mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: run poetry pre-commit all files to black format changes Signed-off-by: Franck Benichou franck.benichou@sciencespo.fr

Browse Source 
Signed-off-by: Benichou <fbenichou@deloitte.ca>
This commit is contained in:
Benichou 2025-04-14 22:43:44 -04:00
parent 45eb3e79f7
commit 30cfaaf39f
1 changed files with 17 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docling/backend/mspowerpoint_backend.py
View File

@ -46,10 +46,13 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
self.pptx_obj = None self.pptx_obj = None
self.valid = False self.valid = False
self.xpath_expr = etree.XPath(".//a:blip", namespaces={ self.xpath_expr = etree.XPath(
".//a:blip",
namespaces={
"a": "http://schemas.openxmlformats.org/drawingml/2006/main", "a": "http://schemas.openxmlformats.org/drawingml/2006/main",
"r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships", "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
}) },
)
try: try:
if isinstance(self.path_or_stream, BytesIO): if isinstance(self.path_or_stream, BytesIO):
self.pptx_obj = Presentation(self.path_or_stream) self.pptx_obj = Presentation(self.path_or_stream)
@ -284,7 +287,9 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
) )
return return
def handle_pictures(self, shape, parent_slide, slide_ind, doc, slide_size, drawing_blip, slide): def handle_pictures(
self, shape, parent_slide, slide_ind, doc, slide_size, drawing_blip, slide
):
def get_pptx_image(drawing_blip): def get_pptx_image(drawing_blip):
rId = drawing_blip[0].get( rId = drawing_blip[0].get(
@ -295,6 +300,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
image_data = image_part.blob image_data = image_part.blob
return image_data return image_data
# Open it with PIL # Open it with PIL
try: try:
# Get the image bytes # Get the image bytes
@ -410,8 +416,10 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
if shape.shape_type == MSO_SHAPE_TYPE.PICTURE: if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
# Handle Pictures # Handle Pictures
drawing_blip = self.xpath_expr(shape.element) drawing_blip = self.xpath_expr(shape.element)
if drawing_blip: #ensure there is a drwaing blip if drawing_blip: # ensure there is a drwaing blip
self.handle_pictures(shape, parent_slide, slide_ind, doc, drawing_blip, slide) self.handle_pictures(
shape, parent_slide, slide_ind, doc, drawing_blip, slide
)
# If shape doesn't have any text, move on to the next shape # If shape doesn't have any text, move on to the next shape
if not hasattr(shape, "text"): if not hasattr(shape, "text"):
return return