mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix OCR tests

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-11-27 12:31:04 +01:00
parent 9777f41137
commit 732bc6f515
33 changed files with 50 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/data_scanned/groundtruth/docling_v1/ocr_test.easyocr.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<paragraph><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</paragraph>
</document>

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.easyocr.json Normal file
View File

@ -0,0 +1 @@
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "73f23122e9edbdb0a115b448e03c8064a0ea8bdc21d02917ce220cf032454f31", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "8c5c5b766c1bdb92242142ca37260089b02380f9c57729703350f646cdf4771e", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [69.0, 688.58837890625, 506.6666564941406, 767.2550048828125], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.easyocr.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.easyocr.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

3
tests/data_scanned/groundtruth/docling_v1/ocr_test.ocrmac.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<paragraph><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</paragraph>
</document>

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.ocrmac.json Normal file
View File

@ -0,0 +1 @@
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "73f23122e9edbdb0a115b448e03c8064a0ea8bdc21d02917ce220cf032454f31", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "8c5c5b766c1bdb92242142ca37260089b02380f9c57729703350f646cdf4771e", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [70.90211486816406, 689.2166748046875, 504.87200927734375, 765.0995483398438], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.ocrmac.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.ocrmac.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

3
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesseract.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<paragraph><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</paragraph>
</document>

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesseract.json Normal file
View File

@ -0,0 +1 @@
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "73f23122e9edbdb0a115b448e03c8064a0ea8bdc21d02917ce220cf032454f31", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "8c5c5b766c1bdb92242142ca37260089b02380f9c57729703350f646cdf4771e", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [71.35887908935547, 690.8582153320312, 504.0870056152344, 765.0995483398438], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesseract.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesseract.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

3
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesserocr.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<paragraph><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</paragraph>
</document>

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesserocr.json Normal file
View File

@ -0,0 +1 @@
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "73f23122e9edbdb0a115b448e03c8064a0ea8bdc21d02917ce220cf032454f31", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "8c5c5b766c1bdb92242142ca37260089b02380f9c57729703350f646cdf4771e", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [71.35887908935547, 690.8582153320312, 504.0870056152344, 765.0995483398438], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesserocr.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v1/ocr_test.tesserocr.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

3
tests/data_scanned/groundtruth/docling_v2/ocr_test.easyocr.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<text><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</document>

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.easyocr.json Normal file
View File

@ -0,0 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.0, "t": 767.2550048828125, "r": 506.6666564941406, "b": 688.58837890625, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.easyocr.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.easyocr.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.0, "t": 74.66666666666663, "r": 506.6666666666667, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 71.33333333333333, "t": 74.66666666666663, "r": 506.6666666666667, "b": 99.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.0, "t": 100.66666666666663, "r": 506.6666666666667, "b": 126.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 70.66666666666667, "t": 128.66666666666663, "r": 154.0, "b": 153.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

3
tests/data_scanned/groundtruth/docling_v2/ocr_test.ocrmac.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<text><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</document>

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.ocrmac.json Normal file
View File

@ -0,0 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 70.90211486816406, "t": 765.0995483398438, "r": 504.87200927734375, "b": 689.2166748046875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.ocrmac.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.ocrmac.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 70.90211866351085, "t": 76.82212829589844, "r": 504.8720079864275, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896755, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 70.90211866351085, "t": 102.66666671251767, "r": 504.8720079864275, "b": 124.83139551297336, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.10852522817731, "t": 130.0013615789096, "r": 153.04479435252625, "b": 152.70503335218427, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

3
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesseract.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<text><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</document>

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesseract.json Normal file
View File

@ -0,0 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 71.35887908935547, "t": 765.0995483398438, "r": 504.0870056152344, "b": 690.8582153320312, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesseract.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesseract.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

3
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesserocr.doctags.txt Normal file
View File

@ -0,0 +1,3 @@
<document>
<text><location><page_1><loc_12><loc_82><loc_85><loc_91></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</document>

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesserocr.json Normal file
View File

@ -0,0 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 71.35887908935547, "t": 765.0995483398438, "r": 504.0870056152344, "b": 690.8582153320312, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesserocr.md Normal file
View File

@ -0,0 +1 @@
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package

1
tests/data_scanned/groundtruth/docling_v2/ocr_test.tesserocr.pages.json Normal file
View File

@ -0,0 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 71.35887908935547, "t": 76.82212829589844, "r": 504.0870056152344, "b": 151.06346130371094, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 74.0, "t": 78.0, "r": 503.3333333333333, "b": 96.66666666666663, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666663, "r": 503.3333333333333, "b": 123.33333333333337, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666663, "r": 150.66666666666666, "b": 150.33333333333337, "coord_origin": "TOPLEFT"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

2
tests/test_e2e_ocr_conversion.py
View File

@ -78,6 +78,7 @@ def test_e2e_conversions():
input_path=pdf_path,
doc_result=doc_result,
generate=GENERATE_V1,
ocr_engine=ocr_options.kind,
fuzzy=True,
)
@ -85,5 +86,6 @@ def test_e2e_conversions():
input_path=pdf_path,
doc_result=doc_result,
generate=GENERATE_V2,
ocr_engine=ocr_options.kind,
fuzzy=True,
)