Spaces:
Sleeping
Sleeping
File size: 1,792 Bytes
c5ed230 bd5f307 c5ed230 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import re
import cn2an
import opencc
import config
converter = opencc.OpenCC(config.ABS_PATH + '/chinese_dialect_lexicons/zaonhe')
# List of (Latin alphabet, ipa) pairs:
_latin_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
('A', 'ᴇ'),
('B', 'bi'),
('C', 'si'),
('D', 'di'),
('E', 'i'),
('F', 'ᴇf'),
('G', 'dʑi'),
('H', 'ᴇtɕʰ'),
('I', 'ᴀi'),
('J', 'dʑᴇ'),
('K', 'kʰᴇ'),
('L', 'ᴇl'),
('M', 'ᴇm'),
('N', 'ᴇn'),
('O', 'o'),
('P', 'pʰi'),
('Q', 'kʰiu'),
('R', 'ᴀl'),
('S', 'ᴇs'),
('T', 'tʰi'),
('U', 'ɦiu'),
('V', 'vi'),
('W', 'dᴀbɤliu'),
('X', 'ᴇks'),
('Y', 'uᴀi'),
('Z', 'zᴇ')
]]
def _number_to_shanghainese(num):
num = cn2an.an2cn(num).replace('一十', '十').replace('二十', '廿').replace('二', '两')
return re.sub(r'((?:^|[^三四五六七八九])十|廿)两', r'\1二', num)
def number_to_shanghainese(text):
return re.sub(r'\d+(?:\.?\d+)?', lambda x: _number_to_shanghainese(x.group()), text)
def latin_to_ipa(text):
for regex, replacement in _latin_to_ipa:
text = re.sub(regex, replacement, text)
return text
def shanghainese_to_ipa(text):
from text.mandarin import symbols_to_chinese
text = symbols_to_chinese(text)
text = number_to_shanghainese(text.upper())
text = converter.convert(text).replace('-', '').replace('$', ' ')
text = re.sub(r'[A-Z]', lambda x: latin_to_ipa(x.group()) + ' ', text)
text = re.sub(r'[、；：]', '，', text)
text = re.sub(r'\s*，\s*', ', ', text)
text = re.sub(r'\s*。\s*', '. ', text)
text = re.sub(r'\s*？\s*', '? ', text)
text = re.sub(r'\s*！\s*', '! ', text)
text = re.sub(r'\s*$', '', text)
return text
|