import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.*;
public class SensitivewordFilter {
@SuppressWarnings("rawtypes")
private static 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
static {
Set<String> set = null;
InputStreamReader read = null;
try {
read = new InputStreamReader(SensitivewordFilter.class.getResourceAsStream("/CensorWords.txt"),"UTF-8");
if (read != null) {
set = new HashSet<>();
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
System.out.println(txt);
set.add(txt);
}
}
sensitiveWordMap = new HashMap(set.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 = set.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);
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) {
nowMap.put("isEnd", "1"); //最后一个
}
}
}
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
if(read!=null){
read.close();
}
}catch (Exception e){
}
}
}
/**
* 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);
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
* @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);
if (length > 0) {
sensitiveWordList.add(txt.substring(i, i + length));
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*
* @version 1.0
*/
public String replaceSensitiveWord(String txt, int matchType, String replaceChar) {
String resultTxt = txt;
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
* @return
* @author chenming
* @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);
if (nowMap != null) {
matchFlag++;
if ("1".equals(nowMap.get("isEnd"))) {
flag = true;
if (SensitivewordFilter.minMatchTYpe == matchType) {
break;
}
}
} else {
break;
}
}
if (matchFlag < 2 || !flag) {
matchFlag = 0;
}
return matchFlag;
}
/**
* 内容测试
*
* @param args
*/
public static void main(String[] args) {
SensitivewordFilter filter = new SensitivewordFilter();
// System.out.println("敏感词的数量：" + filter.sensitiveWordMap.size());
String string = "腐败贪污";
// System.out.println("待检测语句字数：" + string.length());
// long beginTime = System.currentTimeMillis();
Set<String> set = filter.getSensitiveWord(string, 1);
// long endTime = System.currentTimeMillis();
System.out.println("语句中包含敏感词的个数为：" + set.size() + "。包含：" + set);
// System.out.println("总共消耗时间为：" + (endTime - beginTime));
String s = filter.replaceSensitiveWord(string, 1, "*");
System.out.println("前:" + string);
System.out.println("后:" + s);
}
}
注意: CensorWords.txt文件 我是放在和application.properties 相同的位置
敏感词库链接：https://pan.baidu.com/s/1xKK7oTP8k47qA1gBm2uUHg
提取码：5gf7 (敏感词库可以自行添加修改)