docling/tests/data_scanned/groundtruth/docling_v1/ocr_test.json
Peter W. J. Staar c0ba88edf1
feat(cli): add option for html with split-page mode (#1355)
* updated the cli to output html in split-page mode

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* add pin for new docling-core with html split argument

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* relock with fixed html export in docling-core

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update test results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update more tests

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update example

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update lock with docling-core fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update test results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add again chunking extras

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2025-04-14 08:41:50 +02:00

1 line
1.4 KiB
JSON

{"_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": [69.6796630536824, 689.0124221922704, 504.8720051760782, 764.9216921155637], "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}