mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(html): handle nested empty lists (#1154)
Some checks failed
Run Docs CD / build-deploy-docs (push) Failing after 1m20s
Run Docs CI / build-docs (push) Failing after 49s

Browse Source 
Address the case of nested lists in empty list items.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-03-13 16:56:58 +01:00
committed by GitHub
parent 0945973b79
commit f94da44ec5
5 changed files with 456 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docling/backend/html_backend.py
View File

@@ -134,7 +134,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.analyze_tag(cast(Tag, element), doc)
except Exception as exc_child:
_log.error(
f"Error processing child from tag{tag.name}: {exc_child}"
f"Error processing child from tag {tag.name}: {repr(exc_child)}"
)
raise exc_child
elif isinstance(element, NavigableString) and not isinstance(
@@ -347,11 +347,11 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
content_layer=self.content_layer,
)
self.level += 1
self.walk(element, doc)
self.parents[self.level + 1] = None
self.level -= 1
self.walk(element, doc)
self.parents[self.level + 1] = None
self.level -= 1
else:
self.walk(element, doc)
elif element.text.strip():
text = element.text.strip()