luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed recursion error, and place no-coord shapes at front

Browse source
This commit is contained in:
Richard Ye 2025-04-01 15:59:23 -04:00 committed by GitHub
parent b20861442f
commit f62d3e80e8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
packages/markitdown/src/markitdown/converters/_pptx_converter.py
View file

@ -168,13 +168,11 @@ class PptxConverter(DocumentConverter):
# Group Shapes
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
not_none_shapes = [shape for shape in slide.shapes if shape.top is not None and shape.left is not None]
sorted_shapes = sorted(not_none_shapes, key=attrgetter("top", "left"))
sorted_shapes = sorted(shape.shapes, key=lambda x: (float('-inf') if not x.top else x.top, float('-inf') if not x.left else x.left))
for subshape in sorted_shapes:
get_shape_content(subshape, **kwargs)
not_none_shapes = [shape for shape in slide.shapes if shape.top is not None and shape.left is not None]
sorted_shapes = sorted(not_none_shapes, key=attrgetter("top", "left"))
sorted_shapes = sorted(slide.shapes, key=lambda x: (float('-inf') if not x.top else x.top, float('-inf') if not x.left else x.left))
for shape in sorted_shapes:
get_shape_content(shape, **kwargs)