Created
January 5, 2013 15:27
-
-
Save anonymous/4462092 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import string | |
def translit1(string): | |
""" This function works just fine """ | |
capital_letters = { | |
u'А': u'A', | |
u'Б': u'B', | |
u'В': u'V', | |
u'Г': u'G', | |
u'Д': u'D', | |
u'Е': u'E', | |
u'Ё': u'E', | |
u'Ж': u'Zh', | |
u'З': u'Z', | |
u'И': u'I', | |
u'Й': u'Y', | |
u'К': u'K', | |
u'Л': u'L', | |
u'М': u'M', | |
u'Н': u'N', | |
u'О': u'O', | |
u'П': u'P', | |
u'Р': u'R', | |
u'С': u'S', | |
u'Т': u'T', | |
u'У': u'U', | |
u'Ф': u'F', | |
u'Х': u'H', | |
u'Ц': u'Ts', | |
u'Ч': u'Ch', | |
u'Ш': u'Sh', | |
u'Щ': u'Sch', | |
u'Ъ': u'', | |
u'Ы': u'Y', | |
u'Ь': u'', | |
u'Э': u'E', | |
u'Ю': u'Yu', | |
u'Я': u'Ya' | |
} | |
lower_case_letters = { | |
u'а': u'a', | |
u'б': u'b', | |
u'в': u'v', | |
u'г': u'g', | |
u'д': u'd', | |
u'е': u'e', | |
u'ё': u'e', | |
u'ж': u'zh', | |
u'з': u'z', | |
u'и': u'i', | |
u'й': u'y', | |
u'к': u'k', | |
u'л': u'l', | |
u'м': u'm', | |
u'н': u'n', | |
u'о': u'o', | |
u'п': u'p', | |
u'р': u'r', | |
u'с': u's', | |
u'т': u't', | |
u'у': u'u', | |
u'ф': u'f', | |
u'х': u'h', | |
u'ц': u'ts', | |
u'ч': u'ch', | |
u'ш': u'sh', | |
u'щ': u'sch', | |
u'ъ': u'', | |
u'ы': u'y', | |
u'ь': u'', | |
u'э': u'e', | |
u'ю': u'yu', | |
u'я': u'ya' | |
} | |
translit_string = "" | |
for index, char in enumerate(string): | |
if char in lower_case_letters.keys(): | |
char = lower_case_letters[char] | |
elif char in capital_letters.keys(): | |
char = capital_letters[char] | |
if len(string) > index+1: | |
if string[index+1] not in lower_case_letters.keys(): | |
char = char.upper() | |
else: | |
char = char.upper() | |
translit_string += char | |
return translit_string | |
def translit2(text): | |
""" This method should be more easy to grasp, | |
but throws exception: | |
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-51: ordinal not in range(128) | |
""" | |
symbols = string.maketrans(u"абвгдеёзийклмнопрстуфхъыьэАБВГДЕЁЗИЙКЛМНОПРСТУФХЪЫЬЭ", | |
u"abvgdeezijklmnoprstufh'y'eABVGDEEZIJKLMNOPRSTUFH'Y'E") | |
sequence = { | |
u'ж':'zh', | |
u'ц':'ts', | |
u'ч':'ch', | |
u'ш':'sh', | |
u'щ':'sch', | |
u'ю':'ju', | |
u'я':'ja', | |
u'Ж':'Zh', | |
u'Ц':'Ts', | |
u'Ч':'Ch' | |
} | |
for char in sequence.keys(): | |
text = text.replace(char, sequence[char]) | |
return text.translate(symbols) | |
if __name__ == "__main__": | |
print translit1(u"Привет") # prints Privet as expected | |
print translit2(u"Привет") # throws exception: UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-51: ordinal not in range(128) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment