public/kcc
1
0
Fork 0
mirror of https://github.com/ciromattia/kcc synced 2025-12-17 19:51:45 +00:00
Code Issues Releases Wiki Activity

Slugify: Unicode fix

Browse Source
This commit is contained in:
Paweł Jastrzębski
2013-10-10 13:17:03 +02:00
parent 82445d5d3a
commit ea01492e1f
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
kcc/comic2ebook.py
View File

@@ -587,8 +587,11 @@ def getWorkFolder(afile):
def slugify(value): def slugify(value):
# Normalizes string, converts to lowercase, removes non-alpha characters and converts spaces to hyphens. # Normalizes string, converts to lowercase, removes non-alpha characters and converts spaces to hyphens.
import unicodedata import unicodedata
#noinspection PyArgumentList if isinstance(value, str):
value = unicodedata.normalize('NFKD', unicode(value, 'latin1')).encode('ascii', 'ignore') #noinspection PyArgumentList
value = unicodedata.normalize('NFKD', unicode(value, 'latin1')).encode('ascii', 'ignore')
elif isinstance(value, unicode):
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore')
value = re.sub('[^\w\s\.-]', '', value).strip().lower() value = re.sub('[^\w\s\.-]', '', value).strip().lower()
value = re.sub('[-\.\s]+', '-', value) value = re.sub('[-\.\s]+', '-', value)
value = re.sub(r'([0-9]+)', r'00000\1', value) value = re.sub(r'([0-9]+)', r'00000\1', value)