docling-project / docling-project/docling
Mixed Arabic-English PDFs produce incorrect OCR/output text
Open
bug
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Bug
Converting PDFs containing both Arabic and English text, the generated .md output is inconsistent
(Output file on screenshots)
### Steps to reproduce
docling "https://tug.ctan.org/macros/latex/exptl/mem/arabic.pdf"
(arabic.pdf used as example)
### Docling version
Docling version: 2.90.0
Docling Core version: 2.74.0
Docling IBM Models version: 3.13.0
Docling Parse version: 5.9.0
Python: cpython-313 (3.13.13)
Platform: Windows-11-10.0.26200-SP0
### Python version
Python 3.13.13
Contributor guide
Assessment
This issue has not been assessed yet.