java中过滤敏感词

java中过滤敏感词并且将敏感词替换成*号

参考文章：https://www.cnblogs.com/zyguo/p/4705086.html

目录结构：

SensitiveWordsInit 类

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

public class SensitiveWordsInit {
    //字符编码
	private String ENCODING = "GBK";
	@SuppressWarnings("rawtypes")
	public HashMap sensitiveWordMap;
	public SensitiveWordsInit(){
		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;
	}

	@SuppressWarnings({ "rawtypes", "unchecked" })
	private void addSensitiveWordToHashMap(Set<String> keyWordSet) {
	    //初始化敏感词容器，减少扩容操作
		sensitiveWordMap = new HashMap(keyWordSet.size());
		String key = null;  
		Map nowMap = null;
		Map<String, String> newWorMap = null;
		//迭代keyWordSet
		Iterator<String> iterator = keyWordSet.iterator();
		while(iterator.hasNext()){
			//关键字
			key = iterator.next();
			nowMap = sensitiveWordMap;
			for(int i = 0 ; i < key.length() ; i++){
		      	//转换成char型
				char keyChar = key.charAt(i); 
				//获取
				Object wordMap = nowMap.get(keyChar);
				//如果存在该key，直接赋值
				if(wordMap != null){
					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>();
			    	//不是最后一个
					newWorMap.put("isEnd", "0"); 
					nowMap.put(keyChar, newWorMap);
					nowMap = newWorMap;
				}
				if(i == key.length() - 1){
		    		//最后一个
					nowMap.put("isEnd", "1");
				}
			}
		}
	}

	@SuppressWarnings("resource")
	private Set<String> readSensitiveWordFile() throws Exception{
		Set<String> set = null;
		//获取敏感词库的路径
		String filePath = getClass().getClassLoader().getResource("mgck.txt").getPath();
		//读取文件
		File file = new File(filePath);
		InputStreamReader read = new InputStreamReader(new FileInputStream(file),ENCODING);
		try {
			if(file.isFile() && file.exists()){      
				set = new HashSet<String>();
				BufferedReader bufferedReader = new BufferedReader(read);
				String txt = null;
				//读取文件，将文件内容放入到set中
				while((txt = bufferedReader.readLine()) != null){
					set.add(txt);
			    }
			}else{
				throw new Exception("敏感词库文件不存在");
			}
		} catch (Exception e) {
			throw e;
		}finally{
			//关闭文件流
			read.close();
		}
		return set;
	}
}

SensitiveWordsUtil 类

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

public class SensitiveWordsUtil {
	@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 SensitiveWordsUtil(){
		sensitiveWordMap = new SensitiveWordsInit().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
	 */
	public boolean isContaintSensitiveWord(String txt,int matchType){
		boolean flag = false;
		for(int i = 0 ; i < txt.length() ; i++){
			//判断是否包含敏感字符
			int matchFlag = this.CheckSensitiveWord(txt, i, matchType);
			//大于0存在，返回true
			if(matchFlag > 0){ 
				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
	 */
	public Set<String> getSensitiveWord(String txt , int matchType){
		Set<String> sensitiveWordList = new HashSet<String>();
		for(int i = 0 ; i < txt.length() ; i++){
		    //判断是否包含敏感字符
			int length = CheckSensitiveWord(txt, i, matchType);
			//存在,加入list中
			if(length > 0){
				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;
	}
	
	/**
	 * 替换敏感字字符
	 * @param replaceChar 替换字符，默认*
	 */
	public String replaceSensitiveWord(String txt,int matchType,String replaceChar){
		String resultTxt = txt;
		//获取所有的敏感词
		Set<String> set = getSensitiveWord(txt, matchType);     
		Iterator<String> iterator = set.iterator();
		String word = null;
		String replaceString = null;
		while (iterator.hasNext()) {
			word = iterator.next();
			replaceString = getReplaceChars(replaceChar, word.length());
			resultTxt = resultTxt.replaceAll(word, replaceString);
		}
		return resultTxt;
	}
	
	/**
	 * 获取替换字符串
	 * @param replaceChar
	 * @param length
	 */
	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：
	 * @return 如果存在，则返回敏感词字符的长度，不存在返回0
	 */
	@SuppressWarnings({ "rawtypes"})
	public int CheckSensitiveWord(String txt,int beginIndex,int matchType){
		//敏感词结束标识位：用于敏感词只有1位的情况
		boolean  flag = false;    
		//匹配标识数默认为0
		int matchFlag = 0;     
		char word = 0;
		Map nowMap = sensitiveWordMap;
		for(int i = beginIndex; i < txt.length() ; i++){
			word = txt.charAt(i);
			//获取指定key
			nowMap = (Map) nowMap.get(word);
			//存在，则判断是否为最后一个
			if(nowMap != null){  
				//找到相应key，匹配标识+1 
				matchFlag++;     
				//如果为最后一个匹配规则,结束循环，返回匹配标识数
				if("1".equals(nowMap.get("isEnd"))){ 
					//结束标志位为true
					flag = true; 
					//最小规则，直接返回,最大规则还需继续查找
					if(SensitiveWordsUtil.minMatchTYpe == matchType){    
						break;
					}
				}
			}else{     //不存在，直接返回
				break;
			}
		}
		//长度必须大于等于1，为词 
		if(matchFlag < 2 || !flag){ 
			matchFlag = 0;
		}
		return matchFlag;
	}
	
	public static void main(String[] args) {
		SensitiveWordsUtil filter = new SensitiveWordsUtil();
		@SuppressWarnings("resource")
		Scanner sc = new Scanner(System.in);
		System.out.println("敏感词的数量：" + filter.sensitiveWordMap.size());
		System.out.print("输入你要查询的内容：");
		String string = sc.nextLine();
		
		Set<String> set = filter.getSensitiveWord(string, 1);
		System.out.println("语句中包含敏感词的个数为：" + set.size() + "。包含：" + set);
		string = filter.replaceSensitiveWord(string, minMatchTYpe, "*");
		System.out.println("和谐后的内容："+string);
	}
}

结果如图：