AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-12 06:19:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: keep image url (#17430)

Browse Source
This commit is contained in:
Panpan 2025-04-04 15:55:48 +08:00 committed by GitHub
parent 296e2ef90f
commit fc3f14c0ee
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
api/core/rag/cleaner/clean_processor.py
View File

@ -27,9 +27,26 @@ class CleanProcessor:
pattern = r"([a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)"
text = re.sub(pattern, "", text)
# Remove URL
pattern = r"https?://[^\s]+"
text = re.sub(pattern, "", text)
# Remove URL but keep Markdown image URLs
# First, temporarily replace Markdown image URLs with a placeholder
markdown_image_pattern = r"!\[.*?\]\((https?://[^\s)]+)\)"
placeholders: list[str] = []
def replace_with_placeholder(match, placeholders=placeholders):
url = match.group(1)
placeholder = f"__MARKDOWN_IMAGE_URL_{len(placeholders)}__"
placeholders.append(url)
return f"![image]({placeholder})"
text = re.sub(markdown_image_pattern, replace_with_placeholder, text)
# Now remove all remaining URLs
url_pattern = r"https?://[^\s)]+"
text = re.sub(url_pattern, "", text)
# Finally, restore the Markdown image URLs
for i, url in enumerate(placeholders):
text = text.replace(f"__MARKDOWN_IMAGE_URL_{i}__", url)
return text
def filter_string(self, text):