1、敏感詞
鏈接: https://pan.baidu.com/s/1vuM8DJ1jxVO7EOhKVqCL1A 提取碼: iv94 複製這段內容後打開百度網盤手機App,操作更方便哦
放到項目中的resources文件夾下即可
2.工具類
import org.springframework.util.ResourceUtils;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.*;
public class BadWordUtil2 {
public static String filePath = "classpath:dictionary.txt";//敏感詞庫文件路徑
public static Set<String> words;
public static Map<String,String> wordMap;
public static int minMatchTYpe = 1; //最小匹配規則
public static int maxMatchType = 2; //最大匹配規則
static{
BadWordUtil2.words = readTxtByLine(filePath);
addBadWordToHashMap(BadWordUtil2.words);
}
public static Set<String> readTxtByLine(String path){
Set<String> keyWordSet = new HashSet<String>();
BufferedReader reader=null;
String temp=null;
try{
File file= ResourceUtils.getFile(filePath);
if(!file.exists()){ //文件流是否存在
return keyWordSet;
}
//reader=new BufferedReader(new FileReader(file));這樣在web運行的時候,讀取會亂碼
reader=new BufferedReader(new InputStreamReader(new FileInputStream(file),"UTF-8"));
while((temp=reader.readLine())!=null){
keyWordSet.add(temp);
}
} catch(Exception e){
e.printStackTrace();
} finally{
if(reader!=null){
try{
reader.close();
}catch(Exception e){
e.printStackTrace();
}
}
}
return keyWordSet;
}
/**
* 檢查文字中是否包含敏感字符,檢查規則如下:<br>
* @param txt
* @param beginIndex
* @param matchType
* @return,如果存在,則返回敏感詞字符的長度,不存在返回0
* @version 1.0
*/
@SuppressWarnings({ "rawtypes"})
public static int checkBadWord(String txt,int beginIndex,int matchType){
boolean flag = false; //敏感詞結束標識位:用於敏感詞只有1位的情況
int matchFlag = 0; //匹配標識數默認爲0
char word = 0;
Map nowMap = wordMap;
for(int i = beginIndex; i < txt.length() ; i++){
word = txt.charAt(i);
nowMap = (Map) nowMap.get(word); //獲取指定key
if(nowMap != null){ //存在,則判斷是否爲最後一個
matchFlag++; //找到相應key,匹配標識+1
if("1".equals(nowMap.get("isEnd"))){ //如果爲最後一個匹配規則,結束循環,返回匹配標識數
flag = true; //結束標誌位爲true
if(minMatchTYpe == matchType){ //最小規則,直接返回,最大規則還需繼續查找
break;
}
}
}
else{ //不存在,直接返回
break;
}
}
/*“粉飾”匹配詞庫:“粉飾太平”竟然說是敏感詞
* “個人”匹配詞庫:“個人崇拜”竟然說是敏感詞
* if(matchFlag < 2 && !flag){
matchFlag = 0;
}*/
if(!flag){
matchFlag = 0;
}
return matchFlag;
}
/**
* 判斷文字是否包含敏感字符
* @param txt 文字
* @param matchType 匹配規則 1:最小匹配規則,2:最大匹配規則
* @return 若包含返回true,否則返回false
* @version 1.0
*/
public static boolean isContaintBadWord(String txt,int matchType){
boolean flag = false;
for(int i = 0 ; i < txt.length() ; i++){
int matchFlag = checkBadWord(txt, i, matchType); //判斷是否包含敏感字符
if(matchFlag > 0){ //大於0存在,返回true
flag = true;
}
}
return flag;
}
/**
* 替換敏感字字符
* @param txt
* @param matchType
* @param replaceChar 替換字符,默認*
* @version 1.0
*/
public static String replaceBadWord(String txt,int matchType,String replaceChar){
String resultTxt = txt;
Set<String> set = getBadWord(txt, matchType); //獲取所有的敏感詞
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;
}
/**
* 獲取文字中的敏感詞
* @param txt 文字
* @param matchType 匹配規則 1:最小匹配規則,2:最大匹配規則
* @return
* @version 1.0
*/
public static Set<String> getBadWord(String txt , int matchType){
Set<String> sensitiveWordList = new HashSet<String>();
for(int i = 0 ; i < txt.length() ; i++){
int length = checkBadWord(txt, i, matchType); //判斷是否包含敏感字符
if(length > 0){ //存在,加入list中
sensitiveWordList.add(txt.substring(i, i+length));
i = i + length - 1; //減1的原因,是因爲for會自增
}
}
return sensitiveWordList;
}
/**
* 獲取替換字符串
* @param replaceChar
* @param length
* @return
* @version 1.0
*/
private static String getReplaceChars(String replaceChar,int length){
String resultReplace = replaceChar;
for(int i = 1 ; i < length ; i++){
resultReplace += replaceChar;
}
return resultReplace;
}
/**
* TODO 將我們的敏感詞庫構建成了一個類似與一顆一顆的樹,這樣我們判斷一個詞是否爲敏感詞時就大大減少了檢索的匹配範圍。
* @param keyWordSet 敏感詞庫
*/
@SuppressWarnings({ "unchecked", "rawtypes" })
private static void addBadWordToHashMap(Set<String> keyWordSet) {
wordMap = new HashMap(keyWordSet.size()); //初始化敏感詞容器,減少擴容操作
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(); //關鍵字
nowMap = wordMap;
for(int i = 0 ; i < key.length() ; i++){
char keyChar = key.charAt(i); //轉換成char型
Object wordMap = nowMap.get(keyChar); //獲取
if(wordMap != null){ //如果存在該key,直接賦值
nowMap = (Map) wordMap;
}
else{ //不存在則,則構建一個map,同時將isEnd設置爲0,因爲他不是最後一個
newWorMap = new HashMap<String,String>();
newWorMap.put("isEnd", "0"); //不是最後一個
nowMap.put(keyChar, newWorMap);
nowMap = newWorMap;
}
if(i == key.length() - 1){
nowMap.put("isEnd", "1"); //最後一個
}
}
}
}
public static void main(String[] args) {
String string = "六合彩是違法的";
System.out.println(BadWordUtil2.replaceBadWord(string,minMatchTYpe,"*"));
}
}
需要jar包spring-core-5.1.3.RELEASE.jar