mediagoblin/tools/url.py

   1 # GNU MediaGoblin -- federated, autonomous media hosting
   2 # Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
   3 #
   4 # This program is free software: you can redistribute it and/or modify
   5 # it under the terms of the GNU Affero General Public License as published by
   6 # the Free Software Foundation, either version 3 of the License, or
   7 # (at your option) any later version.
   8 #
   9 # This program is distributed in the hope that it will be useful,
  10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12 # GNU Affero General Public License for more details.
  13 #
  14 # You should have received a copy of the GNU Affero General Public License
  15 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  16
  17 import re
  18 # This import *is* used; see word.encode('tranlit/long') below.
  19 from unicodedata import normalize
  20
  21 try:
  22     import translitcodec
  23     USING_TRANSLITCODEC = True
  24 except ImportError:
  25     USING_TRANSLITCODEC = False
  26
  27
  28 _punct_re = re.compile(r'[\t !"#:$%&\'()*\-/<=>?@\[\\\]^_`{|},.]+')
  29
  30
  31 def slugify(text, delim=u'-'):
  32     """
  33     Generates an ASCII-only slug. Taken from http://flask.pocoo.org/snippets/5/
  34     """
  35     result = []
  36     for word in _punct_re.split(text.lower()):
  37         if USING_TRANSLITCODEC:
  38             word = word.encode('translit/long')
  39         else:
  40             word = normalize('NFKD', word).encode('ascii', 'ignore')
  41
  42         if word:
  43             result.append(word)
  44     return unicode(delim.join(result))