mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 12:34:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Identify headers through inhenrited style

Browse Source 
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
This commit is contained in:
Rafael Teixeira de Lima 2025-04-04 14:46:43 +02:00
parent 207cd78a26
commit 851baf1090
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

@ -264,6 +264,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
label = paragraph.style.style_id label = paragraph.style.style_id
name = paragraph.style.name name = paragraph.style.name
base_style_label = None
base_style_name = None
if base_style := getattr(paragraph.style, "base_style", None):
base_style_label = base_style.style_id
base_style_name = base_style.name
if label is None: if label is None:
return "Normal", None return "Normal", None
@ -277,6 +282,10 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
return self._get_heading_and_level(label) return self._get_heading_and_level(label)
if "heading" in name.lower(): if "heading" in name.lower():
return self._get_heading_and_level(name) return self._get_heading_and_level(name)
if base_style_label and "heading" in base_style_label.lower():
return self._get_heading_and_level(base_style_label)
if base_style_name and "heading" in base_style_name.lower():
return self._get_heading_and_level(base_style_name)
return label, None return label, None