hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-11 20:06:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: code block segmentation problem of markdown document (#6465)

Browse Source
This commit is contained in:
灰灰
2024-07-25 17:24:37 +08:00
committed by GitHub
parent 16b4f560cd
commit 5e4ac11df3
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
api/core/rag/extractor/markdown_extractor.py
View File

@@ -54,8 +54,16 @@ class MarkdownExtractor(BaseExtractor):
current_header = None current_header = None
current_text = "" current_text = ""
code_block_flag = False
for line in lines: for line in lines:
if line.startswith("```"):
code_block_flag = not code_block_flag
current_text += line + "\n"
continue
if code_block_flag:
current_text += line + "\n"
continue
header_match = re.match(r"^#+\s", line) header_match = re.match(r"^#+\s", line)
if header_match: if header_match:
if current_header is not None: if current_header is not None: