From: dirkf <fieldhouse@gmx.net>
Date: Tue, 28 Nov 2023 17:26:37 +0000 (+0000)
Subject: [utils] Make restricted filenames ignore characters in Unicode categories Mark, Other
X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=427472351ce6b2fcf5bb35dde32bf9ee5beddd89;p=youtube-dl

[utils] Make restricted filenames ignore characters in Unicode categories Mark, Other

Resolves #32629
---

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 443d2609c..61b94d84c 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -2121,7 +2121,8 @@ def sanitize_filename(s, restricted=False, is_id=False):
         if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
             return '_'
         if restricted and ord(char) > 127:
-            return '_'
+            return '' if unicodedata.category(char)[0] in 'CM' else '_'
+
         return char
 
     # Replace look-alike Unicode glyphs