File size: 1,560 Bytes
9c96d79 |
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 |
import re
import cn2an
import opencc
converter = opencc.OpenCC('chinese_dialect_lexicons/jyutjyu')
# List of (Latin alphabet, ipa) pairs:
_latin_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
('A', 'ei˥'),
('B', 'biː˥'),
('C', 'siː˥'),
('D', 'tiː˥'),
('E', 'iː˥'),
('F', 'e˥fuː˨˩'),
('G', 'tsiː˥'),
('H', 'ɪk̚˥tsʰyː˨˩'),
('I', 'ɐi˥'),
('J', 'tsei˥'),
('K', 'kʰei˥'),
('L', 'e˥llou˨˩'),
('M', 'ɛːm˥'),
('N', 'ɛːn˥'),
('O', 'ou˥'),
('P', 'pʰiː˥'),
('Q', 'kʰiːu˥'),
('R', 'aː˥lou˨˩'),
('S', 'ɛː˥siː˨˩'),
('T', 'tʰiː˥'),
('U', 'juː˥'),
('V', 'wiː˥'),
('W', 'tʊk̚˥piː˥juː˥'),
('X', 'ɪk̚˥siː˨˩'),
('Y', 'waːi˥'),
('Z', 'iː˨sɛːt̚˥')
]]
def number_to_cantonese(text):
return re.sub(r'\d+(?:\.?\d+)?', lambda x: cn2an.an2cn(x.group()), text)
def latin_to_ipa(text):
for regex, replacement in _latin_to_ipa:
text = re.sub(regex, replacement, text)
return text
def cantonese_to_ipa(text):
text = number_to_cantonese(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
|