Created
February 22, 2015 19:28
-
-
Save pahaz/45dd87ce7b5386cb72be to your computer and use it in GitHub Desktop.
Python safe transliterate print (kill UnicodeEncodeError)
This file contains hidden or 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
#!/usr/bin/env python3 | |
# encoding=utf-8 | |
from __future__ import print_function | |
from __future__ import unicode_literals | |
import string | |
ru_lang_translit_map = { | |
"Я": "Ja", "Ю": "Ju", 'Э': 'E', 'Ь': '\'', 'Ы': 'Y', 'Ъ': '\'', "Щ": "Sch", | |
"Ш": "Sh", "Ч": "Ch", "Ц": "Ts", 'Х': 'H', 'Ф': 'F', 'У': 'U', 'Т': 'T', | |
'С': 'S', 'Р': 'R', 'П': 'P', 'О': 'O', 'Н': 'N', 'М': 'M', 'Л': 'L', | |
'К': 'K', 'Й': 'J', 'И': 'I', 'З': 'Z', "Ж": "Zh", 'Ё': 'E', 'Е': 'E', | |
'Д': 'D', 'Г': 'G', 'В': 'V', 'Б': 'B', 'А': 'A', "я": "ja", "ю": "ju", | |
'э': 'e', 'ъ': '\'', 'ы': 'y', 'ь': '\'', "щ": "sch", "ш": "sh", "ч": "ch", | |
"ц": "ts", 'х': 'h', 'ф': 'f', 'у': 'u', 'т': 't', 'с': 's', 'р': 'r', | |
'п': 'p', 'о': 'o', 'н': 'n', 'м': 'm', 'л': 'l', 'к': 'k', 'й': 'j', | |
'и': 'i', 'з': 'z', "ж": "zh", 'ё': 'e', 'е': 'e', 'д': 'd', 'г': 'g', | |
'в': 'v', 'б': 'b', 'а': 'a', | |
} | |
en_lang_translit_map = {} | |
for x in string.ascii_letters: | |
en_lang_translit_map[x] = x | |
digit_translit_map = {} | |
for x in string.digits: | |
digit_translit_map[x] = x | |
punctuation_and_whitespaces_translit_map = {} | |
for x in string.punctuation: | |
punctuation_and_whitespaces_translit_map[x] = x | |
for x in string.whitespace: | |
punctuation_and_whitespaces_translit_map[x] = ' ' | |
allowed_filename_punctuation_and_whitespaces_translit_map = {} | |
for x in "!#$%&'()+,-.;=@[]^_`{}~": | |
allowed_filename_punctuation_and_whitespaces_translit_map[x] = x | |
for x in string.whitespace: | |
allowed_filename_punctuation_and_whitespaces_translit_map[x] = ' ' | |
allowed_filename_translit_map = \ | |
allowed_filename_punctuation_and_whitespaces_translit_map + \ | |
ru_lang_translit_map + en_lang_translit_map + \ | |
digit_translit_map | |
ascii_translit_map = punctuation_and_whitespaces_translit_map + \ | |
en_lang_translit_map + \ | |
digit_translit_map | |
ru_ascii_translit_map = ascii_translit_map + ru_lang_translit_map | |
do_skip_char = lambda c: '' | |
def transliterate(source_str, translit_map=ru_ascii_translit_map, | |
do_if_unknown_char=do_skip_char): | |
return ''.join(map( | |
lambda x: translit_map.get(x, do_if_unknown_char(x)), | |
source_str)) | |
def safe_print(*args, **kwargs): | |
try: | |
print(*args, **kwargs) | |
except UnicodeEncodeError: | |
translited_args = tuple(_safe_transliterate(arg) for arg in args) | |
print(*translited_args, **kwargs) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment