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

feat: add textbox content extraction in msword_backend

Browse Source 
Signed-off-by: Andrew <tsai247365@gmail.com>
This commit is contained in:
Andrew 2025-05-13 17:11:43 +08:00
parent b09fd45a46
commit 498fc79392
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
docling/backend/msword_backend.py
View File

@ -359,15 +359,17 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
@classmethod
def _get_format_from_run(cls, run: Run) -> Optional[Formatting]:
has_any_formatting = run.bold or run.italic or run.underline
return (
Formatting(
bold=run.bold or False,
italic=run.italic or False,
underline=run.underline or False,
)
if has_any_formatting
else None
# The .bold and .italic properties are booleans, but .underline can be an enum
# like WD_UNDERLINE.THICK (value 6), so we need to convert it to a boolean
has_bold = run.bold or False
has_italic = run.italic or False
# Convert any non-None underline value to True
has_underline = bool(run.underline is not None and run.underline)
return Formatting(
bold=has_bold,
italic=has_italic,
underline=has_underline,
)
def _get_paragraph_elements(self, paragraph: Paragraph):