def destress(s, replace={}):
""" Returns the string with no diacritics.
"""
for k, v in replace.items():
s = s.replace(k, v)
for k, v in {
u'ø' : 'o' ,
u'ß' : 'ss',
u'œ' : 'ae',
u'æ' : 'oe',
u'“' : '"' ,
u'”' : '"' ,
u'‘' : "'" ,
u'’' : "'" ,
u'?' : '/' ,
u'¿' : '?' ,
u'¡' : '!'}.items():
s = s.replace(k, v)
f = unicodedata.combining # f('´') == 0
s = unicodedata.normalize('NFKD', s) # é => e + ´
s = ''.join(ch for ch in s if not f(ch))
return s
# print(destress(u'pâté')) # 'pate'
评论列表
文章目录