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

Completed checks

Browse Source 
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak 2024-07-30 14:31:40 +02:00
parent cfdfda3629
commit bff53d403a
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/models/table_structure_model.py
View File

@ -114,7 +114,9 @@ class TableStructureModel:
for element in table_out["tf_responses"]: for element in table_out["tf_responses"]:
if not self.do_cell_matching: if not self.do_cell_matching:
the_bbox = BoundingBox.model_validate(element["bbox"]).scaled(1 / self.scale) the_bbox = BoundingBox.model_validate(
element["bbox"]
).scaled(1 / self.scale)
text_piece = page._backend.get_text_in_rect(the_bbox) text_piece = page._backend.get_text_in_rect(the_bbox)
element["bbox"]["token"] = text_piece element["bbox"]["token"] = text_piece

3
examples/convert.py
View File

@ -58,8 +58,7 @@ def main():
pipeline_options.table_structure_options.do_cell_matching = False pipeline_options.table_structure_options.do_cell_matching = False
doc_converter = DocumentConverter( doc_converter = DocumentConverter(
artifacts_path=artifacts_path, artifacts_path=artifacts_path, pipeline_options=pipeline_options
pipeline_options=pipeline_options
) )
input = DocumentConversionInput.from_paths(input_doc_paths) input = DocumentConversionInput.from_paths(input_doc_paths)