mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-11 22:28:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Empty table handling (#2365)

Browse Source 
* add table raw cells when no table structure model was used

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Add RichTableCell instance for tables with missing structure.

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-10-02 19:35:16 +02:00
committed by GitHub
parent e6c3b05e63
commit ca2be7ff3a
4 changed files with 19 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docling/models/readingorder_model.py
View File

@@ -216,8 +216,13 @@ class ReadingOrderModel:
elif isinstance(element, Table):
# Check if table has no structure prediction
if element.num_rows == 0 and element.num_cols == 0:
# Create minimal 1x1 table with rich cell containing all children
tbl_data = TableData(num_rows=1, num_cols=1, table_cells=[])
# Only create 1x1 table if there are children to put in it
if element.cluster.children:
# Create minimal 1x1 table with rich cell containing all children
tbl_data = TableData(num_rows=1, num_cols=1, table_cells=[])
else:
# Create empty table with no structure
tbl_data = TableData(num_rows=0, num_cols=0, table_cells=[])
else:
tbl_data = TableData(
num_rows=element.num_rows,
@@ -253,8 +258,12 @@ class ReadingOrderModel:
tbl.footnotes.append(new_footnote_item.get_ref())
# Handle case where table has no structure prediction
if element.num_rows == 0 and element.num_cols == 0:
# Handle case where table has no structure prediction but has children
if (
element.num_rows == 0
and element.num_cols == 0
and element.cluster.children
):
# Create rich cell containing all child elements
rich_cell_ref = self._create_rich_cell_group(element, out_doc, tbl)