java基于dfa实现敏感词过滤
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,它是是通过event和当前的state得到下一个state,即event+state=nextstate。
- 准备词库
台独
略。。。。。
可下载开源的词库 词库
- 初始化敏感词库
package cn.pconline.pcloud.admin.dfa;
import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.*;
/**
* @Description 初始化敏感词库,将敏感词加入到HashMap中,构建DFA算法模型
* @Author jie.zhao
* @Date 2020/3/24 19:11
*/
public class SensitiveWordInit {
private String ENCODING = "UTF8";
private String filePath;
public HashMap sensitiveWordMap;
public SensitiveWordInit(String filePath) {
this.filePath = filePath;
}
/**
* 初始化词库
* @return
*/
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);
} 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
* 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
*/
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;
Map nowMap;
Map<String, String> newWorMap;
//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);
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) {
//最后一个
nowMap.put("isEnd", "1");
}
}
}
}
/**
* 读取敏感词库中的内容,将内容添加到set集合中
*
* @return
* @throws Exception
*/
private Set<String> readSensitiveWordFile() throws Exception {
Set<String> set;
InputStream inputStream = new FileInputStream(filePath);
InputStreamReader read = null;
try {
if (inputStream != null) {
//文件流是否存在
read = new InputStreamReader(inputStream, ENCODING);
set = new HashSet<>();
BufferedReader bufferedReader = new BufferedReader(read);
String txt;
while ((txt = bufferedReader.readLine()) != null) {
//读取文件,将文件内容放入到set中
set.add(txt);
}
} else {
throw new Exception("敏感词库文件不存在");
}
} catch (Exception e) {
throw e;
} finally {
if(read!=null){
//关闭文件流
read.close();
}
}
return set;
}
}
- 敏感词过滤
package cn.pconline.pcloud.admin.dfa;
import org.springframework.core.io.ClassPathResource;
import org.springframework.core.io.Resource;
import java.io.File;
import java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;
/**
* @Description Java实现敏感词过滤:http://blog.csdn.net/chenssy/article/details/26961957
* @Author jie.zhao
* @Date 2020/3/24 19:11
*/
public class SensitivewordFilter {
private Map sensitiveWordMap;
public static int minMatchTYpe = 1; //最小匹配规则
public static int maxMatchType = 2; //最大匹配规则
private static SensitivewordFilter instance = new SensitivewordFilter();
/**
* 私有化构造方法
* Words.txt词库文件在resource下
*/
private SensitivewordFilter() {
try {
Resource resource = new ClassPathResource("Words.txt");
File file = resource.getFile();
sensitiveWordMap = new SensitiveWordInit(file.getAbsolutePath()).initKeyWord();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 单例模式只初始化一次
* @return
*/
public static SensitivewordFilter getInstance() {
return instance;
}
/**
* 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);
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
* 比如说我是中国人,铭感词库里面有“中国”、“中国人”,最小规则就变成了:我是**人、最大规则就是:我是***。
* 所以最小规则就是:找到敏感词就结束,最大规则就是:找到最底层的那个敏感词。两个深度不一样!
* @return
*/
public Set<String> getSensitiveWord(String txt, int matchType) {
Set<String> sensitiveWordList = new HashSet<>();
for (int i = 0; i < txt.length(); i++) {
//判断是否包含敏感字符
int length = CheckSensitiveWord(txt, i, matchType);
if (length > 0) {
//存在,加入list中
sensitiveWordList.add(txt.substring(i, i + length));
//减1的原因,是因为for会自增
i = i + length - 1;
}
}
return sensitiveWordList;
}
/**
* 替换敏感字字符
*
* @param txt
* @param matchType
* @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;
String replaceString;
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
* @return
*/
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
*/
@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);
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;
}
public static void main(String[] args) {
long beginTime = System.currentTimeMillis();
SensitivewordFilter filter = SensitivewordFilter.getInstance();
System.out.println("敏感词的数量:" + filter.sensitiveWordMap.size());
String string = "台独积极分子";
System.out.println("被检测字符串长度:" + string.length());
String newStr = filter.replaceSensitiveWord(string, 2, "*");
long endTime = System.currentTimeMillis();
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);
System.out.println("总共耗时:" + (endTime - beginTime) + "ms");
System.out.println("替换后的字符串为:
" + newStr);
}
}
- 运行结果
敏感词的数量:1894
被检测字符串长度:6
语句中包含敏感词的个数为:1。包含:[台独]
总共耗时:149ms
替换后的字符串为:
**积极分子