JAVA 敏感词过滤
在网站中进行敏感词过滤是非常必要的。
先写一个过滤器
public class WordValidator implements Filter{
private WordValidatorUtil wordValidatorUtil=new WordValidatorUtil();
@Override
public void destroy() {
wordValidatorUtil=null;
}
@Override
public void doFilter(ServletRequest arg0, ServletResponse arg1,
FilterChain arg2) throws IOException, ServletException {
HttpServletRequest request= (HttpServletRequest) arg0;
HttpServletResponse response = (HttpServletResponse) arg1;
String txt=request.getParameter("txt");
if(txt!=null)
{
Boolean bool = wordValidatorUtil.isContaintSensitiveWord(txt, 1);
if(bool==true){
System.out.println("有敏感词");
PrintWriter writer=response.getWriter();
writer.print(common.util.Status.SENSITIVE_WORD_TRUE);
writer.flush();
writer.close();
}else {
System.out.println("没有敏感词");
arg2.doFilter(arg0, arg1);
}
}else {
arg2.doFilter(arg0, arg1);
}
return;
}
@Override
public void init(FilterConfig arg0) throws ServletException {
}
}
//WordValidatorUtil 类 判断输入是否包含关键字
public class WordValidatorUtil {
private 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
/**
* 构造函数，初始化敏感词库
*/
public WordValidatorUtil(){
WordValidatorInit wordValidatorInit=new WordValidatorInit();
sensitiveWordMap=wordValidatorInit.initKeyWord();
}
/**
* 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); //判断是否包含敏感字符
if(matchFlag > 0){ //大于0存在，返回true
flag = true;
}
}
return flag;
}
/**
* 检查文字中是否包含敏感字符，检查规则如下：<br>
* @author chenming
* @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
*/
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); //获取指定key
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(WordValidatorUtil.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;
}
}
//敏感词库初始化
public class WordValidatorInit {
private String ENCODING = "UTF-8"; //字符编码
public HashMap sensitiveWordMap;
/**
*
* @version 1.0
*/
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);
//spring获取application，然后application.setAttribute("sensitiveWordMap",sensitiveWordMap);
} catch (Exception e) {
e.printStackTrace();
}
return sensitiveWordMap;
}
/**
* @param keyWordSet 敏感词库
* @version 1.0
*/
private void addSensitiveWordToHashMap(Set<String> keyWordSet) {
sensitiveWordMap = new HashMap(keyWordSet.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 = 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); //获取
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
}
}
}
}
/**
* 读取敏感词库中的内容，将内容添加到set集合中
* @return
* @version 1.0
* @throws Exception
*/
private Set<String> readSensitiveWordFile() throws Exception{
Set<String> set = null;
File file = new File(getClass().getClassLoader().getResource("SensitiveWord.txt").getPath()); //读取文件
InputStreamReader read = new InputStreamReader(new FileInputStream(file),ENCODING);
try {
if(file.isFile() && file.exists()){ //文件流是否存在
set = new HashSet<String>();
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
set.add(txt);
}
}
else{ //不存在抛出异常信息
throw new Exception("敏感词库文件不存在");
}
} catch (Exception e) {
throw e;
}finally{
read.close(); //关闭文件流
}
return set;
}
}