docling-project / docling-project/docling

[BEE] Table model missing the last part of the table in the Japanese document

Open
#3,402 10 comments 0 reactions 0 assignees View on GitHub
bug
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug
The bottom row of the table is missing from the output.

Observation:

These are selectable texts in the table
The token appears in the token list but not considered in table structure.
As per bounding box , token is well within the page

{
"id": "TOKEN_000102",
"confidence": 1.0,
"bbox": { "x": 169, "y": 606, "width": 110, "height": 10, "page_number": 1 },
"text": "ESGワーキング・グループ"
}

### Steps to reproduce
Run IBM_2021_ESG_Report 10.pdf through the latest docling.
The document is kept here -> https://ibm.ent.box.com/folder/380274980502

### Docling version
Latest

### Python version
3.12

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.