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: Proper handling of orphan IDs in layout postprocessing (#1118)

Browse Source 
* Fix the handling of orphan IDs in layout postprocessing

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

* Update test cases

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

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-03-05 14:30:59 +01:00
committed by GitHub
parent 357d41cc47
commit c56ab3a66b
33 changed files with 36 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docling/utils/layout_postprocessor.py
View File

@@ -203,6 +203,7 @@ class LayoutPostprocessor:
"""Initialize processor with cells and spatial indices."""
self.cells = cells
self.page_size = page_size
self.all_clusters = clusters
self.regular_clusters = [
c for c in clusters if c.label not in self.SPECIAL_TYPES
]
@@ -267,7 +268,7 @@ class LayoutPostprocessor:
# Handle orphaned cells
unassigned = self._find_unassigned_cells(clusters)
if unassigned:
next_id = max((c.id for c in clusters), default=0) + 1
next_id = max((c.id for c in self.all_clusters), default=0) + 1
orphan_clusters = []
for i, cell in enumerate(unassigned):
conf = 1.0