File size: 1,063 Bytes
f8a0cc5 |
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 |
import re
import opencc
dialects = {'SZ': 'suzhou', 'WX': 'wuxi', 'CZ': 'changzhou', 'HZ': 'hangzhou',
'SX': 'shaoxing', 'NB': 'ningbo', 'JJ': 'jingjiang', 'YX': 'yixing',
'JD': 'jiading', 'ZR': 'zhenru', 'PH': 'pinghu', 'TX': 'tongxiang',
'JS': 'jiashan', 'HN': 'xiashi', 'LP': 'linping', 'XS': 'xiaoshan',
'FY': 'fuyang', 'RA': 'ruao', 'CX': 'cixi', 'SM': 'sanmen',
'TT': 'tiantai', 'WZ': 'wenzhou', 'SC': 'suichang', 'YB': 'youbu'}
converters = {}
for dialect in dialects.values():
try:
converters[dialect] = opencc.OpenCC(dialect)
except:
pass
def ngu_dialect_to_ipa(text, dialect):
dialect = dialects[dialect]
text = converters[dialect].convert(text).replace('-','').replace('$',' ')
text = re.sub(r'[、；：]', '，', text)
text = re.sub(r'\s*，\s*', ', ', text)
text = re.sub(r'\s*。\s*', '. ', text)
text = re.sub(r'\s*？\s*', '? ', text)
text = re.sub(r'\s*！\s*', '! ', text)
text = re.sub(r'\s*$', '', text)
return text
|