Portál AbcLinuxu, 3. prosince 2025 09:24
>>> import unicodedata
>>> print unicodedata.normalize('NFD', u'ő')
ő
>>> print unicodedata.normalize('NFD', u'ø')
ø
$ perl -Mutf8 -le '$_="Hungarian ő, Scandinavian ø";tr/őø/o/;print' Hungarian o, Scandinavian o
def cleanString(what):
'''Gets rid of letters which are not in English alphabet'''
assert type(what) == unicode
normalized = unicodedata.normalize('NFKD', what)
output = ''
for c in normalized:
if not unicodedata.combining(c):
output += c
return output
Tiskni
Sdílej:
ISSN 1214-1267, (c) 1999-2007 Stickfish s.r.o.