DFA算法进行敏感词过滤

1.新建敏感词文本new_adress.txt，进行添加敏感词

 

 2.代码

# -*- coding:utf-8 -*-
import time

time1 = time.time()
"""
DFA算法：
它的基本思想是基于状态转移来检索敏感词，只需要扫描一次待检测文本，就能对所有敏感词进行检测
"""

# DFA算法
class DFAFilter(object):
    def __init__(self):
        self.keyword_chains = {}  # 关键词链表
        self.delimit = '\x00'  # 限定
    #将敏感词内容添加关键词链表
    def add(self, keyword):
        keyword = keyword.lower()  # 关键词英文变为小写
        chars = keyword.strip()  # 关键字去除首尾空格和换行
        if not chars:  # 如果关键词为空直接返回
            return
        level = self.keyword_chains
        # 遍历关键字的每个字
        for i in range(len(chars)):
            # 如果这个字已经存在字符链的key中就进入其子字典
            if chars[i] in level:
                level = level[chars[i]]
                print(level)
            else:
                #isinstance(level, dict)判断是否是一个类型，是返回True
                if not isinstance(level, dict):
                    print("print(level)",level)
                    break
                for j in range(i, len(chars)):
                    level[chars[j]] = {}
                    last_level, last_char = level, chars[j]
                    level = level[chars[j]]
                last_level[last_char] = {self.delimit: 0}
                break
        if i == len(chars) - 1:
            level[self.delimit] = 0
    #读取敏感词内容
    def parse(self, path):
        with open(path, encoding='utf-8') as f:
            for keyword in f:
                self.add(str(keyword).strip())
        # print(self.keyword_chains)
    #过滤关键词
    def filter(self, message, repl="*"):
        print(self.keyword_chains)
        message = message.lower()
        ret = []
        start = 0
        while start < len(message):
            level = self.keyword_chains
            step_ins = 0
            for char in message[start:]:
                if char in level:
                    step_ins += 1
                    if self.delimit not in level[char]:
                        level = level[char]
                        # print("no",level)
                    else:
                        ret.append(repl * step_ins)
                        # print(ret)
                        start += step_ins - 1
                        break
                else:
                    ret.append(message[start])
                    break
            else:
                ret.append(message[start])
            start += 1

        return ''.join(ret)


if __name__ == "__main__":
    gfw = DFAFilter()
    path='new_adress.txt'
    gfw.parse(path)
    text = "安徽省合肥市蜀山区"
    result = gfw.filter(text)
    print(result)
    time2 = time.time()
    print('总共耗时：' + str(time2 - time1) + 's')

3.运行获取的结果