敏感词汇过滤(不区分大小写)

最近项目中,用户评论内容需要屏蔽敏感词汇,从网上总结以下方法,(不区分大小写,如想设置大小写敏感,可以把代码中content..toLowerCase()去掉).具体看代码:

1.读取敏感词汇文档

<span style="font-size:18px;">package com.blemall.wizlife.util.sensitive;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;

/**
* @Description: 初始化敏感词库，将敏感词加入到HashMap中，构建DFA算法模型
* @Project：test
* @version 1.0
*/
public class SensitiveWordInit {
private String ENCODING = "UTF-8";    //字符编码
@SuppressWarnings("rawtypes")
public HashMap sensitiveWordMap;

public SensitiveWordInit(){
super();
}

@SuppressWarnings("rawtypes")
public Map initKeyWord(){
try {
//读取敏感词库
Set<String> keyWordSet = readSensitiveWordFile();
//将敏感词库加入到HashMap中
addSensitiveWordToHashMap(keyWordSet);
//spring获取application，然后application.setAttribute("sensitiveWordMap",sensitiveWordMap);
} catch (Exception e) {
e.printStackTrace();
}
return sensitiveWordMap;
}

/**
* 读取敏感词库，将敏感词放入HashSet中，构建一个DFA算法模型：<br>
* 中 = {
*      isEnd = 0
*      国 = {<br>
*      	 isEnd = 1
*           人 = {isEnd = 0
*                民 = {isEnd = 1}
*                }
*           男  = {
*           	   isEnd = 0
*           		人 = {
*           			 isEnd = 1
*           			}
*           	}
*           }
*      }
*  五 = {
*      isEnd = 0
*      星 = {
*      	isEnd = 0
*      	红 = {
*              isEnd = 0
*              旗 = {
*                   isEnd = 1
*                  }
*              }
*      	}
*      }
* @param keyWordSet  敏感词库
* @version 1.0
*/
@SuppressWarnings({ "rawtypes", "unchecked" })
private void addSensitiveWordToHashMap(Set<String> keyWordSet) {
sensitiveWordMap = new HashMap(keyWordSet.size());     //初始化敏感词容器，减少扩容操作
String key = null;
Map nowMap = null;
Map<String, String> newWorMap = null;
//迭代keyWordSet
Iterator<String> iterator = keyWordSet.iterator();
while(iterator.hasNext()){
key = iterator.next();    //关键字
nowMap = sensitiveWordMap;
for(int i = 0 ; i < key.length() ; i++){
char keyChar = key.charAt(i);       //转换成char型
Object wordMap = nowMap.get(keyChar);       //获取

if(wordMap != null){        //如果存在该key，直接赋值
nowMap = (Map) wordMap;
}
else{     //不存在则，则构建一个map，同时将isEnd设置为0，因为他不是最后一个
newWorMap = new HashMap<String,String>();
newWorMap.put("isEnd", "0");     //不是最后一个
nowMap.put(keyChar, newWorMap);
nowMap = newWorMap;
}

if(i == key.length() - 1){
nowMap.put("isEnd", "1");    //最后一个
}
}
}
}

/**
* 读取敏感词库中的内容，将内容添加到set集合中
* @author chenming
* @date 2014年4月20日 下午2:31:18
* @return
* @version 1.0
* @throws Exception
*/
@SuppressWarnings("resource")
private Set<String> readSensitiveWordFile() throws Exception{
Set<String> set = null;
ClassLoader loader=SensitiveWordInit.class.getClassLoader();
URL url=loader.getResource("/SensitiveWord.txt");
String filePath =url.getPath();
File file=new File(filePath);
InputStreamReader read = new InputStreamReader(new FileInputStream(file),ENCODING);
try {
if(file.isFile() && file.exists()){      //文件流是否存在
set = new HashSet<String>();
BufferedReader bufferedReader = new BufferedReader(read);
String txt = null;
while((txt = bufferedReader.readLine()) != null){    //读取文件，将文件内容放入到set中
set.add(txt);
}
}
else{         //不存在抛出异常信息
throw new Exception("敏感词库文件不存在");
}
} catch (Exception e) {
throw e;
}finally{
read.close();     //关闭文件流
}
return set;
}
}
</span>

2.具体方法:

replaceSensitiveWord(String content(内容),int matchType(匹配规则),String replaceChar(替换词))

<span style="font-size:18px;">package com.blemall.wizlife.util.sensitive;

import org.springframework.stereotype.Component;

import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;

@Component
public class SensitivewordFilter {
@SuppressWarnings("rawtypes")
private Map sensitiveWordMap = null;
public static int minMatchTYpe = 1;      //最小匹配规则
public static int maxMatchType = 2;      //最大匹配规则

/**
* 构造函数，初始化敏感词库
*/
public SensitivewordFilter(){
sensitiveWordMap = new SensitiveWordInit().initKeyWord();
}

/**
* 判断文字是否包含敏感字符
* @param txt  文字
* @param matchType  匹配规则 1：最小匹配规则，2：最大匹配规则
* @return 若包含返回true，否则返回false
* @version 1.0
*/
public boolean isContaintSensitiveWord(String txt,int matchType){
boolean flag = false;
for(int i = 0 ; i < txt.length() ; i++){
int matchFlag = this.CheckSensitiveWord(txt, i, matchType); //判断是否包含敏感字符
if(matchFlag > 0){    //大于0存在，返回true
flag = true;
}
}
return flag;
}

/**
* 获取文字中的敏感词
* @param txt 文字
* @param matchType 匹配规则 1：最小匹配规则，2：最大匹配规则
* @return
* @version 1.0
*/
public Set<String> getSensitiveWord(String txt , int matchType){
Set<String> sensitiveWordList = new HashSet<String>();

for(int i = 0 ; i < txt.length() ; i++){
int length = CheckSensitiveWord(txt, i, matchType);    //判断是否包含敏感字符
if(length > 0){    //存在,加入list中
sensitiveWordList.add(txt.substring(i, i+length));
i = i + length - 1;    //减1的原因，是因为for会自增
}
}

return sensitiveWordList;
}

/**
* @date 2014年4月20日 下午5:12:07
* @param content
* @param matchType
* @param replaceChar 替换字符，默认*
* @version 1.0
*/
public String replaceSensitiveWord(String content,int matchType,String replaceChar){
String resultTxt = content;
Set<String> set = getSensitiveWord(content.toLowerCase(), matchType);//将输入内容先转换为小写,获取所有的敏感词
Iterator<String> iterator = set.iterator();
String word = null;
String replaceString = null;
while (iterator.hasNext()) {
word = iterator.next();
word="(?i)"+word;
replaceString = getReplaceChars(replaceChar, word.length());
resultTxt = resultTxt.replaceAll(word, replaceString);
}
return resultTxt;
}

/**
* 获取替换字符串
* @param replaceChar
* @param length
* @return
* @version 1.0
*/
private String getReplaceChars(String replaceChar,int length){
String resultReplace = replaceChar;
for(int i = 1 ; i < length ; i++){
resultReplace += replaceChar;
}

return resultReplace;
}

/**
* 检查文字中是否包含敏感字符，检查规则如下：<br>
* @param txt
* @param beginIndex
* @param matchType
* @return，如果存在，则返回敏感词字符的长度，不存在返回0
* @version 1.0
*/
@SuppressWarnings({ "rawtypes"})
public int CheckSensitiveWord(String txt,int beginIndex,int matchType){
boolean  flag = false;    //敏感词结束标识位：用于敏感词只有1位的情况
int matchFlag = 0;     //匹配标识数默认为0
char word = 0;
Map nowMap = sensitiveWordMap;
for(int i = beginIndex; i < txt.length() ; i++){
word = txt.charAt(i);
nowMap = (Map) nowMap.get(word);     //获取指定key
if(nowMap != null){     //存在，则判断是否为最后一个
matchFlag++;     //找到相应key，匹配标识+1
if("1".equals(nowMap.get("isEnd"))){       //如果为最后一个匹配规则,结束循环，返回匹配标识数
flag = true;       //结束标志位为true
if(SensitivewordFilter.minMatchTYpe == matchType){    //最小规则，直接返回,最大规则还需继续查找
break;
}
}
}
else{     //不存在，直接返回
break;
}
}
if(matchFlag < 2 || !flag){        //长度必须大于等于1，为词
matchFlag = 0;
}
return matchFlag;
}

}
</span>

附件:敏感词汇表(SensitiveWord.txt)