chore: propagate docling-core fix (#1389)

* chore: propagate docling-core fix

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* update lock to latest docling-core release

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

---------

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

poetry.lock

@@ -948,13 +948,13 @@ files = [
 
 [[package]]
 name = "docling-core"
-version = "2.26.3"
+version = "2.26.4"
 description = "A python library to define and validate data types in Docling."
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_core-2.26.3-py3-none-any.whl", hash = "sha256:a14956dcde37c5970fd59b8b7b123db2df9b060b9c92b08a5a253350fddf7a0b"},
-    {file = "docling_core-2.26.3.tar.gz", hash = "sha256:7a1dfc3f4c991d732a78f7105f59717596dc894c54a9add3f5ab8ce69e88706f"},
+    {file = "docling_core-2.26.4-py3-none-any.whl", hash = "sha256:42cc246d4889e6d52f004a2ca85b7f8132735fc6769ed2d06764bd498886d480"},
+    {file = "docling_core-2.26.4.tar.gz", hash = "sha256:a8176d467f38a281b9c179104ba17c3b9a1b8c90a3e329add1609a176cad018f"},
 ]
 
 [package.dependencies]

tests/data/groundtruth/docling_v2/2203.01017v2.doctags.txt

@@ -106,10 +106,10 @@
 <text><loc_252><loc_232><loc_445><loc_328>Cell Content. In this section, we evaluate the entire pipeline of recovering a table with content. Here we put our approach to test by capitalizing on extracting content from the PDF cells rather than decoding from images. Tab. 4 shows the TEDs score of HTML code representing the structure of the table along with the content inserted in the data cell and compared with the ground-truth. Our method achieved a 5.3% increase over the state-of-the-art, and commercial solutions. We believe our scores would be higher if the HTML ground-truth matched the extracted PDF cell content. Unfortunately, there are small discrepancies such as spacings around words or special characters with various unicode representations.</text>
 <otsl><loc_272><loc_341><loc_426><loc_406><fcel>Model<ched>Simple<ched>TEDS Complex<ched>All<nl><rhed>Tabula<fcel>78.0<fcel>57.8<fcel>67.9<nl><rhed>Traprange<fcel>60.8<fcel>49.9<fcel>55.4<nl><rhed>Camelot<fcel>80.0<fcel>66.0<fcel>73.0<nl><rhed>Acrobat Pro<fcel>68.9<fcel>61.8<fcel>65.3<nl><rhed>EDD<fcel>91.2<fcel>85.4<fcel>88.3<nl><rhed>TableFormer<fcel>95.4<fcel>90.1<fcel>93.6<nl><caption><loc_252><loc_415><loc_445><loc_435>Table 4: Results of structure with content retrieved using cell detection on PubTabNet. In all cases the input is PDF documents with cropped tables.</caption></otsl>
 <page_footer><loc_241><loc_463><loc_245><loc_469>7</page_footer>
+<page_break>
 <unordered_list><list_item><loc_44><loc_50><loc_50><loc_55>a.</list_item>
 <list_item><loc_54><loc_50><loc_408><loc_55>Red - PDF cells, Green - predicted bounding boxes, Blue - post-processed predictions matched to PDF cells</list_item>
 </unordered_list>
-<page_break>
 <section_header_level_1><loc_44><loc_60><loc_232><loc_64>Japanese language (previously unseen by TableFormer):</section_header_level_1>
 <section_header_level_1><loc_249><loc_60><loc_352><loc_64>Example table from FinTabNet:</section_header_level_1>
 <picture><loc_41><loc_65><loc_246><loc_118></picture>
@@ -127,6 +127,7 @@
 <unordered_list><list_item><loc_256><loc_438><loc_445><loc_450>[1] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-</list_item>
 </unordered_list>
 <page_footer><loc_241><loc_463><loc_245><loc_469>8</page_footer>
+<page_break>
 <unordered_list><list_item><loc_57><loc_48><loc_234><loc_74>end object detection with transformers. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, editors, Computer Vision - ECCV 2020 , pages 213-229, Cham, 2020. Springer International Publishing. 5</list_item>
 <list_item><loc_45><loc_76><loc_234><loc_95>[2] Zewen Chi, Heyan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, and Xian-Ling Mao. Complicated table structure recognition. arXiv preprint arXiv:1908.04729 , 2019. 3</list_item>
 <list_item><loc_45><loc_97><loc_234><loc_116>[3] Bertrand Couasnon and Aurelie Lemaitre. Recognition of Tables and Forms , pages 647-677. Springer London, London, 2014. 2</list_item>
@@ -153,7 +154,6 @@
 <list_item><loc_252><loc_396><loc_445><loc_422>[24] Shah Rukh Qasim, Hassan Mahmood, and Faisal Shafait. Rethinking table recognition using graph neural networks. In 2019 International Conference on Document Analysis and Recognition (ICDAR) , pages 142-147. IEEE, 2019. 3</list_item>
 <list_item><loc_252><loc_424><loc_445><loc_450>[25] Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF Conference on</list_item>
 </unordered_list>
-<page_break>
 <page_footer><loc_241><loc_463><loc_245><loc_469>9</page_footer>
 <page_break>
 <text><loc_57><loc_48><loc_234><loc_60>Computer Vision and Pattern Recognition , pages 658-666, 2019. 6</text>

tests/data/groundtruth/docling_v2/redp5110_sampled.doctags.txt

@@ -182,9 +182,9 @@
 <code><loc_112><loc_267><loc_430><loc_432><_unknown_>CREATE MASK HR_SCHEMA.MASK_TAX_ID_ON_EMPLOYEES ON HR_SCHEMA.EMPLOYEES AS EMPLOYEES FOR COLUMN TAX_ID RETURN CASE WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'HR' ) = 1 THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER = EMPLOYEES . USER_ID THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER <> EMPLOYEES . USER_ID THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( EMPLOYEES . TAX_ID , 8 , 4 ) ) WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'EMP' ) = 1 THEN EMPLOYEES . TAX_ID ELSE 'XXX-XX-XXXX' END ENABLE ;<caption><loc_112><loc_257><loc_288><loc_262>Example 3-9 Creating a mask on the TAX_ID column</caption></code>
 <page_footer><loc_282><loc_477><loc_428><loc_482>Chapter 3. Row and Column Access Control</page_footer>
 <page_footer><loc_438><loc_477><loc_447><loc_482>27</page_footer>
+<page_break>
 <unordered_list><list_item><loc_112><loc_45><loc_368><loc_51>3. Figure 3-10 shows the masks that are created in the HR_SCHEMA.</list_item>
 </unordered_list>
-<page_break>
 <picture><loc_52><loc_60><loc_447><loc_107><caption><loc_53><loc_110><loc_239><loc_115>Figure 3-10 Column masks shown in System i Navigator</caption></picture>
 <section_header_level_1><loc_53><loc_128><loc_167><loc_135>3.6.6 Activating RCAC</section_header_level_1>
 <text><loc_112><loc_144><loc_447><loc_165>Now that you have created the row permission and the two column masks, RCAC must be activated. The row permission and the two column masks are enabled (last clause in the scripts), but now you must activate RCAC on the table. To do so, complete the following steps:</text>
@@ -203,10 +203,10 @@
 <picture><loc_52><loc_270><loc_433><loc_408><caption><loc_53><loc_410><loc_284><loc_415>Figure 3-11 Selecting the EMPLOYEES table from System i Navigator</caption></picture>
 <page_footer><loc_53><loc_477><loc_64><loc_482>28</page_footer>
 <page_footer><loc_76><loc_477><loc_273><loc_482>Row and Column Access Control Support in IBM DB2 for i</page_footer>
+<page_break>
 <unordered_list><list_item><loc_112><loc_45><loc_420><loc_66>2. Figure 4-68 shows the Visual Explain of the same SQL statement, but with RCAC enabled. It is clear that the implementation of the SQL statement is more complex because the row permission rule becomes part of the WHERE clause.</list_item>
 <list_item><loc_112><loc_320><loc_447><loc_341>3. Compare the advised indexes that are provided by the Optimizer without RCAC and with RCAC enabled. Figure 4-69 shows the index advice for the SQL statement without RCAC enabled. The index being advised is for the ORDER BY clause.</list_item>
 </unordered_list>
-<page_break>
 <picture><loc_112><loc_75><loc_446><loc_301><caption><loc_112><loc_303><loc_267><loc_309>Figure 4-68 Visual Explain with RCAC enabled</caption></picture>
 <picture><loc_53><loc_349><loc_414><loc_419><caption><loc_53><loc_421><loc_186><loc_427>Figure 4-69 Index advice with no RCAC</caption></picture>
 <page_footer><loc_175><loc_477><loc_428><loc_482>Chapter 4. Implementing Row and Column Access Control: Banking example</page_footer>

tests/data_scanned/groundtruth/docling_v1/ocr_test.json

@@ -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": [69.6796630536824, 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}
+{"_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": [69.0, 688.5883585611979, 506.6666666666667, 767.2550252278646], "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}

tests/data_scanned/groundtruth/docling_v2/ocr_test.doctags.txt

@@ -1,2 +1,2 @@
-<doctag><text><loc_59><loc_46><loc_424><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
+<doctag><text><loc_58><loc_44><loc_426><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
 </doctag>

tests/data_scanned/groundtruth/docling_v2/ocr_test.json

@@ -1 +1 @@
-{"schema_name": "DoclingDocument", "version": "1.3.0", "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": 69.6796630536824, "t": 764.9216921155637, "r": 504.8720051760782, "b": 689.0124221922704, "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", "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", "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": 69.0, "t": 767.2550252278646, "r": 506.6666666666667, "b": 688.5883585611979, "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", "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}}}