Untitled

How to handle unicode charters in python with regex
aren’t=ain’t
hello=hey

u'arenu2019t' = u'ainu2019t'
u'hello' = u'hey'

text = u"aren't"

def replace_all(text, dict):
    for i, k in dict.iteritems():
        #replace all whole words of I with K in lower cased text, regex = bSTRINGb
        text = re.sub(r"b" + i + r"b", k , text.lower())
    return text

text = u"aren't"

text = u"aren’t"

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re

d = {
    u'aren’t': u'ain’t',
    u'hello': u'hey'
    }
#text = u"aren't"
text = u"aren’t"


def replace_all(text, d):
    for i, k in d.iteritems():
        #replace all whole words of I with K in lower cased text, regex = bSTRINGb
        text = re.sub(r"b" + i + r"b", k , text.lower())
    return text

if __name__ == '__main__':
    newtext = replace_all(text, d)
    print newtext

ain’t

>>> re.sub(ur'barenu2019tb', 'rep', u'arenu2019t')
u'rep'