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

fix: fix header levels for DOCX & HTML (#184)

Browse Source 
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2024-10-28 17:02:52 +01:00
committed by GitHub
parent 94d0729c50
commit b9f5c74a7d
4 changed files with 75 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
docling/backend/msword_backend.py
View File

@@ -294,13 +294,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
level = self.get_level()
if isinstance(curr_level, int):
if curr_level == level:
self.parents[level] = doc.add_heading(
parent=self.parents[level - 1], text=text
)
elif curr_level > level:
if curr_level > level:
# add invisible group
for i in range(level, curr_level):
@@ -310,10 +304,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
name=f"header-{i}",
)
self.parents[curr_level] = doc.add_heading(
parent=self.parents[curr_level - 1], text=text
)
elif curr_level < level:
# remove the tail
@@ -321,13 +311,17 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
if key >= curr_level:
self.parents[key] = None
self.parents[curr_level] = doc.add_heading(
parent=self.parents[curr_level - 1], text=text
)
self.parents[curr_level] = doc.add_heading(
parent=self.parents[curr_level - 1],
text=text,
level=curr_level,
)
else:
self.parents[self.level] = doc.add_heading(
parent=self.parents[self.level - 1], text=text
parent=self.parents[self.level - 1],
text=text,
level=1,
)
return