Geek Answers Handbook

Python UTF-8 Lower Case Turkish Text

using python 2.7:

>myCity = 'Isparta'
>myCity.lower()
>'isparta'
#-should be-
>'ısparta'

I tried some decoding (for example, myCity.decode ("utf-8"). lower ()), but could not find how to do it.

how can these letters be reduced? ('I'> 'ı', 'İ'> 'i', etc.)

EDIT: In Turkish, the lowercase "I" is "ı". The uppercase 'i' is equal to 'İ'

+5
source share
5 answers

Some suggested using a locale tr_TR.utf8. At least on Ubuntu, possibly related to this error , installing this language does not give the desired result:

import locale
locale.setlocale(locale.LC_ALL, 'tr_TR.utf8')

myCity = u'Isparta İsparta'
print(myCity.lower())
# isparta isparta

, , :

lower_map = {
    ord(u'I'): u'ı',
    ord(u'İ'): u'i',
    }

myCity = u'Isparta İsparta'
lowerCity = myCity.translate(lower_map)
print(lowerCity)
# ısparta isparta


ısparta isparta
+8

unicode emre solution

class unicode_tr(unicode):
    CHARMAP = {
        "to_upper": {
            u"ı": u"I",
            u"i": u"İ",
        },
        "to_lower": {
            u"I": u"ı",
            u"İ": u"i",
        }
    }

    def lower(self):
        for key, value in self.CHARMAP.get("to_lower").items():
            self = self.replace(key, value)
        return self.lower()

    def upper(self):
        for key, value in self.CHARMAP.get("to_upper").items():
            self = self.replace(key, value)
        return self.upper()

if __name__ == '__main__':
    print unicode_tr("kitap").upper()
    print unicode_tr("KİTAP").lower()


KİTAP
kitap

.

+4

( tr-TR) locale.setLocale(). , - en-US, I I.

+2

Emre monkey-patching . unicode unicode my_unicode_string = unicode_tr(u'bla bla bla') , unicode

https://github.com/technic-programming/unicode_tr

# -*- coding: utf8 -*-
# Redesigned by @guneysus

import __builtin__
from forbiddenfruit import curse

lcase_table = tuple(u'abcçdefgğhıijklmnoöprsştuüvyz')
ucase_table = tuple(u'ABCÇDEFGĞHIİJKLMNOÖPRSŞTUÜVYZ')

def upper(data):
    data = data.replace('i',u'İ')
    data = data.replace(u'ı',u'I')
    result = ''
    for char in data:
        try:
            char_index = lcase_table.index(char)
            ucase_char = ucase_table[char_index]
        except:
            ucase_char = char
        result += ucase_char
    return result

def lower(data):
    data = data.replace(u'İ',u'i')
    data = data.replace(u'I',u'ı')
    result = ''
    for char in data:
        try:
            char_index = ucase_table.index(char)
            lcase_char = lcase_table[char_index]
        except:
            lcase_char = char
        result += lcase_char
    return result

def capitalize(data):
    return data[0].upper() + data[1:].lower()

def title(data):
    return " ".join(map(lambda x: x.capitalize(), data.split()))

curse(__builtin__.unicode, 'upper', upper)
curse(__builtin__.unicode, 'lower', lower)
curse(__builtin__.unicode, 'capitalize', capitalize)
curse(__builtin__.unicode, 'title', title)

if __name__ == '__main__':
    print u'istanbul'.upper()
    print u'İSTANBUL'.lower()
0

.replace(), /. :

    myCity.replace('I', 'ı').lower()
0

More articles:


All Articles