{"$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":"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"]}],"properties":{"cwe":["CWE-798","CWE-259"]}},{"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":"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":"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"]}],"properties":{"cwe":["CWE-798","CWE-259"]}},{"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"]}],"properties":{"cwe":["CWE-79","CWE-89","CWE-78","CWE-94","CWE-77"]}},{"id":"D31","name":"IaC \u0026 Container Security","shortDescription":{"text":"IaC \u0026 Container Security"},"helpUri":"https://codehealth.canine.dev/dimensions/D31","relationships":[{"target":{"id":"CWE-1032","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-732","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]},{"target":{"id":"CWE-16","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},"kinds":["relevant"]}],"properties":{"cwe":["CWE-1032","CWE-732","CWE-16"]}},{"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":"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"]}],"properties":{"cwe":["CWE-1059"]}}]}},"results":[{"ruleId":"D1","level":"warning","message":{"text":"_pdf_converter._extract_form_content_from_words (cyclomatic 50): _pdf_converter._extract_form_content_from_words 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":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"2e4ad93162f118f02aa0e2947629dafdd5ecb3bc4cf9ebd0c35005a8c4b6cb5c"}},{"ruleId":"D1","level":"warning","message":{"text":"YouTubeConverter.convert (cyclomatic 34): YouTubeConverter.convert 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":"packages/markitdown/src/markitdown/converters/_youtube_converter.py"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"ef51733bd8f0e7a337042088836037dc394933a2498b1c6df078beaf0596a27e"}},{"ruleId":"D1","level":"warning","message":{"text":"PdfConverterWithOCR.convert (cyclomatic 28): PdfConverterWithOCR.convert 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":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"f4633694a543a689ab18a66ad159f5d718160cab114d97f86231ac5e0365f64e"}},{"ruleId":"D1","level":"warning","message":{"text":"__main__.main (cyclomatic 27): __main__.main 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":"packages/markitdown/src/markitdown/__main__.py"},"region":{"startLine":14}}}],"partialFingerprints":{"codehealthFindingId/v1":"b51d8aa70470dca90e6a05c5761a0cf7146c1b921d930268d426a301adb5eddf"}},{"ruleId":"D1","level":"warning","message":{"text":"_pdf_converter._extract_tables_from_words (cyclomatic 26): _pdf_converter._extract_tables_from_words 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":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"c30e8d28fdaaa2dbbb490fc39a8b6db4eebdf16dc9285ee6a8bca5b0417cc726"}},{"ruleId":"D1","level":"warning","message":{"text":"_pdf_converter_with_ocr._extract_images_from_page (cyclomatic 22): _pdf_converter_with_ocr._extract_images_from_page 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":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"22dd0875df765056aa6b191d64e5d7202ad4e88dc2d376b9f297731762a966ac"}},{"ruleId":"D1","level":"warning","message":{"text":"MarkItDown._get_stream_info_guesses (cyclomatic 22): MarkItDown._get_stream_info_guesses 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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":696}}}],"partialFingerprints":{"codehealthFindingId/v1":"a43b80eaacf03fbc0154300eff1329a1cde25a9e35170a62403d25f270e605d4"}},{"ruleId":"D1","level":"warning","message":{"text":"MarkItDown._convert (cyclomatic 21): MarkItDown._convert 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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":561}}}],"partialFingerprints":{"codehealthFindingId/v1":"dafb38c7d9e20bc3878d7bdf0f0205a3b238f688983a3f77df91a9532795a9e2"}},{"ruleId":"D2","level":"warning","message":{"text":"_pdf_converter._extract_form_content_from_words (cognitive 96): _pdf_converter._extract_form_content_from_words has cognitive complexity 96 (threshold 15). Drivers by points: if/else 58, loops 30, boolean chains 7, ternaries 1 (nesting depth added 43). 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":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":120}}}],"partialFingerprints":{"codehealthFindingId/v1":"c57f1a1da78b5d4b3aec741199a97d5e5e58afce49eb2407be8e91fc3a907c64"}},{"ruleId":"D2","level":"warning","message":{"text":"PdfConverterWithOCR.convert (cognitive 78): PdfConverterWithOCR.convert has cognitive complexity 78 (threshold 15). Drivers by points: if/else 55, loops 14, boolean chains 6, error handling 3 (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":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":158}}}],"partialFingerprints":{"codehealthFindingId/v1":"7f58912ef428cda953d4a15edb49647265187e835d9a64fdd0899f8ab6b38ee6"}},{"ruleId":"D2","level":"warning","message":{"text":"YouTubeConverter.convert (cognitive 60): YouTubeConverter.convert has cognitive complexity 60 (threshold 15). Drivers by points: if/else 42, loops 7, boolean chains 4, error handling 4, ternaries 3 (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":"packages/markitdown/src/markitdown/converters/_youtube_converter.py"},"region":{"startLine":70}}}],"partialFingerprints":{"codehealthFindingId/v1":"bd9a7a44499e7966ed1cf697e187ac6d5d15e137c993da71cf601367928f38c6"}},{"ruleId":"D2","level":"warning","message":{"text":"__main__.main (cognitive 52): __main__.main has cognitive complexity 52 (threshold 15). Drivers by points: if/else 38, error handling 7, loops 6, boolean chains 1 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown/src/markitdown/__main__.py"},"region":{"startLine":14}}}],"partialFingerprints":{"codehealthFindingId/v1":"92463a466179aededb18b7f55d003fadf3e838cc7f0b9ee7f1b6d702660bc089"}},{"ruleId":"D2","level":"warning","message":{"text":"MarkItDown._convert (cognitive 48): MarkItDown._convert has cognitive complexity 48 (threshold 15). Drivers by points: if/else 33, error handling 7, boolean chains 5, loops 3 (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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":561}}}],"partialFingerprints":{"codehealthFindingId/v1":"afe08c01ea774cee1bed93209b7adf63269088b3b15956b6540d58815fedb4a6"}},{"ruleId":"D2","level":"warning","message":{"text":"_pdf_converter._extract_tables_from_words (cognitive 45): _pdf_converter._extract_tables_from_words has cognitive complexity 45 (threshold 15). Drivers by points: if/else 28, loops 14, boolean chains 3 (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":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":398}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f5658a4153a5b02115c28c849a9c0f57818d4379125d74ee29f669d5fb5cd30"}},{"ruleId":"D2","level":"warning","message":{"text":"_pdf_converter_with_ocr._extract_images_from_page (cognitive 37): _pdf_converter_with_ocr._extract_images_from_page has cognitive complexity 37 (threshold 15). Drivers by points: if/else 22, boolean chains 6, error handling 6, loops 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":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":28}}}],"partialFingerprints":{"codehealthFindingId/v1":"2f985e0ff8590afd75e6a687dbaf6f67427e312e241603f6b2a96db513494a56"}},{"ruleId":"D2","level":"warning","message":{"text":"MarkItDown.enable_builtins (cognitive 35): MarkItDown.enable_builtins has cognitive complexity 35 (threshold 15). Drivers by points: if/else 35 (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":141}}}],"partialFingerprints":{"codehealthFindingId/v1":"a5bac9b5762ab71f5303f9eb0fa542cc9a76c0b627d788356e30dd95322334bc"}},{"ruleId":"D2","level":"warning","message":{"text":"MarkItDown._get_stream_info_guesses (cognitive 33): MarkItDown._get_stream_info_guesses has cognitive complexity 33 (threshold 15). Drivers by points: if/else 24, boolean chains 9 (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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":696}}}],"partialFingerprints":{"codehealthFindingId/v1":"1a35d4b2b00006eef3d8a2b03e260d730d3a68a605ca444f3b9b67c197d2dcc3"}},{"ruleId":"D2","level":"warning","message":{"text":"XlsxConverterWithOCR._extract_and_ocr_sheet_images (cognitive 27): XlsxConverterWithOCR._extract_and_ocr_sheet_images has cognitive complexity 27 (threshold 15). Drivers by points: if/else 20, error handling 4, loops 2, 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":"packages/markitdown-ocr/src/markitdown_ocr/_xlsx_converter_with_ocr.py"},"region":{"startLine":149}}}],"partialFingerprints":{"codehealthFindingId/v1":"f5ecbef8530f770886fa6e7c08e64782046e3830bd921d9cf89f3a214266a7f8"}},{"ruleId":"D2","level":"warning","message":{"text":"BingSerpConverter.convert (cognitive 25): BingSerpConverter.convert has cognitive complexity 25 (threshold 15). Drivers by points: if/else 9, error handling 8, loops 5, ternaries 2, 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":"packages/markitdown/src/markitdown/converters/_bing_serp_converter.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"de26aabc5296730795151eef948c2973e078734d3d2294ce623b412b582fbf66"}},{"ruleId":"D2","level":"warning","message":{"text":"MarkItDown.convert_response (cognitive 23): MarkItDown.convert_response has cognitive complexity 23 (threshold 15). Drivers by points: if/else 20, loops 3 (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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":489}}}],"partialFingerprints":{"codehealthFindingId/v1":"69bb731bec7bc0fb059dbb5552e53ae35864585a8b3dc1c098a3d29b9930b819"}},{"ruleId":"D2","level":"warning","message":{"text":"PdfConverterWithOCR._ocr_full_pages (cognitive 18): PdfConverterWithOCR._ocr_full_pages has cognitive complexity 18 (threshold 15). Drivers by points: error handling 8, if/else 7, loops 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":340}}}],"partialFingerprints":{"codehealthFindingId/v1":"2a4f6cf64a363be80d388e4b59a659dbbbf13dabe6faccfa2621cae107cca8a3"}},{"ruleId":"D2","level":"warning","message":{"text":"MarkItDown.convert_stream (cognitive 16): MarkItDown.convert_stream has cognitive complexity 16 (threshold 15). Drivers by points: if/else 12, boolean chains 2, loops 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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":362}}}],"partialFingerprints":{"codehealthFindingId/v1":"8f7ec799d967aa67db6b6612979d60eebe77e8a3793058ee598e2a9531d52bfa"}},{"ruleId":"D2","level":"warning","message":{"text":"AudioConverter.convert (cognitive 16): AudioConverter.convert has cognitive complexity 16 (threshold 15). Drivers by points: if/else 9, boolean chains 3, error handling 2, loops 2 (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":"packages/markitdown/src/markitdown/converters/_audio_converter.py"},"region":{"startLine":46}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc5d2c74c11f26ccebaaff7c6441e92eb40b2a6b0b8d2df42d02e7d4c8191002"}},{"ruleId":"D2","level":"warning","message":{"text":"IpynbConverter._convert (cognitive 16): IpynbConverter._convert has cognitive complexity 16 (threshold 15). Drivers by points: if/else 10, loops 5, error handling 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":"packages/markitdown/src/markitdown/converters/_ipynb_converter.py"},"region":{"startLine":57}}}],"partialFingerprints":{"codehealthFindingId/v1":"2369b324b67a9319db6a2f4417caa9518eb1327a3e3233779cc958ddeb03db53"}},{"ruleId":"D2","level":"warning","message":{"text":"PdfConverter.convert (cognitive 16): PdfConverter.convert has cognitive complexity 16 (threshold 15). Drivers by points: if/else 13, boolean chains 1, error handling 1, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":520}}}],"partialFingerprints":{"codehealthFindingId/v1":"d4893782f992024e8c837c18df629309ee1e7e45e8d4405921fa9745abfb2f71"}},{"ruleId":"D3","level":"warning","message":{"text":"FileTooLong: markitdown/_markitdown.py: FileTooLong \u2014 545 significant lines (blank, comment-only and punctuation-only lines excluded). 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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"bfc22f13662b1523b4d6875045d81ae6ebaaade9a0a9f96394fb2eb964d0059b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (29 lines \u00D7 2): packages/markitdown/src/markitdown/converters/_image_converter.py:106-134 | packages/markitdown/src/markitdown/converters/_llm_caption.py:18-46 \u2014 the copies sit in sibling files of one directory: extract the block into a single shared function in that directory and call it from each site, 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":"packages/markitdown/src/markitdown/converters/_image_converter.py"},"region":{"startLine":106}}}],"partialFingerprints":{"codehealthFindingId/v1":"e37e7f09da2b96139a15ab63782c60aab40b245d2bd4acc1f852b07cc7272f44"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:77-93 | packages/markitdown/src/markitdown/converters/_pptx_converter.py:82-98 \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. 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":"packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py"},"region":{"startLine":77}}}],"partialFingerprints":{"codehealthFindingId/v1":"c7500238e866751e441229f438395dac48e5531d165dc655d7c07ea9f53247ac"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (17 lines \u00D7 2): packages/markitdown/src/markitdown/converters/_bing_serp_converter.py:35-51 | packages/markitdown/src/markitdown/converters/_wikipedia_converter.py:29-45 \u2014 the copies sit in sibling files of one directory: extract the block into a single shared function in that directory and call it from each site, 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":"packages/markitdown/src/markitdown/converters/_bing_serp_converter.py"},"region":{"startLine":35}}}],"partialFingerprints":{"codehealthFindingId/v1":"59560c3fc7e66b9b911b852764ba66efb299395cec7f87137c52ee807483d459"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (15 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:172-186 | packages/markitdown/src/markitdown/converters/_pptx_converter.py:196-210 \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 \u0060packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:172\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":"packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py"},"region":{"startLine":172}}}],"partialFingerprints":{"codehealthFindingId/v1":"bc6b234fd29b1ce94a44633d19b8b99d906d8111f5aad43804e6bcbd0058bf31"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_docx_converter_with_ocr.py:69-82 | packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:60-73 \u2014 the copies sit in sibling files of one directory: extract the block into a single shared function in that directory and call it from each site, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at \u0060packages/markitdown-ocr/src/markitdown_ocr/_docx_converter_with_ocr.py:69\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":"packages/markitdown-ocr/src/markitdown_ocr/_docx_converter_with_ocr.py"},"region":{"startLine":69}}}],"partialFingerprints":{"codehealthFindingId/v1":"1468e7804d7a7ca82538e1c32ca5450a9e8827c87b47303c6a21f5ae9296506c"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (14 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py:367-381 | packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py:401-414 \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 \u0060packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py:367\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":"packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py"},"region":{"startLine":367}}}],"partialFingerprints":{"codehealthFindingId/v1":"6efe070297cd6fa0ff5908eed5e16b8d01d16994fe23c441b8a01040f3859de8"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (13 lines \u00D7 2): packages/markitdown/src/markitdown/converters/_rss_converter.py:117-129 | packages/markitdown/src/markitdown/converters/_rss_converter.py:154-166 \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 \u0060packages/markitdown/src/markitdown/converters/_rss_converter.py:117\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":"packages/markitdown/src/markitdown/converters/_rss_converter.py"},"region":{"startLine":117}}}],"partialFingerprints":{"codehealthFindingId/v1":"6affccf125a24a2de8c3e6df963c3654f5010f88a9749757a4bee9e368c0bc16"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 3): packages/markitdown-ocr/src/markitdown_ocr/_xlsx_converter_with_ocr.py:94-106 | packages/markitdown/src/markitdown/converters/_xlsx_converter.py:84-95 | packages/markitdown/src/markitdown/converters/_xlsx_converter.py:146-157 \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. 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":"packages/markitdown-ocr/src/markitdown_ocr/_xlsx_converter_with_ocr.py"},"region":{"startLine":94}}}],"partialFingerprints":{"codehealthFindingId/v1":"fd192f6dec94f0b391e9c28eb90b831ce0f56eee7a2f5edc6a5bdca24ff227ff"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:206-217 | packages/markitdown/src/markitdown/converters/_pptx_converter.py:286-297 \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 \u0060packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:206\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":"packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py"},"region":{"startLine":206}}}],"partialFingerprints":{"codehealthFindingId/v1":"65a93b8244a62e54e10ce01e32210ea1b285609cbbeaa03e22ef288a5ae78e43"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (12 lines \u00D7 2): packages/markitdown/src/markitdown/_markitdown.py:210-221 | packages/markitdown/src/markitdown/_markitdown.py:232-243 \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":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":210}}}],"partialFingerprints":{"codehealthFindingId/v1":"99d1dc553dfd86d2ee66f9177b38688ae2f67d4d5c90ae8caad37b30e017a71b"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (10 lines \u00D7 2): packages/markitdown/src/markitdown/converters/_pdf_converter.py:137-146 | packages/markitdown/src/markitdown/converters/_pdf_converter.py:411-420 \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":"packages/markitdown/src/markitdown/converters/_pdf_converter.py"},"region":{"startLine":137}}}],"partialFingerprints":{"codehealthFindingId/v1":"8080fcc2e0f1e67ccf254f19d062713c09221fbced9eb5d83d1341360d704614"}},{"ruleId":"D4","level":"warning","message":{"text":"Duplicated block (7 lines \u00D7 2): packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py:237-243 | packages/markitdown/src/markitdown/converters/_pptx_converter.py:323-329 \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":"packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py"},"region":{"startLine":237}}}],"partialFingerprints":{"codehealthFindingId/v1":"48c59e4f2149234b193b2e0a7e49bffeb46741a1f609d2006b2b5bd3020f305f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: packages/markitdown/src/markitdown/__main__.py: packages/markitdown/src/markitdown/__main__.py changed 2 times in last 90 days, max complexity 27. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, behind tests written first."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown/src/markitdown/__main__.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"e25057c9a3628fff980618c73f4669a0d66c7b010e5d6ccdf097d7b8aca0716f"}},{"ruleId":"D15","level":"warning","message":{"text":"Hotspot: packages/markitdown/src/markitdown/_markitdown.py: packages/markitdown/src/markitdown/_markitdown.py changed 2 times in last 90 days, max complexity 22. Frequent change and high complexity in one file compound: schedule the next change to it to include carving out the part being edited, behind tests written first."},"locations":[{"physicalLocation":{"artifactLocation":{"uri":"packages/markitdown/src/markitdown/_markitdown.py"},"region":{"startLine":1}}}],"partialFingerprints":{"codehealthFindingId/v1":"c1e09b90447b387ab6a7baaa895b90819071c4405c41e61b03198cc0b459c771"}},{"ruleId":"D16","level":"note","message":{"text":"Off-boarding risk: anonymized user #1: If anonymized user #1 becomes unavailable, 1 significant file(s) lose their only recent owner: packages/markitdown/src/markitdown/converters/_cu_converter.py. Pair on, review, or document these before any departure."},"locations":[],"partialFingerprints":{"codehealthFindingId/v1":"c91b78eaa60f8e06a6608b2060a0594ace97720f98bd10e3530e3de6b182da82"}},{"ruleId":"D29","level":"error","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"d5b8f11381d61a58459ffc7c595fd52d09c03c711894a63a9578043d2338412b"},"taxa":[{"id":"CWE-829","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"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":"39a4ec1b5382c29c3a5b9bb75e7c4bbcebe5c8147e000967834ac9375f5b6978"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"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":"affe7d3c1087ddde52eb753544e0ac48ab309e33a0f55facdfaf08cfea75802c"},"taxa":[{"id":"CWE-1357","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}},{"id":"CWE-353","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"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":"c23a0cffd173fd0c9d7ce190b592d28f72cd83153b03dd69d8e6bc54eab5d0dc"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"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":"ad78f475607e7ff839278ee1cd2f5cde164a30c87da69c21149e8894541a47b1"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"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":"1e8a0ef3aa7b5892e151759edcd77c6b8cb70cc06a34ee18ee516f4fb186b895"},"taxa":[{"id":"CWE-611","toolComponent":{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d"}}]},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"88debff4e93689b458538e4a8434b783c535db251ec7b9177d420a5961a162be"}},{"ruleId":"D31","level":"warning","message":{"text":"A security finding was recorded here. Its details are withheld on the public artifact \u2014 ask the repository owner for the full report."},"partialFingerprints":{"codehealthFindingId/v1":"cabfbbea2b7d29ab5c2675d5dcfb862ccf804032887d8cc3fbab2e811201b31b"}},{"ruleId":"D34","level":"note","message":{"text":"Further orphaned files (smaller): 7 of 31 analysed file(s) have no living knowledge left \u2014 their last meaningful change has decayed away, so if one breaks, no one currently understands it (counted over production source files of roughly 100 lines or more, excluding tests, vendored, generated and example/demo trees, largest first). None is large enough to earn a read-through of its own, so this row stands in for the per-file rows rather than raising one each \u2014 largest first: packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py, packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py, packages/markitdown-ocr/src/markitdown_ocr/_xlsx_converter_with_ocr.py (and 4 more). 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"}}],"taxonomies":[{"name":"CWE","guid":"c3a2b1d0-7f3e-4b2a-9c1d-5e6f7a8b9c0d","organization":"MITRE","informationUri":"https://cwe.mitre.org/","isComprehensive":false,"shortDescription":{"text":"The MITRE Common Weakness Enumeration (CWE)."},"taxa":[{"id":"CWE-1032","guid":"5f21e517-68aa-a650-9a25-5771ef024637","name":"OWASP Top Ten \u2014 Security Misconfiguration category","shortDescription":{"text":"OWASP Top Ten \u2014 Security Misconfiguration category"},"helpUri":"https://cwe.mitre.org/data/definitions/1032.html"},{"id":"CWE-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-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-16","guid":"659db3ea-affc-8453-8add-c1218fbfcb92","name":"Configuration","shortDescription":{"text":"Configuration"},"helpUri":"https://cwe.mitre.org/data/definitions/16.html"},{"id":"CWE-259","guid":"ae9ad959-fbb6-9d5e-892d-3dca66da0b69","name":"Use of Hard-coded Password","shortDescription":{"text":"Use of Hard-coded Password"},"helpUri":"https://cwe.mitre.org/data/definitions/259.html"},{"id":"CWE-353","guid":"09d7e902-d4ee-f05d-ae6c-0a1554d0c18f","name":"CWE-353","shortDescription":{"text":"CWE-353"},"helpUri":"https://cwe.mitre.org/data/definitions/353.html"},{"id":"CWE-611","guid":"1afbae66-ea29-2d59-aaa2-134e3ae2e85a","name":"CWE-611","shortDescription":{"text":"CWE-611"},"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":"Command Injection","shortDescription":{"text":"Command Injection"},"helpUri":"https://cwe.mitre.org/data/definitions/77.html"},{"id":"CWE-78","guid":"2e31ceaf-c7ae-2e5e-9661-cfb1362789cf","name":"OS Command Injection","shortDescription":{"text":"OS Command Injection"},"helpUri":"https://cwe.mitre.org/data/definitions/78.html"},{"id":"CWE-79","guid":"fd45580b-e8c4-fc5e-8c2f-aa8fab0b4dbf","name":"Cross-site Scripting (XSS)","shortDescription":{"text":"Cross-site Scripting (XSS)"},"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":"CWE-829","shortDescription":{"text":"CWE-829"},"helpUri":"https://cwe.mitre.org/data/definitions/829.html"},{"id":"CWE-89","guid":"6d08fdad-37eb-c150-bbf0-d7d946863407","name":"SQL Injection","shortDescription":{"text":"SQL Injection"},"helpUri":"https://cwe.mitre.org/data/definitions/89.html"},{"id":"CWE-94","guid":"75e7f50c-6c2f-dd52-bf40-bf6c52b861fd","name":"Code Injection","shortDescription":{"text":"Code Injection"},"helpUri":"https://cwe.mitre.org/data/definitions/94.html"}]}],"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":8,"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."]}]}