mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-10 13:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Fixed docx import with headers that are also lists (#842)

Browse Source 
* Fix for docx when headers are also lists, now recorded as appropriate headers and subheaders, unit test included

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Update docling/backend/msword_backend.py

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com>

* Update docling/backend/msword_backend.py

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Maxim Lysak <101627549+maxmnemonic@users.noreply.github.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Maxim Lysak
2025-01-31 10:51:21 +01:00
committed by GitHub
parent 2a1f8afe7e
commit 2c037ae62e
5 changed files with 868 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docling/backend/msword_backend.py
View File

@@ -240,7 +240,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
numid = None
# Handle lists
if numid is not None and ilevel is not None:
if (
numid is not None
and ilevel is not None
and p_style_id not in ["Title", "Heading"]
):
self.add_listitem(
element,
docx_obj,
@@ -254,12 +258,22 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
)
self.update_history(p_style_id, p_level, numid, ilevel)
return
elif numid is None and self.prev_numid() is not None: # Close list
for key, val in self.parents.items():
if key >= self.level_at_new_list:
elif (
numid is None
and self.prev_numid() is not None
and p_style_id not in ["Title", "Heading"]
): # Close list
if self.level_at_new_list:
for key in range(len(self.parents)):
if key >= self.level_at_new_list:
self.parents[key] = None
self.level = self.level_at_new_list - 1
self.level_at_new_list = None
else:
for key in range(len(self.parents)):
self.parents[key] = None
self.level = self.level_at_new_list - 1
self.level_at_new_list = None
self.level = 0
if p_style_id in ["Title"]:
for key, val in self.parents.items():
self.parents[key] = None