当前位置:网站首页>Python filtering sensitive word records

Python filtering sensitive word records

2020-11-06 01:28:10 Elementary school students in IT field

sketch :

On sensitive word filtering can be seen as a text anti spam algorithm , for example
subject : Sensitive word text file filtered_words.txt, When the user enters sensitive words , Then use asterisk * Replace , For example, when the user enters 「 Beijing is a good city 」, Has become a 「** It's a good city 」
Code :

#coding=utf-8
def filterwords(x):
    with open(x,'r') as f:
        text=f.read()
    print text.split('\n')
    userinput=raw_input('myinput:')
    for i in text.split('\n'):
        if i in userinput:
            replace_str='*'*len(i.decode('utf-8'))
            word=userinput.replace(i,replace_str)
            return word

print filterwords('filtered_words.txt')

Another example is the anti yellow series :

 Develop sensitive word filters , Prompt users to enter comments , If the user's input contains special characters :
 List of sensitive words  li = [" Aoi Sora "," Tokyo fever ",” Wutenglan ”,” Yui Hatano ”]
 Replace the sensitive words in the user's input with ***, And add it to a list ; If the user's input doesn't have sensitive words , Add it directly to the list above .
content = input(' Please enter your content :')
li = [" Aoi Sora "," Tokyo fever "," Wutenglan "," Yui Hatano "]
i = 0
while i < 4:
    for li[i] in content:
        li1 = content.replace(' Aoi Sora ','***')
        li2 = li1.replace(' Tokyo fever ','***')
        li3 = li2.replace(' Wutenglan ','***')
        li4 = li3.replace(' Yui Hatano ','***')
    else:
        pass
    i += 1

 Insert picture description here
Practical cases :
Together bat Interview questions : Quick replacement 10 One hundred million titles 5 Ten thousand sensitive words , What are the solutions ?
There are a billion titles , In a file , One title per line . Yes 5 Ten thousand sensitive words , There is another file . Write a program to filter out all sensitive words in all headings , Save to another file .

1、DFA Filter sensitive words algorithm

In the algorithm of text filtering ,DFA Is a better algorithm .DFA namely Deterministic Finite Automaton, That is to say, definite finite automata .
The core of the algorithm is to establish many sensitive word trees based on sensitive words .
python Realization DFA Algorithm :

# -*- coding:utf-8 -*-

import time
time1=time.time()

# DFA Algorithm 
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:/ Text anti spam algorithm /sensitive_words.txt"
    gfw.parse(path)
    text=" Xinjiang riot apple new product launch "
    result = gfw.filter(text)

    print(text)
    print(result)
    time2 = time.time()
    print(' The total time is :' + str(time2 - time1) + 's')

Running effect :

 Xinjiang riot apple new product launch 
**** Apple launch **
 The total time is :0.0010344982147216797s

2、AC Automata filter sensitive words algorithm

AC automata : A common example is to give n Word , Give me another paragraph that contains m One character article , Let you find out how many words appear in the article .
Simply speak ,AC Automata is a dictionary tree +kmp Algorithm + Mismatch pointer

# -*- coding:utf-8 -*-

import time
time1=time.time()

# AC Automata algorithm 
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()

    #  Add sensitive word function 
    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

    #  Failed pointer function 
    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])

    #  Find sensitive word functions 
    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

    #  Load sensitive lexicon functions 
    def parse(self, path):
        with open(path,encoding='utf-8') as f:
            for keyword in f:
                self.addword(str(keyword).strip())

    #  The substitution function of sensitive words 
    def words_replace(self, text):
        """
        :param ah: AC automata 
        :param text:  Text 
        :return:  Filter the text after sensitive words 
        """
        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:/ Text anti spam algorithm /sensitive_words.txt'
    ah.parse(path)
    text1=" Xinjiang riot apple new product launch "
    text2=ah.words_replace(text1)

    print(text1)
    print(text2)

    time2 = time.time()
    print(' The total time is :' + str(time2 - time1) + 's')

Running results :

 Xinjiang riot apple new product launch 
**** Apple launch **
 The total time is :0.0010304450988769531s
 WeChat ID

版权声明
本文为[Elementary school students in IT field]所创,转载请带上原文链接,感谢