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

fix(msword): Fixing function return in equations handling (#1194)

Browse Source 
* Fixing function return

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

* Add message

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

---------

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
This commit is contained in:
Rafael Teixeira de Lima 2025-03-19 10:34:25 +01:00 committed by GitHub
parent 1d680b0a32
commit 0b707d0882
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docling/backend/msword_backend.py
View File

@ -275,8 +275,10 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
only_equations.append(latex_equation) only_equations.append(latex_equation)
texts_and_equations.append(latex_equation) texts_and_equations.append(latex_equation)
if "".join(only_texts) != text: if "".join(only_texts).strip() != text.strip():
return text # If we are not able to reconstruct the initial raw text
# do not try to parse equations and return the original
return text, []
return "".join(texts_and_equations), only_equations return "".join(texts_and_equations), only_equations
@ -365,6 +367,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
for eq in equations: for eq in equations:
if len(text_tmp) == 0: if len(text_tmp) == 0:
break break
pre_eq_text = text_tmp.split(eq, maxsplit=1)[0] pre_eq_text = text_tmp.split(eq, maxsplit=1)[0]
text_tmp = text_tmp.split(eq, maxsplit=1)[1] text_tmp = text_tmp.split(eq, maxsplit=1)[1]
if len(pre_eq_text) > 0: if len(pre_eq_text) > 0: