Merge pull request #264 from khoj-ai/fix/remove-guidance-for-desktop-gui

Escape special characters in the URL when adding a link to the remote file
This commit is contained in:
sabaimran
2023-07-02 09:14:08 -07:00
committed by GitHub

View File

@@ -2,6 +2,7 @@
import glob
import logging
import re
import urllib3
from pathlib import Path
from typing import List
@@ -145,7 +146,8 @@ class MarkdownToJsonl(TextToJsonl):
# Check if raw_filename is a URL. If so, save it as is. If not, convert it to a Path.
if type(raw_filename) == str and re.search(r"^https?://", raw_filename):
entry_filename = raw_filename
# Escape the URL to avoid issues with special characters
entry_filename = urllib3.util.parse_url(raw_filename).url
else:
entry_filename = str(Path(raw_filename))
stem = Path(raw_filename).stem