segment.py 文件源码

def get_word_list(self, text, lower=True, strip_stop_words=True, use_tag_filter=False):
        text = util.as_text(text)
        jieba_result = pseg.cut(text)

        if use_tag_filter:
            jieba_result = [
                w for w in jieba_result if w.flag in self.default_tag_filter]
        else:
            jieba_result = [w for w in jieba_result]

        word_list = [w.word.strip() for w in jieba_result if w.flag != 'x']
        word_list = [word for word in word_list if len(word) > 0]

        if lower:
            word_list = [word.lower() for word in word_list]

        if strip_stop_words:
            word_list = [word.strip()
                         for word in word_list if word.strip() not in self.stop_words]

        return word_list