mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-29 21:44:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

restructure title fix

Browse Source 
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Panos Vagenas 2024-10-29 17:18:26 +01:00
parent 5c8e06fbde
commit e11bbc8b0b
1 changed files with 21 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
docling/backend/html_backend.py
View File

@ -179,33 +179,31 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.parents[self.level] = doc.add_text(
parent=self.parents[0], label=DocItemLabel.TITLE, text=text
)
else:
if hlevel > self.level:
return # dont add another heading with the same text!
# add invisible group
for i in range(self.level + 1, hlevel):
self.parents[i] = doc.add_group(
name=f"header-{i}",
label=GroupLabel.SECTION,
parent=self.parents[i - 1],
)
self.level = hlevel
elif hlevel > self.level:
elif hlevel < self.level:
# add invisible group
for i in range(self.level + 1, hlevel):
self.parents[i] = doc.add_group(
name=f"header-{i}",
label=GroupLabel.SECTION,
parent=self.parents[i - 1],
)
self.level = hlevel
# remove the tail
for key, val in self.parents.items():
if key > hlevel:
self.parents[key] = None
self.level = hlevel
elif hlevel < self.level:
# remove the tail
for key, val in self.parents.items():
if key > hlevel:
self.parents[key] = None
self.level = hlevel
self.parents[hlevel] = doc.add_heading(
parent=self.parents[hlevel - 1],
text=text,
level=hlevel,
)
self.parents[hlevel] = doc.add_heading(
parent=self.parents[hlevel - 1],
text=text,
level=hlevel,
)
def handle_paragraph(self, element, idx, doc):
"""Handles paragraph tags (p)."""