mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(ocr): update e2e OCR test data

Browse Source 
Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
This commit is contained in:
Clément Doumouro 2025-04-08 17:48:55 +02:00
parent e2becbcaaf
commit c1ac22947f
22 changed files with 26 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_180.doctags.txt
View File

@ -1,5 +1,4 @@
<document>
<paragraph><location><page_1><loc_75><loc_16><loc_88><loc_18></location>package</paragraph>
<paragraph><location><page_1><loc_15><loc_12><loc_88><loc_15></location>JSON and Markdown in an easy self contained</paragraph>
<paragraph><location><page_1><loc_15><loc_9><loc_88><loc_11></location>Docling bundles PDF document conversion to</paragraph>
<paragraph><location><page_1><loc_74><loc_16><loc_88><loc_18></location>package</paragraph>
<paragraph><location><page_1><loc_15><loc_9><loc_88><loc_15></location>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained</paragraph>
</document>

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_180.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_rotated_180.pdf", "filename-prov": null, "document-hash": "a9cbfe0f2a71171face9ee31d2347ca4195649670ad75680520d67d4a863f982", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "baca27070f05dd84cf0903ded39bcf0fc1fa6ef0ac390e79cf8ba90c8c33ba49", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [444.6666666666667, 131.58835856119788, 521.6666666666666, 150.25502522786462], "page": 1, "span": [0, 7], "__ref_s3_data": null}], "text": "package", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [92.0, 104.58835856119788, 523.0, 123.25502522786462], "page": 1, "span": [0, 43], "__ref_s3_data": null}], "text": "JSON and Markdown in an easy self contained", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [92.0, 77.92169189453125, 521.3333333333334, 96.58835856119788], "page": 1, "span": [0, 42], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to", "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_rotated_180.pdf", "filename-prov": null, "document-hash": "a9cbfe0f2a71171face9ee31d2347ca4195649670ad75680520d67d4a863f982", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "baca27070f05dd84cf0903ded39bcf0fc1fa6ef0ac390e79cf8ba90c8c33ba49", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [441.304584329099, 132.09610360960653, 521.9863114205704, 151.67751306395223], "page": 1, "span": [0, 7], "__ref_s3_data": null}], "text": "package", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [89.12133215549848, 77.02339849621205, 523.3501733013318, 124.86176457554109], "page": 1, "span": [0, 86], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "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}

4
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_180.md
View File

@ -1,5 +1,3 @@
package
JSON and Markdown in an easy self contained
Docling bundles PDF document conversion to
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_180.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_270.doctags.txt
View File

@ -1,3 +1,3 @@
<document>
<paragraph><location><page_1><loc_82><loc_75><loc_84><loc_88></location>package</paragraph>
<paragraph><location><page_1><loc_82><loc_74><loc_84><loc_88></location>package</paragraph>
</document>

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_270.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_rotated_270.pdf", "filename-prov": null, "document-hash": "52f54e7183bdb73aa3713c7b169baca93e276963a138418c26e7d6a1ea128f14", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "59bc9ddba89e7b008185dd16d384493beb034686e5670546786390c5d237a304", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [691.6666666666666, 444.53450520833337, 710.3333333333334, 521.5345052083334], "page": 1, "span": [0, 7], "__ref_s3_data": null}], "text": "package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 595.201171875, "page": 1, "width": 841.9216918945312}], "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_rotated_270.pdf", "filename-prov": null, "document-hash": "52f54e7183bdb73aa3713c7b169baca93e276963a138418c26e7d6a1ea128f14", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "59bc9ddba89e7b008185dd16d384493beb034686e5670546786390c5d237a304", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [691.4680194659409, 442.3948768148814, 709.8255850278712, 523.0765988200898], "page": 1, "span": [0, 7], "__ref_s3_data": null}], "text": "package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 595.201171875, "page": 1, "width": 841.9216918945312}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_270.pages.json
View File

File diff suppressed because one or more lines are too long

3
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_90.doctags.txt
View File

@ -1,4 +1,3 @@
<document>
<paragraph><location><page_1><loc_9><loc_12><loc_11><loc_85></location>Docling bundles PDF document conversion to</paragraph>
<paragraph><location><page_1><loc_12><loc_12><loc_15><loc_85></location><location><page_1><loc_12><loc_12><loc_15><loc_85></location>JSON and Markdown in an easy self contained package</paragraph>
<paragraph><location><page_1><loc_16><loc_12><loc_18><loc_26></location>package</paragraph>
</document>

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_90.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_rotated_90.pdf", "filename-prov": null, "document-hash": "4a282813d93824eaa9bc2a0b2a0d6d626ecc8f5f380bd1320e2dd3e8e53c2ba6", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "f8a4dc72d8b159f69d0bc968b97f3fb9e0ac59dcb3113492432755835935d9b3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [78.0, 73.86783854166663, 96.66666666666667, 503.201171875], "page": 1, "span": [0, 42], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [104.66666666666667, 72.201171875, 123.33333333333333, 503.201171875], "page": 1, "span": [0, 51], "__ref_s3_data": null}, {"bbox": [104.66666666666667, 72.201171875, 123.33333333333333, 503.201171875], "page": 1, "span": [0, 51], "__ref_s3_data": null}], "text": "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": 595.201171875, "page": 1, "width": 841.9216918945312}], "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_rotated_90.pdf", "filename-prov": null, "document-hash": "4a282813d93824eaa9bc2a0b2a0d6d626ecc8f5f380bd1320e2dd3e8e53c2ba6", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "f8a4dc72d8b159f69d0bc968b97f3fb9e0ac59dcb3113492432755835935d9b3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [131.21306574279092, 74.12495603322407, 152.19606490864376, 154.19400205373182], "page": 1, "span": [0, 7], "__ref_s3_data": null}], "text": "package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 595.201171875, "page": 1, "width": 841.9216918945312}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}

4
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_90.md
View File

@ -1,3 +1 @@
Docling bundles PDF document conversion to
JSON and Markdown in an easy self contained package
package

2
tests/data_scanned/groundtruth/docling_v1/ocr_test_rotated_90.pages.json
View File

File diff suppressed because one or more lines are too long

5
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.doctags.txt
View File

@ -1,4 +1,3 @@
<doctag><text><loc_374><loc_411><loc_438><loc_422>package</text>
<text><loc_77><loc_427><loc_439><loc_438>JSON and Markdown in an easy self contained</text>
<text><loc_77><loc_443><loc_438><loc_454>Docling bundles PDF document conversion to</text>
<doctag><text><loc_371><loc_410><loc_438><loc_422>package</text>
<text><loc_75><loc_426><loc_440><loc_454>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained</text>
</doctag>

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.json
View File

@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_180", "origin": {"mimetype": "application/pdf", "binary_hash": 2530576989861832966, "filename": "ocr_test_rotated_180.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"}, {"cref": "#/texts/1"}, {"cref": "#/texts/2"}], "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": 444.6666666666667, "t": 150.25502522786462, "r": 521.6666666666666, "b": 131.58835856119788, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 7]}], "orig": "package", "text": "package", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 92.0, "t": 123.25502522786462, "r": 523.0, "b": 104.58835856119788, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 43]}], "orig": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/2", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 92.0, "t": 96.58835856119788, "r": 521.3333333333334, "b": 77.92169189453125, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 42]}], "orig": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_180", "origin": {"mimetype": "application/pdf", "binary_hash": 2530576989861832966, "filename": "ocr_test_rotated_180.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"}, {"cref": "#/texts/1"}], "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": 441.304584329099, "t": 151.67751306395223, "r": 521.9863114205704, "b": 132.09610360960653, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 7]}], "orig": "package", "text": "package", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 89.12133215549848, "t": 124.86176457554109, "r": 523.3501733013318, "b": 77.02339849621205, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 86]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

4
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.md
View File

@ -1,5 +1,3 @@
package
JSON and Markdown in an easy self contained
Docling bundles PDF document conversion to
Docling bundles PDF document conversion to JSON and Markdown in an easy self contained

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.pages.json
View File

File diff suppressed because one or more lines are too long

4
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.doctags.txt
View File

@ -1,3 +1,3 @@
<doctag><page_header><loc_427><loc_61><loc_454><loc_423>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained</page_header>
<text><loc_411><loc_62><loc_422><loc_127>package</text>
<doctag><page_header><loc_426><loc_60><loc_454><loc_424>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained</page_header>
<text><loc_411><loc_61><loc_422><loc_128>package</text>
</doctag>

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.json
View File

@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_270", "origin": {"mimetype": "application/pdf", "binary_hash": 10890858393843077593, "filename": "ocr_test_rotated_270.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"}, {"cref": "#/texts/1"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "furniture", "label": "page_header", "prov": [{"page_no": 1, "bbox": {"l": 718.6666666666666, "t": 522.8678385416666, "r": 764.0, "b": 91.86783854166669, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 86]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 691.6666666666666, "t": 521.5345052083334, "r": 710.3333333333334, "b": 444.53450520833337, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 7]}], "orig": "package", "text": "package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 841.9216918945312, "height": 595.201171875}, "image": null, "page_no": 1}}}
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_270", "origin": {"mimetype": "application/pdf", "binary_hash": 10890858393843077593, "filename": "ocr_test_rotated_270.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"}, {"cref": "#/texts/1"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "furniture", "label": "page_header", "prov": [{"page_no": 1, "bbox": {"l": 717.1685859527342, "t": 524.2990548540179, "r": 764.8982839673505, "b": 90.32916553110118, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 86]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 691.4680194659409, "t": 523.0765988200898, "r": 709.8255850278712, "b": 442.3948768148814, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 7]}], "orig": "package", "text": "package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 841.9216918945312, "height": 595.201171875}, "image": null, "page_no": 1}}}

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.pages.json
View File

File diff suppressed because one or more lines are too long

4
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.doctags.txt
View File

@ -1,3 +1,3 @@
<doctag><text><loc_46><loc_77><loc_57><loc_438>Docling bundles PDF document conversion to</text>
<text><loc_62><loc_77><loc_73><loc_439><loc_62><loc_77><loc_73><loc_439>JSON and Markdown in an easy self contained package</text>
<doctag><page_header><loc_46><loc_75><loc_74><loc_440>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained</page_header>
<text><loc_78><loc_370><loc_90><loc_438>package</text>
</doctag>

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.json
View File

@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_90", "origin": {"mimetype": "application/pdf", "binary_hash": 6989291015361162334, "filename": "ocr_test_rotated_90.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"}, {"cref": "#/texts/1"}], "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": 78.0, "t": 503.201171875, "r": 96.66666666666667, "b": 73.86783854166663, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 42]}], "orig": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 104.66666666666667, "t": 503.201171875, "r": 123.33333333333333, "b": 72.201171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 43]}, {"page_no": 1, "bbox": {"l": 104.66666666666667, "t": 503.201171875, "r": 123.33333333333333, "b": 72.201171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [44, 51]}], "orig": "JSON and Markdown in an easy self contained package", "text": "JSON and Markdown in an easy self contained package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 841.9216918945312, "height": 595.201171875}, "image": null, "page_no": 1}}}
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test_rotated_90", "origin": {"mimetype": "application/pdf", "binary_hash": 6989291015361162334, "filename": "ocr_test_rotated_90.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"}, {"cref": "#/texts/1"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "furniture", "label": "page_header", "prov": [{"page_no": 1, "bbox": {"l": 77.10171546422428, "t": 506.07735421856773, "r": 124.91101654503161, "b": 71.88562244773436, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 86]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained", "formatting": null, "hyperlink": null}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 131.21306574279092, "t": 154.19400205373182, "r": 152.19606490864376, "b": 74.12495603322407, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 7]}], "orig": "package", "text": "package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 841.9216918945312, "height": 595.201171875}, "image": null, "page_no": 1}}}

4
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.md
View File

@ -1,3 +1 @@
Docling bundles PDF document conversion to
JSON and Markdown in an easy self contained package
package

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.pages.json
View File

File diff suppressed because one or more lines are too long