mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Correct text extraction for table cells (#21)

Browse Source 
* - Fixes for scaling transformation for table cell bounding boxes when using do_cell_matching = False
- Corrected examples/convert.py with appropriate parameter, for good quality example conversion

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>

* Completed checks

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2024-07-30 14:51:47 +02:00
committed by GitHub
parent b07c4a7a4a
commit f4bf3d25b9
2 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/convert.py
View File

@@ -53,7 +53,13 @@ def main():
artifacts_path = DocumentConverter.download_models_hf()
doc_converter = DocumentConverter(artifacts_path=artifacts_path)
pipeline_options = PipelineOptions(do_table_structure=True)
# use text cells predicted from table structure model, instead of matching with pdf cells
pipeline_options.table_structure_options.do_cell_matching = False
doc_converter = DocumentConverter(
artifacts_path=artifacts_path, pipeline_options=pipeline_options
)
input = DocumentConversionInput.from_paths(input_doc_paths)