use unicodedata.normalize for sort_title
This commit is contained in:
parent
dcd8731b75
commit
67a31d1f58
1 changed files with 5 additions and 1 deletions
|
@ -7,6 +7,7 @@ import os
|
|||
import sys
|
||||
import re
|
||||
import hashlib
|
||||
import unicodedata
|
||||
|
||||
import ox
|
||||
import ox.iso
|
||||
|
@ -164,7 +165,10 @@ def parse_path(path):
|
|||
def sort_title(title):
|
||||
#title
|
||||
title = re.sub(u'[\'!¿¡,\.;\-"\:\*\[\]]', '', title)
|
||||
title = title.replace(u'Æ', 'Ae')
|
||||
|
||||
#title = title.replace(u'Æ', 'Ae')
|
||||
title = unicodedata.normalize('NFKD',title)
|
||||
|
||||
#pad numbered titles
|
||||
title = re.sub('(\d+)', lambda x: '%010d' % int(x.group(0)), title)
|
||||
return title.strip()
|
||||
|
|
Loading…
Reference in a new issue