Created
February 17, 2013 14:21
-
-
Save namongk/4971666 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#-*-coding:utf-8-*- | |
import re | |
import unicodedata | |
from django.utils.encoding import smart_unicode | |
# Extra characters outside of alphanumerics that we'll allow. | |
SLUG_OK = '-_~' | |
def slugify(s, ok=SLUG_OK, lower=True, spaces=False): | |
# L and N signify letter/number. | |
# http://www.unicode.org/reports/tr44/tr44-4.html#GC_Values_Table | |
rv = [] | |
for c in unicodedata.normalize('NFKC', smart_unicode(s)): | |
cat = unicodedata.category(c)[0] | |
if cat in 'LN' or c in ok: | |
rv.append(c) | |
if cat == 'Z': # space | |
rv.append(' ') | |
new = ''.join(rv).strip() | |
if not spaces: | |
new = re.sub('[-\s]+', '-', new) | |
return new.lower() if lower else new |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment