orhan/test
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Handle PPTX shapes where position is None (#1161)

Browse Source 
* Handle shapes where position is None
* Fixed recursion error, and place no-coord shapes at front
This commit is contained in:
Richard Ye
2025-08-26 18:28:17 -04:00
committed by GitHub
parent 59eb60f8cb
commit 17365654c9
1 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
packages/markitdown/src/markitdown/converters/_pptx_converter.py
View File

@@ -168,11 +168,23 @@ 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")) 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: for subshape in sorted_shapes:
get_shape_content(subshape, **kwargs) get_shape_content(subshape, **kwargs)
sorted_shapes = sorted(slide.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: for shape in sorted_shapes:
get_shape_content(shape, **kwargs) get_shape_content(shape, **kwargs)