{ "kind": "synthetic_pdfplumber_edge_case_exploration", "executed_at_utc": "2026-10-14T11:45:45+00:00", "environment": { "python": "3.12.14", "os": "Linux", "architecture": "x86_64", "packages": { "pdfplumber": "0.11.9", "reportlab": "4.4.9", "pypdfium2": "5.13.0" } }, "extractor": "pdfplumber.Page.extract_tables", "fixtures": { "digital-ruled.pdf": { "sha256": "c8f832ec40ef5d7b3b77c222cd782f2f7f258e632664aed623cbe66b28889f40", "bytes": 2194 }, "multipage-ruled.pdf": { "sha256": "07027d40f391b07dd88939b44bc4f8d1d7a0272d2c77b8d85d90b999e982e4f9", "bytes": 3292 }, "borderless-regular.pdf": { "sha256": "7018b0a5f5be6177bb5c4242cbaec90044cf6255635139e7b5ce18a3f3f0f5b7", "bytes": 1985 }, "rotated-90.pdf": { "sha256": "62876cd904ef60170b438073b62fd2b0dc758270938e939f55f329c9e6416a42", "bytes": 2195 }, "image-only.pdf": { "sha256": "b8524f856ae512604d80ce8426966ac0664129cf15cb129ee20084396229c2ec", "bytes": 25125 } }, "results": [ { "case_id": "digital-ruled-default", "fixture": "digital-ruled.pdf", "settings": { "vertical_strategy": "lines", "horizontal_strategy": "lines" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 0, "width": 612, "height": 792, "character_count": 53, "image_count": 0, "tables": [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] } ], "raw_exact_match": true, "normalized_exact_match": true, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ] }, { "case_id": "multipage-ruled-default", "fixture": "multipage-ruled.pdf", "settings": { "vertical_strategy": "lines", "horizontal_strategy": "lines" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ], [ [ [ "Item", "Quantity", "Unit price" ], [ "Delta", "4", "8.50" ], [ "Epsilon", "3", "12.00" ], [ "Zeta", "6", "5.75" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 0, "width": 612, "height": 792, "character_count": 53, "image_count": 0, "tables": [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] }, { "page": 2, "rotation": 0, "width": 612, "height": 792, "character_count": 54, "image_count": 0, "tables": [ [ [ "Item", "Quantity", "Unit price" ], [ "Delta", "4", "8.50" ], [ "Epsilon", "3", "12.00" ], [ "Zeta", "6", "5.75" ] ] ] } ], "raw_exact_match": true, "normalized_exact_match": true, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ], [ [ [ "Item", "Quantity", "Unit price" ], [ "Delta", "4", "8.50" ], [ "Epsilon", "3", "12.00" ], [ "Zeta", "6", "5.75" ] ] ] ], "explicit_stitching": { "algorithm": "Concatenate tables in page order, removing a repeated first row only when it exactly equals the first table's header.", "expected": [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ], [ "Delta", "4", "8.50" ], [ "Epsilon", "3", "12.00" ], [ "Zeta", "6", "5.75" ] ], "actual": [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ], [ "Delta", "4", "8.50" ], [ "Epsilon", "3", "12.00" ], [ "Zeta", "6", "5.75" ] ], "exact_match": true, "limitation": "Assumes these tables belong together; does not infer continuation or handle missing/split rows." } }, { "case_id": "borderless-default-lines", "fixture": "borderless-regular.pdf", "settings": { "vertical_strategy": "lines", "horizontal_strategy": "lines" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 0, "width": 612, "height": 792, "character_count": 53, "image_count": 0, "tables": [] } ], "raw_exact_match": false, "normalized_exact_match": false, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [] ] }, { "case_id": "borderless-text-strategies", "fixture": "borderless-regular.pdf", "settings": { "vertical_strategy": "text", "horizontal_strategy": "text" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 0, "width": 612, "height": 792, "character_count": 53, "image_count": 0, "tables": [ [ [ "Item", "Quantity", "Unit" ], [ "", "", "" ], [ "Alpha", "2", "10.00" ], [ "", "", "" ], [ "Beta", "5", "3.25" ], [ "", "", "" ], [ "Gamma", "1", "99.00" ] ] ] } ], "raw_exact_match": false, "normalized_exact_match": false, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ] }, { "case_id": "rotated-90-default", "fixture": "rotated-90.pdf", "settings": { "vertical_strategy": "lines", "horizontal_strategy": "lines" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 90, "width": 792, "height": 612, "character_count": 53, "image_count": 0, "tables": [ [ [ "Gamma", "Beta", "Alpha", "Item" ], [ "1", "5", "2", "Quantity" ], [ "99.00", "3.25", "10.00", "Unit\nprice" ] ] ] } ], "raw_exact_match": false, "normalized_exact_match": false, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [ [ [ "Gamma", "Beta", "Alpha", "Item" ], [ "1", "5", "2", "Quantity" ], [ "99.00", "3.25", "10.00", "Unit\nprice" ] ] ] ] }, { "case_id": "image-only-without-ocr", "fixture": "image-only.pdf", "settings": { "vertical_strategy": "lines", "horizontal_strategy": "lines" }, "expected_tables_by_page": [ [ [ [ "Item", "Quantity", "Unit price" ], [ "Alpha", "2", "10.00" ], [ "Beta", "5", "3.25" ], [ "Gamma", "1", "99.00" ] ] ] ], "observed_pages": [ { "page": 1, "rotation": 0, "width": 612, "height": 792, "character_count": 0, "image_count": 1, "tables": [] } ], "raw_exact_match": false, "normalized_exact_match": false, "normalization": "Strip cell whitespace and discard wholly blank rows; no reordering or inferred cells.", "normalized_tables_by_page": [ [] ] } ], "limits": [ "Synthetic, regular English text and simple numeric cells; no customer documents.", "One fixture per edge case is not representative evidence or an accuracy estimate.", "Only pdfplumber is executed as an extractor; ReportLab generates and PDFium renders fixtures.", "No OCR pipeline/model was installed or run, and no model licenses were cleared.", "No network calls, uploads, speed or memory measurements.", "No production website, matcher dataset, ranking or public artifact is changed." ] }