请问一下如何在JSP网站中过滤敏感词汇啊？？如何实现

Question

一个门户上的简单留言功能。提交敏感词汇的时候自动过滤掉。请问如何实现啊。大家谁做过有没有这样的例子麻烦发我一下啊。[email protected]

Answer 1

我没有做过。但是给你说下我的思路啊
1.用表或者文件保存需要过滤的关键字。这里我感觉用XML文件保存就可以了，甚至用文本文件也未尝不可。
2.提供一个方法读取这个保存过滤关键字的XML文件或者文本文件。如：
  public String[] getFilterWords(){}
3.当用户写了留言，提交的时候，就把留言的字符替换。如：
  String str = "留言的字符内容";
  for(String filterWord : getFilterWords()) {
      str.replace(filterWord , "*");
  }

Answer 2

可以利用 JSP 的自定义标签来进行关键字过滤；

Answer 3

/**默认读取的过滤词文件*/
    public final static String DEFAULT_FILENAME = "keyWord.properties";
    
    public final static String FILENAME_FOR_DOCTITLE = "keyWordForTitle.properties";
    
    private static Map<String, String> keywords = new HashMap<String, String>();
    
    private static Map<String, Pattern> patterns = new HashMap<String, Pattern>();    static {
        try {
         /**默认读取keyWord.properties文件*/
         readFile(DEFAULT_FILENAME);
        } catch (Exception e) {
            logger.error("init Error!", e);
        }
    }    private static void readFile(String filename){
     try{
     if(patterns.containsKey(filename)){
     return;
     }
    
     StringBuffer patternBuf = new StringBuffer("");
        InputStream in = KeyWordFilter.class.getClassLoader().getResourceAsStream(filename);
        if (null == in) {
            in = KeyWordFilter.class.getClassLoader().getResourceAsStream(
                "META-INF/" + filename);
        }
        InputStreamReader isr = new InputStreamReader(in, "UTF-8");
        BufferedReader br = new BufferedReader(isr);
        patternBuf.append("(");
        String keyword = null;
        while((keyword = br.readLine()) != null){
         patternBuf.append(keyword + "|");
        }
        patternBuf.deleteCharAt(patternBuf.length() - 1);
        patternBuf.append(")");
        String keyWords = patternBuf.toString();
        keywords.put(filename, keyWords);
        patterns.put(filename, Pattern.compile(keyWords));
     }catch (Exception e) {
            logger.error("read file: " + filename, e);
        }
    }
    
    public static String doFilter(String content) {
        return doFilter(content, DEFAULT_FILENAME);
    }    public static boolean doChecker(String content) {
     return doChecker(content, DEFAULT_FILENAME); 
    }
    
    public static String doFilter(String content, String filename) {
     if(null == content){
     return null;
     }
    
     readFile(filename);
     Pattern pattern = patterns.get(filename);
        Matcher m = pattern.matcher(content);
        content = m.replaceAll("");
        return content;
    }    public static boolean doChecker(String content, String filename) {
     if(null == content){
     return false;
     }
    
     readFile(filename);
     Pattern pattern = patterns.get(filename);
        Matcher m = pattern.matcher(content);
        return m.find();
    }        public static void main(String[] args) {
            String test1 = "订票";
            System.out.println(KeyWordFilter.doChecker(test1));
            System.out.println(KeyWordFilter.doFilter(test1));
            
            System.out.println(KeyWordFilter.doChecker(test1, FILENAME_FOR_DOCTITLE));
            System.out.println(KeyWordFilter.doFilter(test1, FILENAME_FOR_DOCTITLE));
        }写几个敏感词文件就行了

Answer 4

KeyWordFilter这个是什么东西？？？

Answer 5

public class FilterTest extends HttpServlet implements Filter {
   private FilterConfig filterConfig;   public void init(FilterConfig filterConfig) throws ServletException {
       this.filterConfig = filterConfig;
   }   public void doFilter(ServletRequest request, ServletResponse response,
                        FilterChain filterChain) {
       String[] filterString = {"AAA", "vbb", "vvv", "", ""};//过滤字符串
       String str = "";       try {
           request.setCharacterEncoding("utf-8");
           HttpServletRequest req= (HttpServletRequest) request;
           String filterParam= req.getParameter("filterParam");           if (filterParam != null && !filterParam.trim().length() > 0) {
               for (int i = 0; i < filterString.length; i++) {
                   str = filterString[i];
                   if (filterParam .indexOf(str) != -1) 
                       filterParam = filterParam.replaceAll(str,"******");
               }
               req.setAttribute("filterParam", filterParam);
           }
           filterChain.doFilter(request, response);
       } catch (ServletException sx) {
           filterConfig.getServletContext().log(sx.getMessage());
       } catch (IOException iox) {
           filterConfig.getServletContext().log(iox.getMessage());
       }
   }
   public void destroy() {
   }
}

Answer 6

package filter;import java.io.CharArrayWriter;
import java.io.IOException;
import java.io.PrintWriter;
import java.util.StringTokenizer;import javax.servlet.Filter;
import javax.servlet.FilterChain;
import javax.servlet.FilterConfig;
import javax.servlet.ServletException;
import javax.servlet.ServletRequest;
import javax.servlet.ServletResponse;
import javax.servlet.http.HttpServletResponse;
import javax.servlet.http.HttpServletResponseWrapper;public class IllegalContentFilter implements Filter {
    protected FilterConfig filterConfig;    public void destroy() {
        this.filterConfig = null;
    }    public void doFilter(ServletRequest request, ServletResponse response, FilterChain chain) throws IOException, ServletException {
        request.setCharacterEncoding("gbk");
        response.setCharacterEncoding("gbk");        HttpServletResponse res = (HttpServletResponse) response;
        PrintWriter out = response.getWriter();
        WrapperImpl wrapper = new WrapperImpl(res);        chain.doFilter(request, wrapper);
        
        out.println(replaceIllegalContent(wrapper.toString(), filterConfig.getInitParameter("illegalContent"), filterConfig.getInitParameter("replaceString")));
    }    public void init(FilterConfig filterConfig) throws ServletException {
        this.filterConfig = filterConfig;
    }    public String replaceIllegalContent(String content, String illegalContent, String replaceString) {
        if (content == null || content.trim().equals("") || illegalContent == null || illegalContent.trim().equals("") || replaceString == null || replaceString.trim().equals("")) {
            System.err.println("缺少必要的属性无法过滤 返回传进来的内容");
        } else {
            for (StringTokenizer tokenizer = new StringTokenizer(illegalContent, ",", false); tokenizer.hasMoreTokens();) {
                content = content.replaceAll(tokenizer.nextToken(), replaceString);
            }
        }
        return content;
    }    private class WrapperImpl extends HttpServletResponseWrapper {
        private CharArrayWriter output;        public WrapperImpl(HttpServletResponse response) {
            super(response);
            output = new CharArrayWriter();
        }        public String toString() {
            return output.toString();
        }        public PrintWriter getWriter() {
            return new PrintWriter(output);
        }
    }
}web.xml code<?xml version="1.0" encoding="UTF-8"?>
<web-app version="2.5" xmlns="http://java.sun.com/xml/ns/javaee"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://java.sun.com/xml/ns/javaee 
    http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd">    <filter>
        <filter-name>illegalFilter</filter-name>
        <filter-class>filter.IllegalContentFilter</filter-class>
        <init-param>
            <param-name>illegalContent</param-name>
            <param-value>
                去你吗的,草你吗,草你妈,操你妈,靠,SB,傻B,傻逼,我日,日你娘,干你娘,上你妈,毛泽东,组织,开枪,马克思,列宁,恩格斯,周恩来
            </param-value>
        </init-param>
        <init-param>
            <param-name>replaceString</param-name>
            <param-value>[河蟹]</param-value>
        </init-param>
    </filter>
    <filter-mapping>
        <filter-name>illegalFilter</filter-name>
        <url-pattern>/*</url-pattern>
    </filter-mapping>
</web-app>

Answer 7

参考http://download.csdn.net/source/1537199