Created
October 7, 2022 15:03
-
-
Save nazartm/a57040cca921bb720eb583b88e8f3d83 to your computer and use it in GitHub Desktop.
Transliterates from cyrillic turkmen alphabet to latin turkmen alphabet
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
import re | |
import sys | |
special_cases = [r'(Ё|Ю|Я)\.', r'(\s)Е\.', r'(\s)е', r'(\s)Е', r'(\s)?("|«|“)е', r'(\s)?("|«|“)Е', r'^Е', r'^е'] | |
special_case_mappings= ['Ý.', r'\1Ý.', r'\1ýe', r'\1Ýe', r'\1\2ýe', r'\1\2Ýe', 'Ýe', 'ýe'] | |
turkmen_cyrillic_lc = ("а", "б", "в", "г", "д", "ъе", "е", "ё", "ж", "җ", "з", "и", "й", "к", "л", "м", "н", "ң", "о", "ө", "п", "р", "с", "т", "у", "ү", "ф", "х", "ц", "ч", "ш", "щ", "ъ", "ы", "ь", "э", "ә", "ю", "я") | |
turkmen_latin_lc = ("a", "b", "w", "g", "d", "ýe", "e", "ýo", "ž", "j", "z", "i", "ý", "k", "l", "m", "n", "ň", "o", "ö", "p", "r", "s", "t", "u", "ü", "f", "h", "s", "ç", "ş", "ş", "", "y", "", "e", "ä", "ýu", "ýa") | |
turkmen_cyrillic_uc = ("А", "Б", "В", "Г", "Д", "ъе", "Е", "Ё", "Ж", "Җ", "З", "И", "Й", "К", "Л", "М", "Н", "Ң", "О", "Ө", "П", "Р", "С", "Т", "У", "Ү", "Ф", "Х", "Ц", "Ч", "Ш", "Щ", "Ъ", "Ы", "Ь", "Э", "Ә", "Ю", "Я") | |
turkmen_latin_uc = ("A", "B", "W", "G", "D", "Ýe", "E", "Ýo", "Ž", "J", "Z", "I", "Ý", "K", "L", "M", "N", "Ň", "O", "Ö", "P", "R", "S", "T", "U", "Ü", "F", "H", "S", "Ç", "Ş", "Ş", "", "Y", "", "E", "Ä", "Ýu", "Ýa") | |
fix_patterns = (r'(a|i|ö|ä|e|y|ü)e', r'(A|I|Ö|Ä|E|Y|Ü)e', r'(A|I|Ö|Ä|E|Y|Ü)E', r'Ý(a|e|u|o)([A-ZÝŽŇÖÜÇŞÄ]+)') | |
fix_replacements = (r'\1ýe', r'\1ýe', r'\1ÝE', lambda m: m.group(0).upper()) | |
def batch_regex(text, regex_needles, replacements): | |
for i, needle in enumerate(regex_needles): | |
text = re.sub(needle, replacements[i], text) | |
return text | |
def batch_replace(text, needles, replacements): | |
for i, needle in enumerate(needles): | |
text = text.replace(needle, replacements[i]) | |
return text | |
""" | |
Transliterates from cyrillic turkmen alphabet to latin turkmen alphabet | |
""" | |
def transliterate(text): | |
text = batch_regex(text, special_cases, special_case_mappings) | |
text = batch_replace(text, turkmen_cyrillic_lc, turkmen_latin_lc) | |
text = batch_replace(text, turkmen_cyrillic_uc, turkmen_latin_uc) | |
text = batch_regex(text, fix_patterns, fix_replacements) | |
return text | |
if __name__ == '__main__': | |
if len(sys.argv) < 2: | |
print("Usage: python3 transliterate.py <filename>") | |
sys.exit(0) | |
input_file = sys.argv[1] | |
with open(input_file) as f: | |
text = f.read() | |
transliterated = transliterate(text) | |
print(transliterated) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment