mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleaning up

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-10-25 17:56:42 +02:00
parent 3e490c4184
commit 28a09a5029
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/backend/html_backend.py
View File

@ -148,8 +148,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
if isinstance(item, str): if isinstance(item, str):
return [item] return [item]
# result.append(self.get_direct_text(item))
if item.name not in ["ul", "ol"]: if item.name not in ["ul", "ol"]:
try: try:
# Iterate over the children (and their text and tails) # Iterate over the children (and their text and tails)
@ -255,7 +253,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
if nested_lists: if nested_lists:
name = element.name name = element.name
# text = self.get_direct_text(element)
# Text in list item can be hidden within hierarchy, hence # Text in list item can be hidden within hierarchy, hence
# we need to extract it recursively # we need to extract it recursively
text = self.extract_text_recursively(element) text = self.extract_text_recursively(element)