NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(docx): Support of SDTs in docx backend (#853)

Browse Source 
Support of table of content containers in docx backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak 2025-01-31 14:52:24 +01:00 committed by GitHub
parent 2c037ae62e
commit d727b04ad0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
docling/backend/msword_backend.py
View File

@ -137,6 +137,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
namespaces = { 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",
"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main",
} }
xpath_expr = XPath(".//a:blip", namespaces=namespaces) xpath_expr = XPath(".//a:blip", namespaces=namespaces)
drawing_blip = xpath_expr(element) drawing_blip = xpath_expr(element)
@ -150,6 +151,14 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
elif drawing_blip: elif drawing_blip:
self.handle_pictures(element, docx_obj, drawing_blip, doc) self.handle_pictures(element, docx_obj, drawing_blip, doc)
# Check for the sdt containers, like table of contents
elif tag_name in ["sdt"]:
sdt_content = element.find(".//w:sdtContent", namespaces=namespaces)
if sdt_content is not None:
# Iterate paragraphs, runs, or text inside <w:sdtContent>.
paragraphs = sdt_content.findall(".//w:p", namespaces=namespaces)
for p in paragraphs:
self.handle_text_elements(p, docx_obj, doc)
# Check for Text # Check for Text
elif tag_name in ["p"]: elif tag_name in ["p"]:
# "tcPr", "sectPr" # "tcPr", "sectPr"