22 lines
597 B
Python
22 lines
597 B
Python
|
import re
|
||
|
|
import unicodedata
|
||
|
|
|
||
|
|
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 = []
|
||
|
|
s = re.sub('\s*&\s*', ' and ', s)
|
||
|
|
for c in unicodedata.normalize('NFKC', 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
|
||
|
|
|