnrichRoot.scala"},"region":{"startLine":55}}}],"partialFingerprints":{"codehealthFindingId/v1":"58d53f2d51d542ab7bbfbdb814b8068a4fd8dc776e3f4c3a53cf54ec86d19607"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 4): src/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala:41-45 | src/main/scala/org/archive/webservices/archivespark/model/BoundMultiEnrichFunc.scala:41-45 | src/main/scala/org/archive/webservices/archivespark/model/EnrichFunc.scala:74-78 | src/main/scala/org/archive/webservices/archivespark/model/MultiEnrichFunc.scala:39-43 \u2014 before extracting anything, compare \u0060src/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala\u0060 and \u0060src/main/scala/org/archive/webservices/archivespark/model/BoundMultiEnrichFunc.scala\u0060 as WHOLE FILES: 85% of the shorter file\u0027s lines also appear in the other, so this reads as one file having been copied from the other rather than as a helper waiting to be extracted. The 1 duplicated block(s) this scan matched between them are fragments of that copy, not the extent of it \u2014 treat the file pair as the unit. If that is what happened, the fix is to keep one copy and have the other call it (or delete it), which resolves this row and its siblings together \u2014 extracting one helper per block leaves the fork in place. Read the line range as the matched WINDOW rather than a finished unit: at \u0060src/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala:41\u0060 it runs out through the closing brace of the declaration holding it \u2014 the window is that declaration\u0027s tail, not a fragment that begins part-way through something, so those exact lines cannot be lifted as they stand \u2014 widen the region to the smallest complete statement or declaration that contains it, and extract that."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala"},"region":{"startLine":41}}}],"partialFingerprints":{"codehealthFindingId/v1":"d471ab08be3debc4b765d18b939e9659b73da5f76ba2ef4434f0e413fc004b3d"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (5 lines \u00D7 2): src/main/scala/org/archive/webservices/archivespark/model/EnrichFunc.scala:68-72 | src/main/scala/org/archive/webservices/archivespark/model/MultiEnrichFunc.scala:33-37 \u2014 the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach \u2014 a file they already depend on, or a new one alongside them \u2014 and call it from both call sites, so a change lands once."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"src/main/scala/org/archive/webservices/archivespark/model/EnrichFunc.scala"},"region":{"startLine":68}}}],"partialFingerprints":{"codehealthFindingId/v1":"5c6929dbe0744b2a77de56d6c9e430b7a4f5d316761dd0b9acea6b95d67ece4a"}},{"ruleId":"D9","level":"note","message":{"text":"No tests found: No test suite could be collected \u2014 no discoverable tests to count. If this repository does test, wiring the suite to a framework a runner can collect (ScalaTest, MUnit or specs2) is what makes it countable here; a pipeline step that invokes a runner is not evidence on its own, because a runner over an empty suite passes. Tests written as plain executables or shell/PowerShell harnesses are not collectible this way and are not scored here."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"c9bf64cbb5a4ae13d6bcd01fa3bc8d2879d860c73bc67f176ee3c2cecb8adce3"}},{"ruleId":"D34","level":"note","message":{"text":"Dormant codebase: 24 of 24 significant files have no living knowledge \u2014 the codebase as a whole is dormant, not 24 separate risks. Counted over 24 of the 77 production source files in this repository: the rest are under the ~2,400-byte size floor this dimension measures over. Re-engage owners or document before change."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"4c69f1e54b7dd6fe9029dd02df6ba8f8145b789f2f18dbdaa086c40ded49dba6"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/Enrichable.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5c791e071e25059b392317eaf9f2468c2e1427f7ce575a5b22164e3206a0e1b"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/specific/warc/implicits/WarcRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"a1b2513c9b4407a29bf5a2af271ba1ad6582e70269bbfaa505c3fb5529c6d06d"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/pointers/FieldPointer.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"ba8747ee030b9a323921b9482c194513a920c74a5abe59e7cb07010e88cc3360"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/MultiValueEnrichable.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"31c83c0bc554ff0dd102cc0a1c4362545a33651a09a8d2601ddd1e95a6f479d0"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/EnrichFunc.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"08b739459cd1ecca7157dd7eeb00c2580c084e89d84d72983d0aa7678bde2aa9"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/ArchiveSpark.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"6c343ddd66b5abb03c4e51fa751e983f0152d015194ca7c2c63545da634f3fce"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/BoundMultiEnrichFunc.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f091c25c744d0aa122b9b43585fb989a628865ba27e0965548542cdfd1e9403a"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/BoundEnrichFunc.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3ef15a97746f7092367cb3ba098d122f7a5912df0e4d692b777b96099bb4af7c"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/functions/Entities.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"3173c080fe3bc987738bdf7c3f3ff604d32e97cfde0eb2224b5ec0f14c500047"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/implicits/EnrichableRDD.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"67260177eab1a47ebfc92a8c62a7780619936fcdb5ed10052d8b9dcd5f7cf9f8"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/functions/Values.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cc13227541926fbbf99b7a783ea11aad6977bd420dd37c0a0f521deafccf3c49"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/specific/warc/WaybackRecord.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5662478afaf53fa20a115885a4928115f5c056777f4c146c81de9afa7ad7c6cf"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/util/Bytes.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"5ed9f08d772d67e60d45b8a18ff35fb7f7df6b6a1e3467042da60829b376eb17"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/functions/Html.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"b31b80cfa4f575f8270033e4c2933a0577b25e337e242506fa5f49910c5243bc"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/util/JupyterHelpers.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8f54a0cf75a7fb1bfc3de3502aa45566b7f6937f0d2f54472b3d2c2664de81f"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/functions/StringContent.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c92e6da677b285a5f596a427492fe06a78d2b1416b327e3b5a15d2783524ccea"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/specific/warc/functions/WarcPayload.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c5ad350fc5ec3244960ddc22893219ad9a9a7acca4a30a8d6e5f96a604655c26"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/MultiEnrichFunc.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"cfce0c8534a29648efe67141c5a2dbded1e1a659b0cf367ea704de1453764461"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/specific/warc/WarcRecord.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e1ef75c258768110d16cbeadd2149307a6b027a59d2c390410c2d45019f01539"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/util/Json.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"eaa6d8558ae30bdcffb731015b3f4781396451c207d5c3e26ab6bb09dee89298"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/model/EnrichRoot.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"05e7f024232725249c14c0b4364b0470a530ee53345a5c8b56a003fc44d6ad90"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/specific/warc/functions/HttpPayload.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"26991e3a45ee8cd1cc5b861a9cf3584ac76fa94b9ee8ba1e01057340e0b31681"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/util/HttpHeader.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"f56bc5c1eee099f3b5d983c81e8c1bb70d910ed8941d4f8d9dcb9bb562691224"}},{"ruleId":"D34","level":"note","message":{"text":"Orphaned file: No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have 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/main/scala/org/archive/webservices/archivespark/package.scala"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"2ee89eadf7aefe0ef0b1dc7da2c10497216efc863cf66d8b12fcf4721f2fd66a"}},{"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":"M3","level":"note","message":{"text":"No tests/ separation: Tests aren\u0027t grouped in a dedicated test folder \u2014 the test surface isn\u0027t separable from production code at a glance."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"999e0c784909c76b6346a705ee63961fe363ed1cd6a94e3f80e2ebe7820ccd5d"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/WarcSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/WarcSpec.scala\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/DataSpecs.md"},"region":{"startLine":15}}}],"partialFingerprints":{"codehealthFindingId/v1":"3a5d1e528f3f64561f21c163d5626d8e701a5cd01d1f94c383f3a7e447a9742b"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/specs/CdxHdfsSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/specs/CdxHdfsSpec.scala\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/DataSpecs.md"},"region":{"startLine":19}}}],"partialFingerprints":{"codehealthFindingId/v1":"bb0c59a94d85df9631e91396ff47ee8f00645f74777e0b83bd99a79d832a1597"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/specs/WarcCdxHdfsSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/specs/WarcCdxHdfsSpec.scala\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/DataSpecs.md"},"region":{"startLine":21}}}],"partialFingerprints":{"codehealthFindingId/v1":"dfc82bcb0759b35c294c3bf5b881225f50bcc91fc4847a14e30f8c7362a91a18"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/specs/WarcHdfsCdxPathRddSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/specs/WarcHdfsCdxPathRddSpec.scala\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/DataSpecs.md"},"region":{"startLine":26}}}],"partialFingerprints":{"codehealthFindingId/v1":"292ddefacf5761fe6ae816e0a852a4430272fb7473dbfef1c37bd9295b22bb56"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/specs/WaybackSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/specs/WaybackSpec.scala\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/DataSpecs.md"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"c8d50414a44112cd013ee29f729478f0cbe491db34fefc3d0c9fac0d34add742"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/specs/WaybackCdxHdfsSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/specs/WaybackCdxHdfsSpec.scala\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/DataSpecs.md"},"region":{"startLine":34}}}],"partialFingerprints":{"codehealthFindingId/v1":"e52edbb2307913966d784ccb544c717755ca7fb6de81ef7ba9d7cbd06f416038"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/raw/HdfsFileSpec.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/raw/HdfsFileSpec.scala\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/DataSpecs.md"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"3b70bf76f9abb582e7debf9d97521621de0c5a01d6cff5377632f112f5d0655e"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/DataSpecs.md links to \u0060../src/main/scala/org/archive/archivespark/specific/raw/FileStreamRecord.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/raw/FileStreamRecord.scala\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/DataSpecs.md"},"region":{"startLine":43}}}],"partialFingerprints":{"codehealthFindingId/v1":"cf0abae0ab56c0430b6315bf05afdb5e18373070744a65cbc8e0bc58d6b7cfe2"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/EnrichFuncs.md links to \u0060../src/main/scala/org/archive/archivespark/functions/HtmlText.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/functions/HtmlText.scala\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/EnrichFuncs.md"},"region":{"startLine":21}}}],"partialFingerprints":{"codehealthFindingId/v1":"130c356a9f1df5f2e0da6187b558c4e4f231b834ab341b36739af3c6e89d32e6"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/EnrichFuncs.md links to \u0060../src/main/scala/org/archive/archivespark/functions/HtmlAttribute.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/functions/HtmlAttribute.scala\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/EnrichFuncs.md"},"region":{"startLine":23}}}],"partialFingerprints":{"codehealthFindingId/v1":"58c6191de1d91fc816a46252656931c233ea438b2de3410dbe2fc06b3c093e02"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/EnrichFuncs.md links to \u0060../src/main/scala/org/archive/archivespark/functions/LowerCase.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/functions/LowerCase.scala\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/EnrichFuncs.md"},"region":{"startLine":25}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a301c6cd1038a8849c2983fc272c02828f40fbf59ded09130ead33bf1a8eecd"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/EnrichFuncs.md links to \u0060../src/main/scala/org/archive/archivespark/functions/Entities.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/functions/Entities.scala\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/EnrichFuncs.md"},"region":{"startLine":29}}}],"partialFingerprints":{"codehealthFindingId/v1":"94187ec39dc17e9c548b317abdf0c4b1a93cdb830ef8cf37b8b271140cf7b653"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/EnrichFuncs.md links to \u0060../src/main/scala/org/archive/archivespark/functions/Values.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/functions/Values.scala\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/EnrichFuncs.md"},"region":{"startLine":31}}}],"partialFingerprints":{"codehealthFindingId/v1":"397f5714b797223ffaf03209aec65b36e318c13a813be9f053af864e4ad646d8"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/General_Usage.md links to \u0060Install_Juyter.md\u0060, but \u0060docs/Install_Juyter.md\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/General_Usage.md"},"region":{"startLine":14}}}],"partialFingerprints":{"codehealthFindingId/v1":"97731dad9014d6f4ede52f7a69e75c105b67c34076807a50e27c2f90b6ba3da8"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/Installing_Jupyter.md documents the environment variable \u0060HADOOP_CONF_DIR\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/Installing_Jupyter.md"},"region":{"startLine":60}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc6b74e51ebe4430796ba1f361bc862c0f3aebb65991a0913f67cf374892407b"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/Installing_Jupyter.md documents the environment variable \u0060SPARK_OPTS\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/Installing_Jupyter.md"},"region":{"startLine":63}}}],"partialFingerprints":{"codehealthFindingId/v1":"08a121825121656ed9ad0456f46978abe026f4118de4ee0cae485037ba261b79"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/Operations.md links to \u0060../src/main/scala/org/archive/archivespark/specific/warc/WarcFileMeta.scala\u0060, but \u0060src/main/scala/org/archive/archivespark/specific/warc/WarcFileMeta.scala\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/Operations.md"},"region":{"startLine":45}}}],"partialFingerprints":{"codehealthFindingId/v1":"f141f9d4ac795078b86af5309402cf18d91f3ee68d36faf73d6533d4596c7789"}},{"ruleId":"M4","level":"note","message":{"text":"README/code drift: docs/Using_Jupyter.md links to \u0060Install_Juyter.md\u0060, but \u0060docs/Install_Juyter.md\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/Using_Jupyter.md"},"region":{"startLine":30}}}],"partialFingerprints":{"codehealthFindingId/v1":"c3c01c6388c45187019818d56e1a2000253be27d12f5deefe6bd696be6e539fa"}},{"ruleId":"P1","level":"warning","message":{"text":"No CI pipeline: No CI workflow found (.github/workflows, azure-pipelines.yml, .gitlab-ci.yml, \u2026) \u2014 changes aren\u0027t gated by an automated build/test."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"44f01af96e50474fba2df84d95ddf4f7e1d34c29c307830b9efc9057daa6b670"}},{"ruleId":"P3","level":"note","message":{"text":"No SAST: No static application security testing detected. For this repository\u0027s stack, add scalafix or scapegoat (or \u0060semgrep --config=auto\u0060, which runs on any language) \u2014 this repository has no CI pipeline yet, so run it locally to clear the existing findings, then make it a step of the first workflow you add so a regression fails the build. What was searched, so you can tell an absence from a miss: the 0 CI workflow file(s) in this repository, and the scanner and linter configuration checked in beside them. A scan that runs outside CI, one configured in your forge\u0027s web UI rather than in a committed file, or a tool whose name is none of those this check carries, is not seen \u2014 if that is your case the row is wrong, and saying so is more useful than adding a second scanner."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"6e54424179c892f03ef2fd003130ac4bd43f39bbf3b1ca0a0143e25acb80ec87"}},{"ruleId":"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":"X5","level":"note","message":{"text":"Scala\u0027s null is not held to the type system everywhere: No build over this repository\u0027s 75 Scala product file(s) passes \u0060-Yexplicit-nulls\u0060, enables WartRemover\u0027s \u0060Null\u0060 wart or runs Scalafix\u0027s \u0060DisableSyntax.noNulls\u0060, so every reference type admits null and nothing reports a \u0060null\u0060 written into the code or returned from a Java API \u2014 the first one to reach a method call is a \u0060NullPointerException\u0060. \u0060Option\u0060 by convention is a habit no tool here holds the code to."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"23e7c3c6da50151f07723c64ca4f881fd5903e713d143161a7c0594ad7ba29cc"}}],"taxonomies":[{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d","organization":"MITRE","informationUri":"https://cwe.mitre.org/","isComprehensive":false,"shortDescription":{"text":"The MITRE Common Weakness Enumeration (CWE)."},"taxa":[{"id":"CWE-259","guid":"ae9ad959-fbb6-9d5e-892d-3dca66da0b69","name":"Use of Hard-coded Password","shortDescription":{"text":"Use of Hard-coded Password"},"helpUri":"https://cwe.mitre.org/data/definitions/259.html"},{"id":"CWE-77","guid":"332c8ade-6612-9f56-a06b-d8d90b1a8750","name":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/77.html"},{"id":"CWE-78","guid":"2e31ceaf-c7ae-2e5e-9661-cfb1362789cf","name":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/78.html"},{"id":"CWE-79","guid":"fd45580b-e8c4-fc5e-8c2f-aa8fab0b4dbf","name":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)","shortDescription":{"text":"Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/79.html"},{"id":"CWE-798","guid":"5e8f057d-fee3-995a-a0cb-9fc5b0d174d1","name":"Use of Hard-coded Credentials","shortDescription":{"text":"Use of Hard-coded Credentials"},"helpUri":"https://cwe.mitre.org/data/definitions/798.html"},{"id":"CWE-89","guid":"6d08fdad-37eb-c150-bbf0-d7d946863407","name":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)","shortDescription":{"text":"Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/89.html"},{"id":"CWE-94","guid":"75e7f50c-6c2f-dd52-bf40-bf6c52b861fd","name":"Improper Control of Generation of Code (\u0027Code Injection\u0027)","shortDescription":{"text":"Improper Control of Generation of Code (\u0027Code Injection\u0027)"},"helpUri":"https://cwe.mitre.org/data/definitions/94.html"}]},{"name":"OWASP Top 10","guid":"7d1f0c2e-4b6a-4e39-9a51-0b2e8c3d5f61","version":"2025","organization":"OWASP Foundation","informationUri":"https://top10.owasp.org/2025/","isComprehensive":false,"shortDescription":{"text":"The OWASP Top 10:2025 web application security risks."},"taxa":[{"id":"A05:2025","guid":"87e86033-3231-8458-8e4a-5cb82743553a","name":"Injection","shortDescription":{"text":"Injection"},"helpUri":"https://top10.owasp.org/2025/A05_2025-Injection/"},{"id":"A07:2025","guid":"334ddd78-539d-d35c-83dd-253647eb7eaf","name":"Authentication Failures","shortDescription":{"text":"Authentication Failures"},"helpUri":"https://top10.owasp.org/2025/A07_2025-Authentication_Failures/"}]}],"properties":{"codehealthPublication":{"public":true,"notice":"This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings \u2014 which rule fired, in which file, on which line, and how to fix it \u2014 are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.","securityFindingsRedacted":0,"secretScannerRunsExcluded":0}}}]}