mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Revise DocTags, fix iterate_items to output content_layer in items (#965)

Browse Source 
* Testing fix for docling-core dt

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* fix: Fix code_formula test unit, update test-cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Fix code-formula model for new docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Update fixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test cases for office formats

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update deps and lockfile

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Clean up imports

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2025-02-17 14:11:55 +01:00
committed by GitHub
parent 77eb77bdc2
commit 6e75f0b5d3
36 changed files with 1034 additions and 1428 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/data_scanned/groundtruth/docling_v1/ocr_test.json
View File

@@ -1 +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": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [69.6796646118164, 689.012451171875, 504.87200927734375, 764.9216918945312], "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", "payload": null, "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}
{"_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": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [72.33333587646484, 691.58837890625, 503.3333435058594, 763.9216918945312], "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", "payload": null, "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}

2
tests/data_scanned/groundtruth/docling_v1/ocr_test.pages.json
View File

@@ -1 +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": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "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": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "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": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}]}, "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": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}, "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": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

5
tests/data_scanned/groundtruth/docling_v2/ocr_test.doctags.txt
View File

@@ -1,3 +1,2 @@
<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>
<doctag><text><loc_61><loc_46><loc_423><loc_89>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</doctag>

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.json
View File

@@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.1.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "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}}}
{"schema_name": "DoclingDocument", "version": "1.1.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 72.33333587646484, "t": 763.9216918945312, "r": 503.3333435058594, "b": 691.58837890625, "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}}}

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json
View File

@@ -1 +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": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "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": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "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": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}]}, "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": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}, "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": 72.33333333333333, "t": 78.0, "r": 503.3333333333333, "b": 150.33333333333334, "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": 96.66666666666667, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 72.33333333333333, "t": 104.66666666666667, "r": 503.3333333333333, "b": 123.33333333333333, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 73.66666666666667, "t": 131.66666666666666, "r": 150.66666666666666, "b": 150.33333333333334, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]