摘要：
returnlevel=self.keyword_chainsforiinrange（len（chars））：len（char））：编码='utf-8'）asf:step_ins+=1ifself.delimitioninlevel[char]：ret.append（repl*step_ins）start+=step_ins-1breakelse：
原文：https://blog.csdn.net/u013421629/article/details/83178970
一道bat面试题：快速替换10亿条标题中的5万个敏感词，有哪些解决思路？
有十亿个标题，存在一个文件中，一行一个标题。有5万个敏感词，存在另一个文件。写一个程序过滤掉所有标题中的所有敏感词，保存到另一个文件中。
1、DFA过滤敏感词算法
在实现文字过滤的算法中，DFA是比较好的实现算法。DFA即Deterministic Finite Automaton，也就是确定有穷自动机。
算法核心是建立了以敏感词为基础的许多敏感词树。
python 实现DFA算法：
# -*- coding:utf-8 -*-
import time
time1=time.time()
# DFA算法
class DFAFilter():
def __init__(self):
self.keyword_chains = {}
self.delimit = 'x00'
def add(self, keyword):
keyword = keyword.lower()
chars = keyword.strip()
if not chars:
return
level = self.keyword_chains
for i in range(len(chars)):
if chars[i] in level:
level = level[chars[i]]
else:
if not isinstance(level, dict):
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
def parse(self, path):
with open(path,encoding='utf-8') as f:
for keyword in f:
self.add(str(keyword).strip())
def filter(self, message, repl="*"):
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]
else:
ret.append(repl * step_ins)
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="F:/文本反垃圾算法/sensitive_words.txt"
gfw.parse(path)
text="新疆骚乱苹果新品发布会雞八"
result = gfw.filter(text)
print(text)
print(result)
time2 = time.time()
print('总共耗时：' + str(time2 - time1) + 's')
运行效果：
E:laidefapython.exe "E:/Program Files/pycharmproject/敏感词过滤算法/敏感词过滤算法DFA.py"
新疆骚乱苹果新品发布会雞八
****苹果新品发布会**
总共耗时：0.0010344982147216797s
Process finished with exit code 0
2、AC自动机过滤敏感词算法
AC自动机：一个常见的例子就是给出n个单词，再给出一段包含m个字符的文章，让你找出有多少个单词在文章里出现过。
简单地讲，AC自动机就是字典树+kmp算法+失配指针
# -*- coding:utf-8 -*-
import time
time1=time.time()
# AC自动机算法
class node(object):
def __init__(self):
self.next = {}
self.fail = None
self.isWord = False
self.word = ""
class ac_automation(object):
def __init__(self):
self.root = node()
# 添加敏感词函数
def addword(self, word):
temp_root = self.root
for char in word:
if char not in temp_root.next:
temp_root.next[char] = node()
temp_root = temp_root.next[char]
temp_root.isWord = True
temp_root.word = word
# 失败指针函数
def make_fail(self):
temp_que = []
temp_que.append(self.root)
while len(temp_que) != 0:
temp = temp_que.pop(0)
p = None
for key,value in temp.next.item():
if temp == self.root:
temp.next[key].fail = self.root
else:
p = temp.fail
while p is not None:
if key in p.next:
temp.next[key].fail = p.fail
break
p = p.fail
if p is None:
temp.next[key].fail = self.root
temp_que.append(temp.next[key])
# 查找敏感词函数
def search(self, content):
p = self.root
result = []
currentposition = 0
while currentposition < len(content):
word = content[currentposition]
while word in p.next == False and p != self.root:
p = p.fail
if word in p.next:
p = p.next[word]
else:
p = self.root
if p.isWord:
result.append(p.word)
p = self.root
currentposition += 1
return result
# 加载敏感词库函数
def parse(self, path):
with open(path,encoding='utf-8') as f:
for keyword in f:
self.addword(str(keyword).strip())
# 敏感词替换函数
def words_replace(self, text):
"""
:param ah: AC自动机
:param text: 文本
:return: 过滤敏感词之后的文本
"""
result = list(set(self.search(text)))
for x in result:
m = text.replace(x, '*' * len(x))
text = m
return text
if __name__ == '__main__':
ah = ac_automation()
path='F:/文本反垃圾算法/sensitive_words.txt'
ah.parse(path)
text1="新疆骚乱苹果新品发布会雞八"
text2=ah.words_replace(text1)
print(text1)
print(text2)
time2 = time.time()
print('总共耗时：' + str(time2 - time1) + 's')E:laidefapython.exe "E:/Program Files/pycharmproject/敏感词过滤算法/AC自动机过滤敏感词算法.py"
新疆骚乱苹果新品发布会雞八
****苹果新品发布会**
总共耗时：0.0010304450988769531s
Process finished with exit code 0
3、java 实现参考链接：
https://www.cnblogs.com/AlanLee/p/5329555.html
4、敏感词生成
# -*- coding:utf-8 -*-
path = 'F:/文本反垃圾算法/sensitive_worlds7.txt'
from 敏感词过滤算法.langconv import *
import pandas as pd
import pypinyin
# 文本转拼音
def pinyin(text):
"""
:param text: 文本
:return: 文本转拼音
"""
gap = ' '
piny = gap.join(pypinyin.lazy_pinyin(text))
return piny
# 繁体转简体
def tradition2simple(text):
"""
:param text: 要过滤的文本
:return: 繁体转简体函数
"""
line = Converter('zh-hans').convert(text)
return line
data=pd.read_csv(path,sep=' ')
chinise_lable=[]
chinise_type=data['type']
for i in data['lable']:
line=tradition2simple(i)
chinise_lable.append(line)
chg_data=pd.DataFrame({'lable':chinise_lable,'type':chinise_type})
eng_lable=[]
eng_type=data['type']
for i in data['lable']:
# print(i)
piny=pinyin(i)
# print(piny)
eng_lable.append(piny)
eng_data=pd.DataFrame({'lable':eng_lable,'type':eng_type})
# print(eng_data)
# 合并
result=chg_data.append(eng_data,ignore_index=True)
# 数据框去重
res = result.drop_duplicates()
print(res)
# 输出
res.to_csv('F:/文本反垃圾算法/中英混合的敏感词10.txt',header=True,index=False,sep=' ',encoding='utf-8')