敏感词库
资源: https://pan.baidu.com/s/1PKb2BhtVcxiF7cc70qy5Vg 提取码: n4be
敏感词库工具类(注意查看词库编码格式是否为utf-8,否则乱码)
package com.jpxx.pxxdj.common.util;
import java.io.*;
import java.util.*;
/**
* 敏感词库工具类
*/
public class BadWordUtils {
public static Set<String> words;
public static Map<String,String> wordMap;
/**
* 最小匹配规则
*/
public static int minMatchTYpe = 1;
/**
* 最大匹配规则
*/
public static int maxMatchType = 2;
static{
InputStream in = ClassLoader.getSystemResourceAsStream("mgck-master/keywords.txt");
BadWordUtils.words = readTxtByLine(in);
addBadWordToHashMap(BadWordUtils.words);
}
public static Set<String> readTxtByLine(InputStream in){
Set<String> keyWordSet = new HashSet<>();
BufferedReader in2=new BufferedReader(new InputStreamReader(in));
String y="";
while(true){
try {
if (!((y=in2.readLine())!=null)) break;
keyWordSet.add(y);
System.out.println(y);
} catch (IOException e) {
e.printStackTrace();
}
}
return keyWordSet;
}
/**
* 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 static int checkBadWord(String txt,int beginIndex,int matchType){
boolean flag = false;
int matchFlag = 0;
char word = 0;
Map nowMap = wordMap;
for(int i = beginIndex; i < txt.length() ; i++){
word = txt.charAt(i);
nowMap = (Map) nowMap.get(word);
if(nowMap != null){
matchFlag++;
if("1".equals(nowMap.get("isEnd"))){
flag = true;
if(minMatchTYpe == matchType){
break;
}
}
}
else{
break;
}
}
if(!flag){
matchFlag = 0;
}
return matchFlag;
}
/**
* 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 static boolean isContaintBadWord(String txt,int matchType){
boolean flag = false;
for(int i = 0 ; i < txt.length() ; i++){
int matchFlag = checkBadWord(txt, i, matchType);
if(matchFlag > 0){
flag = true;
}
}
return flag;
}
/**
* 替换敏感字字符
* @param txt
* @param matchType
* @param replaceChar 替换字符,默认*
* @version 1.0
*/
public static String replaceBadWord(String txt,int matchType,String replaceChar){
String resultTxt = txt;
Set<String> set = getBadWord(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 static Set<String> getBadWord(String txt , int matchType){
Set<String> sensitiveWordList = new HashSet();
for(int i = 0 ; i < txt.length() ; i++){
int length = checkBadWord(txt, i, matchType);
if(length > 0){
sensitiveWordList.add(txt.substring(i, i+length));
i = i + length - 1;
}
}
return sensitiveWordList;
}
/**
* 获取替换字符串
* @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;
}
@SuppressWarnings({ "unchecked", "rawtypes" })
private static void addBadWordToHashMap(Set<String> keyWordSet) {
wordMap = new HashMap(keyWordSet.size());
String key;
Map nowMap;
Map<String, String> newWorMap;
Iterator<String> iterator = keyWordSet.iterator();
while(iterator.hasNext()){
key = iterator.next();
nowMap = wordMap;
for(int i = 0 ; i < key.length() ; i++){
char keyChar = key.charAt(i);
Object wordMap = nowMap.get(keyChar);
if(wordMap != null){
nowMap = (Map) wordMap;
}
else{
newWorMap = new HashMap<>();
newWorMap.put("isEnd", "0");
nowMap.put(keyChar, newWorMap);
nowMap = newWorMap;
}
if(i == key.length() - 1){
nowMap.put("isEnd", "1");
}
}
}
}
}
过滤html标签工具类
package com.jpxx.pxxdj.common.util;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class HTMLUtils {
/**
* 过滤所有HTML 标签
* @param htmlStr
* @return
*/
public static String filterHTMLTag(String htmlStr) {
//定义HTML标签的正则表达式
String reg_html="<[^>]+>";
Pattern pattern=Pattern.compile(reg_html,Pattern.CASE_INSENSITIVE);
Matcher matcher=pattern.matcher(htmlStr);
htmlStr=matcher.replaceAll("");
return htmlStr;
}
/**
* 过滤标签,通过标签名
* @param htmlStr
* @param tagName
* @return
*/
public static String filterTagByName(String htmlStr,String tagName) {
String reg_html="<"+tagName+"[^>]*?>[\\s\\S]*?<\\/"+tagName+">";
Pattern pattern=Pattern.compile(reg_html,Pattern.CASE_INSENSITIVE);
Matcher matcher=pattern.matcher(htmlStr);
htmlStr=matcher.replaceAll(""); //过滤html标签
return htmlStr;
}
/**
* 过滤标签上的 style 样式
* @param htmlStr
* @return
*/
public static String filterHTMLTagInStyle(String htmlStr) {
String reg_html="style=('|\")(.*?)('|\")";
Pattern pattern=Pattern.compile(reg_html,Pattern.CASE_INSENSITIVE);
Matcher matcher=pattern.matcher(htmlStr);
htmlStr=matcher.replaceAll(""); //过滤html标签
return htmlStr;
}
/**
* 替换表情
* @param htmlStr
* @return
*/
public static String replayFace(String htmlStr) {
String reg_html="\\[em_\\d{1,}\\]";
Pattern pattern =Pattern.compile(reg_html,Pattern.CASE_INSENSITIVE);
Matcher matcher=pattern.matcher(htmlStr);
if(matcher.find()) {
matcher.reset();
while(matcher.find()) {
String num = matcher.group(0);
String number=num.substring(num.lastIndexOf('_')+1, num.length()-1);
htmlStr = htmlStr.replace(num, "<img src='/face/arclist/"+number+".gif' border='0' />");
}
}
return htmlStr;
}
}