From e8ba274776d51f3f4301ce8fce49f55865880a39 Mon Sep 17 00:00:00 2001
From: Tulir Asokan <tulir@maunium.net>
Date: Sat, 10 Aug 2019 13:23:35 +0300
Subject: [PATCH] Use unicodedata for cleaning up whitespace names

---
 mautrix_telegram/puppet.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mautrix_telegram/puppet.py b/mautrix_telegram/puppet.py
index d7be58de..3fd9f571 100644
--- a/mautrix_telegram/puppet.py
+++ b/mautrix_telegram/puppet.py
@@ -15,6 +15,7 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 from typing import Awaitable, Any, Dict, Iterable, Optional, Union, TYPE_CHECKING
 from difflib import SequenceMatcher
+import unicodedata
 import asyncio
 import logging
 
@@ -194,7 +195,7 @@ class Puppet(CustomPuppetMixin):
         whitespace = ("\t\n\r\v\f \u00a0\u034f\u180e\u2063\u202f\u205f\u2800\u3000\u3164\ufeff"
                       "\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u200b"
                       "\u200c\u200d\u200e\u200f")
-        name = name.strip(whitespace)
+        name = str(filter(lambda c: unicodedata.category(c) != 'Cf', name.strip(whitespace)))
         return name
 
     @classmethod