Build a Java Redis-Powered Hot Search Feature with Sensitive Word Filtering

Introduction

Use Java and Redis to implement a simple hot‑search function that supports displaying a logged‑in user’s search history, deleting personal history, recording each entered character in a Redis ZSet (using a DFA algorithm), incrementing hot‑search scores, retrieving the top ten hot queries, and filtering inappropriate words.

Hot‑search and Personal Search History API

Add a hot‑search term to Redis (filtering illegal words first).

Increase the hot‑search score by 1 each time the term is clicked.

Query the top ten hot terms for a given key.

Insert a personal search record.

Query personal search records.

Redis Service Implementation

package com.****.****.****.user;

import com.jianlet.service.user.RedisService;
import org.apache.commons.lang.StringUtils;
import org.springframework.data.redis.core.*;
import org.springframework.stereotype.Service;
import javax.annotation.Resource;
import java.util.*;
import java.util.concurrent.TimeUnit;

/**
 * @author: mrwanghc
 * @date: 2022/5/13
 * @description:
 */
@Transactional
@Service("redisService")
public class RedisServiceImpl implements RedisService {

    //导入数据源
    @Resource(name = "redisSearchTemplate")
    private StringRedisTemplate redisSearchTemplate;

    //新增一条该userid用户在搜索栏的历史记录
    //searchkey 代表输入的关键词
    @Override
    public int addSearchHistoryByUserId(String userid, String searchkey) {
        String shistory = RedisKeyUtils.getSearchHistoryKey(userid);
        boolean b = redisSearchTemplate.hasKey(shistory);
        if (b) {
            Object hk = redisSearchTemplate.opsForHash().get(shistory, searchkey);
            if (hk != null) {
                return 1;
            } else {
                redisSearchTemplate.opsForHash().put(shistory, searchkey, "1");
            }
        } else {
            redisSearchTemplate.opsForHash().put(shistory, searchkey, "1");
        }
        return 1;
    }

    //删除个人历史数据
    @Override
    public Long delSearchHistoryByUserId(String userid, String searchkey) {
        String shistory = RedisKeyUtils.getSearchHistoryKey(userid);
        return redisSearchTemplate.opsForHash().delete(shistory, searchkey);
    }

    //获取个人历史数据列表
    @Override
    public List<String> getSearchHistoryByUserId(String userid) {
        List<String> stringList = null;
        String shistory = RedisKeyUtils.getSearchHistoryKey(userid);
        boolean b = redisSearchTemplate.hasKey(shistory);
        if (b) {
            Cursor<Map.Entry<Object, Object>> cursor = redisSearchTemplate.opsForHash().scan(shistory, ScanOptions.NONE);
            while (cursor.hasNext()) {
                Map.Entry<Object, Object> map = cursor.next();
                String key = map.getKey().toString();
                stringList.add(key);
            }
            return stringList;
        }
        return null;
    }

    //新增一条热词搜索记录，将用户输入的热词存储下来
    @Override
    public int incrementScoreByUserId(String searchkey) {
        Long now = System.currentTimeMillis();
        ZSetOperations zSetOperations = redisSearchTemplate.opsForZSet();
        ValueOperations<String, String> valueOperations = redisSearchTemplate.opsForValue();
        List<String> title = new ArrayList<>();
        title.add(searchkey);
        for (int i = 0, lengh = title.size(); i < lengh; i++) {
            String tle = title.get(i);
            try {
                if (zSetOperations.score("title", tle) <= 0) {
                    zSetOperations.add("title", tle, 0);
                    valueOperations.set(tle, String.valueOf(now));
                }
            } catch (Exception e) {
                zSetOperations.add("title", tle, 0);
                valueOperations.set(tle, String.valueOf(now));
            }
        }
        return 1;
    }

    //根据searchkey搜索其相关最热的前十名 (如果searchkey为null空，则返回redis存储的前十最热词条)
    @Override
    public List<String> getHotList(String searchkey) {
        String key = searchkey;
        Long now = System.currentTimeMillis();
        List<String> result = new ArrayList<>();
        ZSetOperations zSetOperations = redisSearchTemplate.opsForZSet();
        ValueOperations<String, String> valueOperations = redisSearchTemplate.opsForValue();
        Set<String> value = zSetOperations.reverseRangeByScore("title", 0, Double.MAX_VALUE);
        if (StringUtils.isNotEmpty(searchkey)) {
            for (String val : value) {
                if (StringUtils.containsIgnoreCase(val, key)) {
                    if (result.size() > 9) {
                        break;
                    }
                    Long time = Long.valueOf(valueOperations.get(val));
                    if ((now - time) < 2592000000L) {
                        result.add(val);
                    } else {
                        zSetOperations.add("title", val, 0);
                    }
                }
            }
        } else {
            for (String val : value) {
                if (result.size() > 9) {
                    break;
                }
                Long time = Long.valueOf(valueOperations.get(val));
                if ((now - time) < 2592000000L) {
                    result.add(val);
                } else {
                    zSetOperations.add("title", val, 0);
                }
            }
        }
        return result;
    }

    //每次点击给相关词searchkey热度 +1
    @Override
    public int incrementScore(String searchkey) {
        String key = searchkey;
        Long now = System.currentTimeMillis();
        ZSetOperations zSetOperations = redisSearchTemplate.opsForZSet();
        ValueOperations<String, String> valueOperations = redisSearchTemplate.opsForValue();
        zSetOperations.incrementScore("title", key, 1);
        valueOperations.getAndSet(key, String.valueOf(now));
        return 1;
    }
}

Sensitive Word Filtering Configuration

Define a Spring Boot @Configuration class that loads a list of prohibited words from static/censorword.txt and builds a DFA‑based map for fast detection.

package com.***.***.interceptor;

import org.springframework.context.annotation.Configuration;
import org.springframework.core.io.ClassPathResource;
import java.io.*;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Map;
import java.util.Set;

//屏蔽敏感词初始化
@Configuration
@SuppressWarnings({ "rawtypes", "unchecked" })
public class SensitiveWordInit {
    //字符编码
    private String ENCODING = "UTF-8";
    //初始化敏感字库
    public Map initKeyWord() throws IOException {
        //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 ,存入Set中
    private Set<String> readSensitiveWordFile() throws IOException {
        Set<String> wordSet = null;
        ClassPathResource classPathResource = new ClassPathResource("static/censorword.txt");
        InputStream inputStream = classPathResource.getInputStream();
        try {
            InputStreamReader read = new InputStreamReader(inputStream, ENCODING);
            wordSet = new HashSet<String>();
            BufferedReader br = new BufferedReader(read);
            String txt = null;
            while ((txt = br.readLine()) != null) {
                wordSet.add(txt);
            }
            br.close();
            read.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return wordSet;
    }

    //将HashSet中的敏感词,存入HashMap中
    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++) {
                char keyChar = word.charAt(i);
                Object tempMap = nowMap.get(keyChar);
                if (tempMap != null) {
                    nowMap = (Map) tempMap;
                } else {
                    Map<String, String> newMap = new HashMap<String, String>();
                    newMap.put("isEnd", "0");
                    nowMap.put(keyChar, newMap);
                    nowMap = newMap;
                }
                if (i == word.length() - 1) {
                    nowMap.put("isEnd", "1");
                }
            }
        }
        return wordMap;
    }
}

The utility class SensitiveFilter provides methods to detect and replace sensitive words using the DFA map.

package com.***.***.interceptor;

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

//敏感词过滤器：利用DFA算法 进行敏感词过滤
public class SensitiveFilter {
    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 SensitiveFilter instance = null;
    //构造函数，初始化敏感词库
    private SensitiveFilter() throws IOException {
        sensitiveWordMap = new SensitiveWordInit().initKeyWord();
    }
    //获取单例
    public static SensitiveFilter getInstance() throws IOException {
        if (null == instance) {
            instance = new SensitiveFilter();
        }
        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++) {
            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
    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;
    }
    private String getReplaceChars(String replaceChar, int length) {
        String resultReplace = replaceChar;
        for (int i = 1; i < length; i++) {
            resultReplace += replaceChar;
        }
        return resultReplace;
    }
    public int CheckSensitiveWord(String txt, int beginIndex, int matchType) {
        boolean flag = false;
        int matchFlag = 0;
        Map nowMap = sensitiveWordMap;
        for (int i = beginIndex; i < txt.length(); i++) {
            char word = txt.charAt(i);
            nowMap = (Map) nowMap.get(word);
            if (nowMap != null) {
                matchFlag++;
                if ("1".equals(nowMap.get("isEnd"))) {
                    flag = true;
                    if (SensitiveFilter.minMatchType == matchType) {
                        break;
                    }
                }
            } else {
                break;
            }
        }
        if (SensitiveFilter.maxMatchType == matchType) {
            if (matchFlag < 2 || !flag) {
                matchFlag = 0;
            }
        }
        if (SensitiveFilter.minMatchType == matchType) {
            if (matchFlag < 2 && !flag) {
                matchFlag = 0;
            }
        }
        return matchFlag;
    }
}

In a controller you can invoke the filter to reject or replace illegal characters before further processing:

//非法敏感词汇判断
SensitiveFilter filter = SensitiveFilter.getInstance();
int n = filter.CheckSensitiveWord(searchkey, 0, 1);
if (n > 0) {
    logger.info("这个人输入了非法字符--> {},不知道他到底要查什么~ userid--> {}", searchkey, userid);
    return null;
}
//或者进行替换
String safe = filter.replaceSensitiveWord(searchkey, 1, "*");