From 989a01c2610832193c268d072ada8814bfd4c00d Mon Sep 17 00:00:00 2001 From: pukkandan Date: Thu, 4 Aug 2022 20:19:32 +0530 Subject: [PATCH] [outtmpl] Smarter replacing of unsupported characters Closes #1330 --- yt_dlp/utils.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py index c56f31013f..3a33cad2e7 100644 --- a/yt_dlp/utils.py +++ b/yt_dlp/utils.py @@ -40,6 +40,7 @@ import tempfile import time import traceback import types +import unicodedata import urllib.error import urllib.parse import urllib.request @@ -647,6 +648,9 @@ def sanitize_filename(s, restricted=False, is_id=NO_DEFAULT): return ACCENT_CHARS[char] elif not restricted and char == '\n': return '\0 ' + elif is_id is NO_DEFAULT and not restricted and char in '"*:<>?|/\\': + # Replace with their full-width unicode counterparts + return {'/': '\u29F8', '\\': '\u29f9'}.get(char, chr(ord(char) + 0xfee0)) elif char == '?' or ord(char) < 32 or ord(char) == 127: return '' elif char == '"': @@ -659,6 +663,8 @@ def sanitize_filename(s, restricted=False, is_id=NO_DEFAULT): return '\0_' return char + if restricted and is_id is NO_DEFAULT: + s = unicodedata.normalize('NFKC', s) s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s) # Handle timestamps result = ''.join(map(replace_insane, s)) if is_id is NO_DEFAULT: