Zergling_man/moment
Zergling_man/moment
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix parsing links with some special characters

Browse Source 
Add these characters to the regex allowed list for URL /paths:
non-latin word characters, : ! $ * + ^ @

This also fixes the parsing of matrix.to URLs in messages.
This commit is contained in:
miruka 2021-03-30 18:18:02 -04:00
parent 9fa2816d4b
commit c8bf607fc2
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/backend/html_markdown.py
View File

@ -149,8 +149,8 @@ class HTMLProcessor:
link_regexes = [re.compile(r, re.IGNORECASE) link_regexes = [re.compile(r, re.IGNORECASE)
if isinstance(r, str) else r for r in [ if isinstance(r, str) else r for r in [
# Normal :// URLs # Normal :// URLs
(r"(?P<body>[a-zA-Z\d]+://(?P<host>[a-z\d._-]+(?:\:\d+)?)" (r"(?P<body>[a-z\d]+://(?P<host>[a-z\d._-]+(?:\:\d+)?)"
r"(?:/[/\-_.,a-z\d#%&?;=~]*)?(?:\([/\-_.,a-z\d#%&?;=~]*\))?)"), r"(?:/[/\-.,\w#%&?:;=~!$*+^@]*)?(?:\([/\-_.,a-z\d#%&?;=~]*\))?)"),
# mailto: and tel: # mailto: and tel:
r"mailto:(?P<body>[a-z0-9._-]+@(?P<host>[a-z0-9.:-]*[a-z\d]))", r"mailto:(?P<body>[a-z0-9._-]+@(?P<host>[a-z0-9.:-]*[a-z\d]))",