0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

stripAccents

Browse source
This commit is contained in:
j 2010-09-01 14:55:52 +02:00
parent 4a19d5f938
commit 82b7ff413c
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ox/normalize.py
View file

@ -2,6 +2,7 @@
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
# GPL 2008 # GPL 2008
import re import re
import unicodedata
_articles = ('the', 'la', 'a', 'die', 'der', 'le', 'el', _articles = ('the', 'la', 'a', 'die', 'der', 'le', 'el',
"l'", 'il', 'das', 'les', 'o', 'ein', 'i', 'un', 'los', 'de', "l'", 'il', 'das', 'les', 'o', 'ein', 'i', 'un', 'los', 'de',
@ -191,3 +192,8 @@ def normalizePath(path):
if path.endswith('.'): path = path[:-1] + '_' if path.endswith('.'): path = path[:-1] + '_'
return path return path
def stripAccents(s):
if isinstance(s, str):
s = unicode(s)
return ''.join((c for c in unicodedata.normalize('NFD', s) if unicodedata.category(c) != 'Mn'))