utils.py 文件源码

def preprocess_WithSpeech(stopword_file, news):
    content = jieba.posseg.cut(news)  # ??????

    content = filter(lambda x: hasMeaningfulWords(x), content)  # ???????????
    content = [i.word for i in content]
    content = filter(lambda x: len(x) > 1, content)  # ?????

    stopw = [line.strip().decode('utf-8') for line in open(stopword_file).readlines()]

    parsed = set(content) - set(stopw)
    return ' '.join(parsed)