classifiers.py 文件源码

def __is_clause_pattern3(self, the_clause, seg_result):
        for a_phrase in self.__phrase_dict:
            keys = a_phrase.keys()
            to_compile = a_phrase["key"].replace("……", "[\u4e00-\u9fa5]*")

            if "start" in keys:
                to_compile = to_compile.replace("*", "{" + a_phrase["start"] + "," + a_phrase["end"] + "}")
            if "head" in keys:
                to_compile = a_phrase["head"] + to_compile

            match = re.compile(to_compile).search(the_clause)
            if match is not None:
                can_continue = True
                pos = [flag for word, flag in posseg.cut(match.group())]
                if "between_tag" in keys:
                    if a_phrase["between_tag"] not in pos and len(pos) > 2:
                        can_continue = False

                if can_continue:
                    for i in range(len(seg_result)):
                        if seg_result[i].word in match.group():
                            try:
                                if seg_result[i + 1].word in match.group():
                                    return self.__emotional_word_analysis(
                                        a_phrase["key"] + ":" + match.group(), a_phrase["value"],
                                        [x for x, y in seg_result], i)
                            except IndexError:
                                return self.__emotional_word_analysis(
                                    a_phrase["key"] + ":" + match.group(), a_phrase["value"],
                                    [x for x, y in seg_result], i)
        return ""