zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-24 01:16:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(html_parser): keep text before the first block element (#17073)

Browse Source
This commit is contained in:
Andrew Chen
2026-07-23 12:43:16 +08:00
committed by GitHub
parent 5478f955ab
commit 8af2467112
2 changed files with 26 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
deepdoc/parser/html_parser.py
View File

@@ -159,7 +159,10 @@ class RAGFlowHtmlParser:
if title_flag:
content = f"{TITLE_TAGS[tag_name]} {content}"
if last_block_id != block_id:
if last_block_id is not None:
# Flush whatever is buffered, including loose text that
# precedes the first block (last_block_id is None there),
# which was otherwise overwritten and lost.
if current_content:
block_content.append(current_content)
current_content = content
last_block_id = block_id