docling-project / docling-project/docling
[BEE] The tableformer outout for Japanese Invoice is incorrect
Open
bug
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Bug
The table headers are incorrect for the given table.
"| 商品名 ／ 品⽬ |数 |量 単 |価 ⾦ 額 |"
^^^^^^^^^^^^^
instead of the expected output of
"| 商品名 ／ 品⽬ |数 量| 単 価| ⾦ 額 |"
^^^^^^^^^^^^^
### Steps to reproduce
Run Japanese document 1 niwa_invoice_microtech.pdf through docling and observe the output
### Docling version
2.42.2
### Python version
3.11
Contributor guide
Assessment
This issue has not been assessed yet.