简易敏感词工具
package com.benwunet.bks.util;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;
import java.util.Map;
public class SensitiveFilterService {
private Map sensitiveWordMap = null;
// 最小匹配规则
public static int minMatchType = 1;
// 最大匹配规则
public static int maxMatchType = 2;
// 单例
private static SensitiveFilterService instance = null;
// 构造函数，初始化敏感词库
private SensitiveFilterService() {
sensitiveWordMap = new SensitiveWordInit().initKeyWord();
}
// 获取单例
public static SensitiveFilterService getInstance() {
if (null == instance) {
instance = new SensitiveFilterService();
}
return instance;
}
// 获取文字中的敏感词
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));
// 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
* @return
*/
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
* @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>
* 如果存在，则返回敏感词字符的长度，不存在返回0
*
* @param txt
* @param beginIndex
* @param matchType
* @return
*/
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;
Map nowMap = sensitiveWordMap;
for (int i = beginIndex; i < txt.length(); i++) {
char 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 (SensitiveFilterService.minMatchType == matchType) {
break;
}
}
} else {
// 不存在，直接返回
break;
}
}
if (SensitiveFilterService.maxMatchType == matchType) {
//长度必须大于等于1，为词
if (matchFlag < 2 || !flag) {
matchFlag = 0;
}
}
if (SensitiveFilterService.minMatchType == matchType) {
//长度必须大于等于1，为词
if (matchFlag < 2 && !flag) {
matchFlag = 0;
}
}
return matchFlag;
}
}
package com.benwunet.bks.util;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.*;
/**
* @description 屏蔽敏感词初始化
**/
public class SensitiveWordInit {
// 字符编码
private String ENCODING = "UTF-8";
// 初始化敏感字库
public Map initKeyWord() {
// 读取敏感词库 ,存入Set中
Set<String> wordSet = readSensitiveWordFile();
// 将敏感词库加入到HashMap中//确定有穷自动机DFA
return addSensitiveWordToHashMap(wordSet);
}
/**
* * 读取敏感词库，将敏感词放入HashSet中，构建一个DFA算法模型：<br>
* * 中 = {
* * isEnd = 0
* * 国 = {
* * 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 敏感词库
*
*/
/**
* 读取敏感词库 ,存入HashMap中
* @return
*/
private Set<String> readSensitiveWordFile() {
Set<String> wordSet = null;
// app为项目地址
/*
* String app = System.getProperty("user.dir"); System.out.println(app);
* URL resource = Thread.currentThread().getContextClassLoader()
* .getResource("/"); String path = resource.getPath().substring(1);
* System.out.println(path); File file = new File(path +
* "censorwords.txt");
*/
File file = null;
try {
//通过url获取敏感词库
file = UrlToFileUtil.urlToFile("https://***********/phic.txt");
// file = new File(
// "D:\\JAVA\\bks_v2.2\\bks\\project\\bks-project\\bks-applet-center\\src\\main\\resources\\phic.txt");
}catch (Exception e) {
e.printStackTrace();
}
try {
// 读取文件输入流
InputStreamReader read = new InputStreamReader(new FileInputStream(file), ENCODING);
// 文件是否是文件 和 是否存在
if (file.isFile() && file.exists()) {
wordSet = new HashSet<String>();
// StringBuffer sb = new StringBuffer();
// BufferedReader是包装类，先把字符读到缓存里，到缓存满了，再读入内存，提高了读的效率。
BufferedReader br = new BufferedReader(read);
String txt = null;
// 读取文件，将文件内容放入到set中
while ((txt = br.readLine()) != null) {
wordSet.add(txt);
}
br.close();
/*
* String str = sb.toString(); String[] ss = str.split("，"); for
* (String s : ss) { wordSet.add(s); }
*/
}
// 关闭文件流
read.close();
} catch (Exception e) {
e.printStackTrace();
}
return wordSet;
}
/**
* 将HashSet中的敏感词,存入HashMap中
* @param wordSet
* @return
*/
private Map addSensitiveWordToHashMap(Set<String> wordSet) {
// 初始化敏感词容器，减少扩容操作
Map wordMap = new HashMap(wordSet.size());
for (String word : wordSet) {
Map nowMap = wordMap;
for (int i = 0; i < word.length(); i++) {
// 转换成char型
char keyChar = word.charAt(i);
// 获取
Object tempMap = nowMap.get(keyChar);
// 如果存在该key，直接赋值
if (tempMap != null) {
nowMap = (Map) tempMap;
} 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
// 设置标志位
Map<String, String> newMap = new HashMap<String, String>();
newMap.put("isEnd", "0");
// 添加到集合
nowMap.put(keyChar, newMap);
nowMap = newMap;
}
// 最后一个
if (i == word.length() - 1) {
nowMap.put("isEnd", "1");
}
}
}
return wordMap;
}
}
urlTofile工具类
package com.benwunet.bks.util;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URL;
public class UrlToFileUtil {
/**
* 将url转换成文件
* @param url
* @return
* @throws Exception
*/
public static File urlToFile(String url)throws Exception{
//对本地文件命名
String fileName = url.substring(url.lastIndexOf("."),url.length());
File file = null;
URL urlfile;
InputStream inStream = null;
OutputStream os = null;
try {
file = File.createTempFile("net_url", fileName);
//下载
urlfile = new URL(url);
inStream = urlfile.openStream();
os = new FileOutputStream(file);
int bytesRead = 0;
byte[] buffer = new byte[8192];
while ((bytesRead = inStream.read(buffer, 0, 8192)) != -1) {
os.write(buffer, 0, bytesRead);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
if (null != os) {
os.close();
}
if (null != inStream) {
inStream.close();
}
} catch (Exception e) {
e.printStackTrace();
}
}
return file;
}
}
测试用例
package com.benwunet.bks;
import com.benwunet.bks.util.SensitiveFilterService;
public class SensitiveWordTest {
public static void main(String[] args) throws Exception {
//需要屏蔽哪些字就在censorword.txt文档内添加即可
SensitiveFilterService filter = SensitiveFilterService.getInstance();
String txt = "xx需要进行检测的字符串_____________________狗杂种";
//如果需要过滤则用“”替换
//如果需要屏蔽，则用“*”替换
String hou = filter.replaceSensitiveWord(txt, 1, "*");
System.out.println("替换前的文字为：" + txt);
System.out.println("替换后的文字为：" + hou);
}
}
测试结果
敏感词库