mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-29 13:34:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
8ec8c38de8
docling/tests/data_scanned/ocr_test.pages.json
Nikos Livathinos be6489bde0 fix(tests): Refactor the data_scanned with a very simple document that allows all OCR engines to produce the same result. 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
2024-10-08 07:07:28 +02:00

1 line
12 KiB
JSON
Raw Blame History

[{"page_no": 0, "page_hash": "5b246e5b7c627e174ffcbbe2a41131c2f19e4c2b02314f6bc9ca65c11f9b8d76", "size": {"width": 595.2000122070312, "height": 841.9200439453125}, "cells": [{"id": 0, "text": "Docling ", "bbox": {"l": 72.00000026697958, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}}, {"id": 1, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, self-", "bbox": {"l": 72.00000026697958, "t": 108.73199825838697, "r": 498.1307718470936, "b": 123.38397937123091, "coord_origin": "1"}}, {"id": 2, "text": "contained package. ", "bbox": {"l": 72.00000026697958, "t": 123.371959370318, "r": 175.68600065145242, "b": 138.02399048316556, "coord_origin": "1"}}, {"id": 3, "text": "Features ", "bbox": {"l": 72.00000026697958, "t": 167.29200270612273, "r": 119.69380044383055, "b": 181.94398381896667, "coord_origin": "1"}}, {"id": 4, "text": "Converts any PDF document to JSON or Markdown format, stable and lightning fast. ", "bbox": {"l": 72.00000026697958, "t": 196.5719749299883, "r": 503.4534918668306, "b": 211.22395604283201, "coord_origin": "1"}}, {"id": 5, "text": "Understands detailed page layout, reading order and recovers table structures. ", "bbox": {"l": 72.00000026697958, "t": 225.85200715385838, "r": 478.9497717759695, "b": 240.50397826670132, "coord_origin": "1"}}, {"id": 6, "text": "Extracts metadata from the document, such as title, authors, references and language. ", "bbox": {"l": 72.00000026697958, "t": 255.13197937772395, "r": 519.8010919274483, "b": 269.7840104905715, "coord_origin": "1"}}, {"id": 7, "text": "Includes OCR support for scanned PDFs. ", "bbox": {"l": 72.00000026697958, "t": 284.41200160159326, "r": 285.15097105735396, "b": 299.0639827144371, "coord_origin": "1"}}, {"id": 8, "text": "Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain ", "bbox": {"l": 72.00000026697958, "t": 313.69197382545883, "r": 486.82465180517005, "b": 328.34395493830255, "coord_origin": "1"}}, {"id": 9, "text": "Provides a simple and convenient CLI. ", "bbox": {"l": 72.00000026697958, "t": 342.97197604932654, "r": 270.3559310024932, "b": 357.6239871621727, "coord_origin": "1"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "Section-header", "bbox": {"l": 71.608642578125, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}, "confidence": 0.8694888949394226, "cells": [{"id": 0, "text": "Docling ", "bbox": {"l": 72.00000026697958, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}}]}, {"id": 1, "label": "Text", "bbox": {"l": 71.54174041748047, "t": 108.73199825838697, "r": 498.7333068847656, "b": 138.02399048316556, "coord_origin": "1"}, "confidence": 0.8374634981155396, "cells": [{"id": 1, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, self-", "bbox": {"l": 72.00000026697958, "t": 108.73199825838697, "r": 498.1307718470936, "b": 123.38397937123091, "coord_origin": "1"}}, {"id": 2, "text": "contained package. ", "bbox": {"l": 72.00000026697958, "t": 123.371959370318, "r": 175.68600065145242, "b": 138.02399048316556, "coord_origin": "1"}}]}, {"id": 2, "label": "Text", "bbox": {"l": 71.21173858642578, "t": 167.29200270612273, "r": 519.8010919274483, "b": 357.6239871621727, "coord_origin": "1"}, "confidence": 0.6254582405090332, "cells": [{"id": 3, "text": "Features ", "bbox": {"l": 72.00000026697958, "t": 167.29200270612273, "r": 119.69380044383055, "b": 181.94398381896667, "coord_origin": "1"}}, {"id": 4, "text": "Converts any PDF document to JSON or Markdown format, stable and lightning fast. ", "bbox": {"l": 72.00000026697958, "t": 196.5719749299883, "r": 503.4534918668306, "b": 211.22395604283201, "coord_origin": "1"}}, {"id": 5, "text": "Understands detailed page layout, reading order and recovers table structures. ", "bbox": {"l": 72.00000026697958, "t": 225.85200715385838, "r": 478.9497717759695, "b": 240.50397826670132, "coord_origin": "1"}}, {"id": 6, "text": "Extracts metadata from the document, such as title, authors, references and language. ", "bbox": {"l": 72.00000026697958, "t": 255.13197937772395, "r": 519.8010919274483, "b": 269.7840104905715, "coord_origin": "1"}}, {"id": 7, "text": "Includes OCR support for scanned PDFs. ", "bbox": {"l": 72.00000026697958, "t": 284.41200160159326, "r": 285.15097105735396, "b": 299.0639827144371, "coord_origin": "1"}}, {"id": 8, "text": "Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain ", "bbox": {"l": 72.00000026697958, "t": 313.69197382545883, "r": 486.82465180517005, "b": 328.34395493830255, "coord_origin": "1"}}, {"id": 9, "text": "Provides a simple and convenient CLI. ", "bbox": {"l": 72.00000026697958, "t": 342.97197604932654, "r": 270.3559310024932, "b": 357.6239871621727, "coord_origin": "1"}}]}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "Section-header", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "Section-header", "bbox": {"l": 71.608642578125, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}, "confidence": 0.8694888949394226, "cells": [{"id": 0, "text": "Docling ", "bbox": {"l": 72.00000026697958, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}}]}, "text": "Docling"}, {"label": "Text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "Text", "bbox": {"l": 71.54174041748047, "t": 108.73199825838697, "r": 498.7333068847656, "b": 138.02399048316556, "coord_origin": "1"}, "confidence": 0.8374634981155396, "cells": [{"id": 1, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, self-", "bbox": {"l": 72.00000026697958, "t": 108.73199825838697, "r": 498.1307718470936, "b": 123.38397937123091, "coord_origin": "1"}}, {"id": 2, "text": "contained package. ", "bbox": {"l": 72.00000026697958, "t": 123.371959370318, "r": 175.68600065145242, "b": 138.02399048316556, "coord_origin": "1"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, selfcontained package."}, {"label": "Text", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "Text", "bbox": {"l": 71.21173858642578, "t": 167.29200270612273, "r": 519.8010919274483, "b": 357.6239871621727, "coord_origin": "1"}, "confidence": 0.6254582405090332, "cells": [{"id": 3, "text": "Features ", "bbox": {"l": 72.00000026697958, "t": 167.29200270612273, "r": 119.69380044383055, "b": 181.94398381896667, "coord_origin": "1"}}, {"id": 4, "text": "Converts any PDF document to JSON or Markdown format, stable and lightning fast. ", "bbox": {"l": 72.00000026697958, "t": 196.5719749299883, "r": 503.4534918668306, "b": 211.22395604283201, "coord_origin": "1"}}, {"id": 5, "text": "Understands detailed page layout, reading order and recovers table structures. ", "bbox": {"l": 72.00000026697958, "t": 225.85200715385838, "r": 478.9497717759695, "b": 240.50397826670132, "coord_origin": "1"}}, {"id": 6, "text": "Extracts metadata from the document, such as title, authors, references and language. ", "bbox": {"l": 72.00000026697958, "t": 255.13197937772395, "r": 519.8010919274483, "b": 269.7840104905715, "coord_origin": "1"}}, {"id": 7, "text": "Includes OCR support for scanned PDFs. ", "bbox": {"l": 72.00000026697958, "t": 284.41200160159326, "r": 285.15097105735396, "b": 299.0639827144371, "coord_origin": "1"}}, {"id": 8, "text": "Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain ", "bbox": {"l": 72.00000026697958, "t": 313.69197382545883, "r": 486.82465180517005, "b": 328.34395493830255, "coord_origin": "1"}}, {"id": 9, "text": "Provides a simple and convenient CLI. ", "bbox": {"l": 72.00000026697958, "t": 342.97197604932654, "r": 270.3559310024932, "b": 357.6239871621727, "coord_origin": "1"}}]}, "text": "Features Converts any PDF document to JSON or Markdown format, stable and lightning fast. Understands detailed page layout, reading order and recovers table structures. Extracts metadata from the document, such as title, authors, references and language. Includes OCR support for scanned PDFs. Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain Provides a simple and convenient CLI."}], "body": [{"label": "Section-header", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "Section-header", "bbox": {"l": 71.608642578125, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}, "confidence": 0.8694888949394226, "cells": [{"id": 0, "text": "Docling ", "bbox": {"l": 72.00000026697958, "t": 71.78082545188033, "r": 127.90485047427754, "b": 91.41455694309684, "coord_origin": "1"}}]}, "text": "Docling"}, {"label": "Text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "Text", "bbox": {"l": 71.54174041748047, "t": 108.73199825838697, "r": 498.7333068847656, "b": 138.02399048316556, "coord_origin": "1"}, "confidence": 0.8374634981155396, "cells": [{"id": 1, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, self-", "bbox": {"l": 72.00000026697958, "t": 108.73199825838697, "r": 498.1307718470936, "b": 123.38397937123091, "coord_origin": "1"}}, {"id": 2, "text": "contained package. ", "bbox": {"l": 72.00000026697958, "t": 123.371959370318, "r": 175.68600065145242, "b": 138.02399048316556, "coord_origin": "1"}}]}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy, selfcontained package."}, {"label": "Text", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "Text", "bbox": {"l": 71.21173858642578, "t": 167.29200270612273, "r": 519.8010919274483, "b": 357.6239871621727, "coord_origin": "1"}, "confidence": 0.6254582405090332, "cells": [{"id": 3, "text": "Features ", "bbox": {"l": 72.00000026697958, "t": 167.29200270612273, "r": 119.69380044383055, "b": 181.94398381896667, "coord_origin": "1"}}, {"id": 4, "text": "Converts any PDF document to JSON or Markdown format, stable and lightning fast. ", "bbox": {"l": 72.00000026697958, "t": 196.5719749299883, "r": 503.4534918668306, "b": 211.22395604283201, "coord_origin": "1"}}, {"id": 5, "text": "Understands detailed page layout, reading order and recovers table structures. ", "bbox": {"l": 72.00000026697958, "t": 225.85200715385838, "r": 478.9497717759695, "b": 240.50397826670132, "coord_origin": "1"}}, {"id": 6, "text": "Extracts metadata from the document, such as title, authors, references and language. ", "bbox": {"l": 72.00000026697958, "t": 255.13197937772395, "r": 519.8010919274483, "b": 269.7840104905715, "coord_origin": "1"}}, {"id": 7, "text": "Includes OCR support for scanned PDFs. ", "bbox": {"l": 72.00000026697958, "t": 284.41200160159326, "r": 285.15097105735396, "b": 299.0639827144371, "coord_origin": "1"}}, {"id": 8, "text": "Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain ", "bbox": {"l": 72.00000026697958, "t": 313.69197382545883, "r": 486.82465180517005, "b": 328.34395493830255, "coord_origin": "1"}}, {"id": 9, "text": "Provides a simple and convenient CLI. ", "bbox": {"l": 72.00000026697958, "t": 342.97197604932654, "r": 270.3559310024932, "b": 357.6239871621727, "coord_origin": "1"}}]}, "text": "Features Converts any PDF document to JSON or Markdown format, stable and lightning fast. Understands detailed page layout, reading order and recovers table structures. Extracts metadata from the document, such as title, authors, references and language. Includes OCR support for scanned PDFs. Integrates easily with LLM app / RAG frameworks like LlamaIndex and LangChain Provides a simple and convenient CLI."}], "headers": []}}]
Reference in New Issue View Git Blame Copy Permalink