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

Handle shapes where position is None

Browse source
This commit is contained in:
Richard Ye 2025-03-28 10:26:00 -04:00 committed by GitHub
parent 9e067c42b6
commit 0706e5919c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
packages/markitdown/src/markitdown/converters/_pptx_converter.py
View file

@ -168,11 +168,13 @@ class PptxConverter(DocumentConverter):
# Group Shapes # Group Shapes
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP: if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
sorted_shapes = sorted(shape.shapes, key=attrgetter("top", "left")) 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"))
for subshape in sorted_shapes: for subshape in sorted_shapes:
get_shape_content(subshape, **kwargs) get_shape_content(subshape, **kwargs)
sorted_shapes = sorted(slide.shapes, key=attrgetter("top", "left")) 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"))
for shape in sorted_shapes: for shape in sorted_shapes:
get_shape_content(shape, **kwargs) get_shape_content(shape, **kwargs)