mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 03:55:00 +00:00
cf78d5b7b9
* feat: Pass predicted page-headers and page-footers through to DoclingDocument furniture Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * chore: Update all test GT Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update all test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update all test cases again Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update lock Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update lock to final docling-core Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
1 line
1.2 KiB
JSON
1 line
1.2 KiB
JSON
{"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}}} |