class DFA:
    """DFA 算法
       敏感字中“*”代表任意一個(gè)字符
    """

    def __init__(self, sensitive_words: list, skip_words: list):  # 對(duì)于敏感詞sensitive_words及無(wú)意義的詞skip_words可以通過(guò)數(shù)據(jù)庫(kù)、文件或者其他存儲(chǔ)介質(zhì)進(jìn)行保存
        self.state_event_dict = self._generate_state_event(sensitive_words)
        self.skip_words = skip_words

    def __repr__(self):
        return '{}'.format(self.state_event_dict)

    @staticmethod
    def _generate_state_event(sensitive_words) -> dict:
        state_event_dict = {}
        for word in sensitive_words:
            tmp_dict = state_event_dict
            length = len(word)
            for index, char in enumerate(word):
                if char not in tmp_dict:
                    next_dict = {'is_end': False}
                    tmp_dict[char] = next_dict
                    tmp_dict = next_dict
                else:
                    next_dict = tmp_dict[char]
                    tmp_dict = next_dict
                if index == length - 1:
                    tmp_dict['is_end'] = True
        return state_event_dict

    def match(self, content: str):
        match_list = []
        state_list = []
        temp_match_list = []

        for char_pos, char in enumerate(content):
            if char in self.skip_words:
                continue
            if char in self.state_event_dict:
                state_list.append(self.state_event_dict)
                temp_match_list.append({
                    "start": char_pos,
                    "match": ""
                })
            for index, state in enumerate(state_list):
                is_match = False
                state_char = None
                if '*' in state: # 對(duì)于一些敏感詞，比如大傻X，可能是大傻B，大傻×，大傻...，采用通配符*，一個(gè)*代表一個(gè)字符
                    state_list[index] = state['*']
                    state_char = state['*']
                    is_match = True
                if char in state:
                    state_list[index] = state[char]
                    state_char = state[char]
                    is_match = True
                if is_match:
                    if state_char["is_end"]:
                        stop = char_pos + 1
                        temp_match_list[index]['match'] = content[
                                                          temp_match_list[index]['start']:stop]
                        match_list.append(copy.deepcopy(temp_match_list[index]))
                        if len(state_char.keys()) == 1:
                            state_list.pop(index)
                            temp_match_list.pop(index)
                else:
                    state_list.pop(index)
                    temp_match_list.pop(index)
        for index, match_words in enumerate(match_list):
            print(match_words['start'])
        return match_list

if __name__ == '__main__':
    dfa = DFA(['我愛(ài)你', '我愛(ài)他', '我愛(ài)她', '我愛(ài)你呀', '我愛(ài)他呀', '我愛(ài)她呀', '我愛(ài)她啊'], skip_words=[])  # 暫時(shí)不配置skip_words
    print(dfa)

if __name__ == '__main__':
    dfa = DFA(['我愛(ài)你', '我愛(ài)他', '我愛(ài)她', '我愛(ài)你呀', '我愛(ài)他呀', '我愛(ài)她呀', '我愛(ài)她啊'], ['\n', '\r\n', '\r'])
    # print(dfa)
    print(dfa.match('白菊我愛(ài)你呀哈哈哈'))

if '*' in state: # 對(duì)于一些敏感詞，比如大傻X，可能是大傻B，大傻×，大傻...，采用通配符*，一個(gè)*代表一個(gè)字符
 state_list[index] = state['*']
 state_char = state['*']
 is_match = True

if __name__ == '__main__':
    dfa = DFA(['大傻*'], [])
    print(dfa)
    print(dfa.match('大傻X安樂(lè)飛大傻B'))

if __name__ == '__main__':
    dfa = DFA(['大傻*'], [])
    print(dfa)
    print(dfa.match('大%傻X安樂(lè)飛大&傻B'))

if __name__ == '__main__':
    dfa = DFA(['大傻*'], ['%', '&'])
    print(dfa)
    print(dfa.match('大%傻X安樂(lè)飛大&傻B'))