mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-10 13:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(pypdfium): resolve overlapping text when merging bounding boxes (#1549)

Browse Source 
get merged_text from boundingbox instead of merging it to prevent overlaps

Signed-off-by: Pedro Ribeiro <pedro_ribeiro_93@hotmail.com>
This commit is contained in:
Pedro Ribeiro
2025-05-19 14:26:00 +01:00
committed by GitHub
parent 12a0e64892
commit 98b5eeb844
52 changed files with 52225 additions and 4690 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docling/backend/pypdfium2_backend.py
View File

@@ -175,13 +175,18 @@ class PyPdfiumPageBackend(PdfPageBackend):
if len(group) == 1:
return group[0]
merged_text = "".join(cell.text for cell in group)
merged_bbox = BoundingBox(
l=min(cell.rect.to_bounding_box().l for cell in group),
t=min(cell.rect.to_bounding_box().t for cell in group),
r=max(cell.rect.to_bounding_box().r for cell in group),
b=max(cell.rect.to_bounding_box().b for cell in group),
)
assert self._ppage is not None
self.text_page = self._ppage.get_textpage()
bbox = merged_bbox.to_bottom_left_origin(page_size.height)
merged_text = self.text_page.get_text_bounded(*bbox.as_tuple())
return TextCell(
index=group[0].index,
text=merged_text,