基于DFA敏感词过滤

时间:2022-10-12 23:59:37

在springmvc中基于拦截器实现敏感词过滤

将两个类SensitiveWordInit.java(实例化敏感词map类)和SensitivewordUtils.java(敏感词工具类)放入util中

package com.util;

import com.entity.SysSensitivewords;//这里是敏感词实体类有对应的service dao从数据库查数据也可以用读txt文件来实现敏感词map的实例化

import java.util.*;


/**  * 敏感词库初始化  *  * @author AlanLee  */ public class SensitiveWordInit {
    /**  * 敏感词库  */  public static HashMap sensitiveWordMap;

    /**  * 初始化敏感词  *  * @return  */  public static Map initKeyWord(List<SysSensitivewords> sensitiveWords) {
        try {
            // 从敏感词集合对象中取出敏感词并封装到Set集合中
            Set<String> keyWordSet = new HashSet<String>();
            for (SysSensitivewords s : sensitiveWords) {
                keyWordSet.add(s.getContent().trim());
            }
            // 将敏感词库加入到HashMap中
            addSensitiveWordToHashMap(keyWordSet);
        } catch (Exception e) {
            e.printStackTrace();
        }
        return sensitiveWordMap;
    }

    /**  * 封装敏感词库  *  * @param keyWordSet  */  @SuppressWarnings("rawtypes")
    private static void addSensitiveWordToHashMap(Set<String> keyWordSet) {
        // 初始化HashMap对象并控制容器的大小
        sensitiveWordMap = new HashMap(keyWordSet.size());
        // 敏感词
        String key = null;
        // 用来按照相应的格式保存敏感词库数据
        Map nowMap = null;
        // 用来辅助构建敏感词库
        Map<String, String> newWorMap = null;
        // 使用一个迭代器来循环敏感词集合
        Iterator<String> iterator = keyWordSet.iterator();
        while (iterator.hasNext()) {
            key = iterator.next();
            // 等于敏感词库,HashMap对象在内存中占用的是同一个地址,所以此nowMap对象的变化,sensitiveWordMap对象也会跟着改变
            nowMap = sensitiveWordMap;
            for (int i = 0; i < key.length(); i++) {
                // 截取敏感词当中的字,在敏感词库中字为HashMap对象的Key键值
                char keyChar = key.charAt(i);

                // 判断这个字是否存在于敏感词库中
                Object wordMap = nowMap.get(keyChar);
                if (wordMap != null) {
                    nowMap = (Map) wordMap;
                } else {
                    newWorMap = new HashMap<String, String>();
                    newWorMap.put("isEnd", "0");
                    nowMap.put(keyChar, newWorMap);
                    nowMap = newWorMap;
                }

                // 如果该字是当前敏感词的最后一个字,则标识为结尾字
                if (i == key.length() - 1) {
                    nowMap.put("isEnd", "1");
                }
                // System.out.println("封装敏感词库过程:"/*+sensitiveWordMap*/);
            }
            //System.out.println("查看敏感词库数据:" /*+ sensitiveWordMap*/);
        }
        System.out.println("查看敏感词库数据:" + sensitiveWordMap);
    }


}
package com.util;

import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;

/**  * 敏感词过滤工具类  *  * @author AlanLee  */ public class SensitivewordUtils {
    /**  * 敏感词库  */  public static Map sensitiveWordMap = null;

    /**  * 只过滤最小敏感词  */  public static int minMatchTYpe = 1;

    /**  * 过滤所有敏感词  */  public static int maxMatchType = 2;

    /**  * 敏感词库敏感词数量  *  * @return  */  public static int getWordSize() {
        if (SensitivewordUtils.sensitiveWordMap == null) {
            return 0;
        }
        return SensitivewordUtils.sensitiveWordMap.size();
    }

    /**  * 是否包含敏感词  *  * @param txt  * @param matchType  * @return  */  public static boolean isContaintSensitiveWord(String txt, int matchType) {
        boolean flag = false;
        for (int i = 0; i < txt.length(); i++) {
            int matchFlag = checkSensitiveWord(txt, i, matchType);
            if (matchFlag > 0) {
                flag = true;
            }
        }
        return flag;
    }

    /**  * 获取敏感词内容  *  * @param txt  * @param matchType  * @return 敏感词内容  */  public static 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) {
                // 将检测出的敏感词保存到集合中
                sensitiveWordList.add(txt.substring(i, i + length));
                i = i + length - 1;
            }
        }

        return sensitiveWordList;
    }

    /**  * 替换敏感词  *  * @param txt  * @param matchType  * @param replaceChar  * @return  */  public static 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;
    }

    /**  * 替换敏感词内容  *  * @param replaceChar  * @param length  * @return  */  private static String getReplaceChars(String replaceChar, int length) {
        String resultReplace = replaceChar;
        for (int i = 1; i < length; i++) {
            resultReplace += replaceChar;
        }

        return resultReplace;
    }

    /**  * 检查敏感词数量  *  * @param txt  * @param beginIndex  * @param matchType  * @return  */  public static int checkSensitiveWord(String txt, int beginIndex, int matchType) {
        boolean flag = false;
        // 记录敏感词数量
        int matchFlag = 0;
        char word = 0;
        Map nowMap = SensitivewordUtils.sensitiveWordMap;
        for (int i = beginIndex; i < txt.length(); i++) {
            word = txt.charAt(i);
            // 判断该字是否存在于敏感词库中
            nowMap = (Map) nowMap.get(word);
            if (nowMap != null) {
                matchFlag++;
                // 判断是否是敏感词的结尾字,如果是结尾字则判断是否继续检测
                if ("1".equals(nowMap.get("isEnd"))) {
                    flag = true;
                    // 判断过滤类型,如果是小过滤则跳出循环,否则继续循环
                    if (SensitivewordUtils.minMatchTYpe == matchType) {
                        break;
                    }
                }
            } else {
                break;
            }
        }
        if (!flag) {
            matchFlag = 0;
        }
        return matchFlag;
    }

}

实现拦截器 

package com.interceptor;
import org.apache.log4j.Logger;
import org.springframework.beans.factory.BeanFactory;
import org.springframework.web.context.request.RequestContextHolder;
import org.springframework.web.context.request.ServletRequestAttributes;
import org.springframework.web.context.support.WebApplicationContextUtils;
import org.springframework.web.servlet.HandlerInterceptor;
import org.springframework.web.servlet.ModelAndView;

import javax.annotation.Resource;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import javax.servlet.http.HttpSession;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.*;

/**  * 拦截敏感词  */ public class DFAInterceptor implements HandlerInterceptor {
    private static final Logger logger = Logger.getLogger(DFAInterceptor.class);
    @Resource
    SysSensitivewordsService sysSensitivewordsService;
    private List<String> excludeUrls;

    public List<String> getExcludeUrls() {

        return excludeUrls;
    }

    public void setExcludeUrls(List<String> excludeUrls) {

        this.excludeUrls = excludeUrls;
    }

    @Override
    public void postHandle(HttpServletRequest httpServletRequest, HttpServletResponse httpServletResponse, Object o, ModelAndView modelAndView) throws Exception {

    }

    @Override
    public void afterCompletion(HttpServletRequest httpServletRequest, HttpServletResponse httpServletResponse, Object o, Exception e) throws Exception {

    }

    /**  * 之前拦截  *  * @param request  * @param httpServletResponse  * @param o  * @return  * @throws Exception  */  @Override
    public boolean preHandle(HttpServletRequest request, HttpServletResponse httpServletResponse, Object o) throws Exception {
        String requestPath = this.getRequestPath(request);// 用户访问的资源地址
        // 如果该请求不在拦截范围内,直接返回true
        if (excludeUrls.contains(requestPath)) {
            return true;
        } else {
            //遍历ParameterMap获取值
            Map<String, String[]> parameterMap = request.getParameterMap();
            StringBuffer sb = new StringBuffer();
            Iterator<Map.Entry<String, String[]>> iterator = parameterMap.entrySet().iterator();
                while (iterator.hasNext()) {
                    String[] value = iterator.next().getValue();
                    sb.append(Arrays.toString(value));
                }
                //存在实例化的敏感词map就不查数据库
            if (SensitiveWordInit.sensitiveWordMap == null || SensitivewordUtils.getWordSize() == 0) {
                List<SysSensitivewords> bySearch = sysSensitivewordsService.findBySearch(new SysSensitivewords());
                SensitivewordUtils.sensitiveWordMap = SensitiveWordInit.initKeyWord(bySearch);
            }
            //判断是否存在敏感词 存在抛出exist_sensitivewords异常与页面配置文件对应
            boolean flag = SensitivewordUtils.isContaintSensitiveWord(sb.toString(), 1);
            if (flag) {//此处用的出现敏感词抛异常前端显示的方式 实际情况实际处理比如替换的时候就调用replaceSensitiveWord()方法 但是如果是替换 就不能直接遍历parametermap获取值拼接字符串
throw new GlobalException("exist_sensitivewords");
         } return !flag ; } } /** * 截取访问路径 * * @param request * @return */ public static String getRequestPath(HttpServletRequest request) { String requestPath = request.getRequestURI() ; // 去掉其他参数 if (requestPath.indexOf( "&") > - 1) { requestPath = requestPath.substring( 0 , requestPath.indexOf( "&")) ; } // 去掉jsessionid参数 if (requestPath.indexOf( ";") > - 1) { requestPath = requestPath.substring( 0 , requestPath.indexOf( ";")) ; } // 去掉项目路径 requestPath = requestPath.substring(request.getContextPath().length() + 1) ; return requestPath ; }}

spring-mvc.xml配置

<!-- 拦截器 -->
<mvc:interceptors> 
<mvc:interceptor>
<!--<mvc:mapping path="/**"/>这是拦截所有url--> < mvc :mapping path ="/**/save" /> <bean class ="com.idp.common.interceptor.DFAInterceptor" > <property name ="excludeUrls" > <list> <value>login/checkUser </value> <value>login/getMailVerifyCode </value> <value>login/logout </value> <value>user/updatePwd </value> </list> </property> </bean> </ mvc :interceptor> </ mvc :interceptors>

实体类就是很简单的

public class SysSensitivewords extends BaseEntity implements Serializable {
   
   private static final long serialVersionUID = 1L;
   
   /**id*/  private Integer id;
   /**类型*/  private String type;
   /**内容*/  private String content;
   
   
   /**  *方法: 取得Integer  *@return: Integer id  */  public Integer getId(){
      return this.id;
   }

   /**  *方法: 设置Integer  *@param: Integer id  */  public void setId(Integer id){
      this.id = id;
   }
   
   /**  *方法: 取得String  *@return: String 类型  */  public String getType(){
      return this.type;
   }

   /**  *方法: 设置String  *@param: String 类型  */  public void setType(String type){
      this.type = type;
   }
   
   /**  *方法: 取得String  *@return: String 内容  */  public String getContent(){
      return this.content;
   }

   /**  *方法: 设置String  *@param: String 内容  */  public void setContent(String content){
      this.content = content;
   }
   
   
}