train_and_predict.py 文件源码

def mycut(s):
    result = []
    j = 0
    s = re_replace.sub(' ', s)
    for i in not_cuts.finditer(s):
        result.extend(jieba.lcut(s[j:i.start()], HMM=False))
        if s[i.start()] in [u'?', u'“']:
            result.extend([s[i.start()], s[i.start()+1:i.end()-1], s[i.end()-1]])
        else:
            result.append(s[i.start():i.end()])
        j = i.end()
    result.extend(jieba.lcut(s[j:], HMM=False))
    return result