From 7a275c763731d9c96b7cf32f2e27b8dc8bebacd7 Mon Sep 17 00:00:00 2001 From: Bruno Rigal <29140541+brunorigal@users.noreply.github.com> Date: Tue, 10 Jun 2025 19:43:20 +0200 Subject: [PATCH] fix: Handle NoneType error in MsPowerpointDocumentBackend (#1747) fix:nonetyperror in pptx backend Signed-off-by: Bruno Rigal Co-authored-by: Bruno Rigal --- docling/backend/mspowerpoint_backend.py | 29 ++++++++++++++----------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/docling/backend/mspowerpoint_backend.py b/docling/backend/mspowerpoint_backend.py index 3b9a6bb..5091b0c 100644 --- a/docling/backend/mspowerpoint_backend.py +++ b/docling/backend/mspowerpoint_backend.py @@ -423,18 +423,21 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB # Handle notes slide if slide.has_notes_slide: notes_slide = slide.notes_slide - notes_text = notes_slide.notes_text_frame.text.strip() - if notes_text: - bbox = BoundingBox(l=0, t=0, r=0, b=0) - prov = ProvenanceItem( - page_no=slide_ind + 1, charspan=[0, len(notes_text)], bbox=bbox - ) - doc.add_text( - label=DocItemLabel.TEXT, - parent=parent_slide, - text=notes_text, - prov=prov, - content_layer=ContentLayer.FURNITURE, - ) + if notes_slide.notes_text_frame is not None: + notes_text = notes_slide.notes_text_frame.text.strip() + if notes_text: + bbox = BoundingBox(l=0, t=0, r=0, b=0) + prov = ProvenanceItem( + page_no=slide_ind + 1, + charspan=[0, len(notes_text)], + bbox=bbox, + ) + doc.add_text( + label=DocItemLabel.TEXT, + parent=parent_slide, + text=notes_text, + prov=prov, + content_layer=ContentLayer.FURNITURE, + ) return doc