1 功能要求
使用SpringBoot和redis实现一个简单的热搜功能,具备以下功能:
- 搜索栏展示当前登陆的个人用户的搜索历史记录,删除个人历史记录
- 用户在搜索栏输入某字符,则将该字符记录下来 以zset格式存储的redis中,记录该字符被搜索的个数以及当前的时间戳 (用了DFA算法,感兴趣的自己百度学习吧)
- 每当用户查询了已在redis存在了的字符时,则直接累加个数, 用来获取平台上最热查询的十条数据。(可以自己写接口或者直接在redis中添加一些预备好的关键词)
- 最后还要做不雅文字过滤功能
代码实现热搜与个人搜索记录功能,主要controller层下几个方法就行了 :
- 向redis 添加热搜词汇(添加的时候使用下面不雅文字过滤的方法来过滤下这个词汇,合法再去存储
- 每次点击给相关词热度 +1
- 根据key搜索相关最热的前十名
- 插入个人搜索记录
- 查询个人搜索记录
2 代码实现
2.1 项目结构如下
2.2 引入相关maven依赖
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-test</artifactId>
<scope>test</scope>
</dependency>
<!-- https://mvnrepository.com/artifact/org.springframework.boot/spring-boot-starter-data-redis -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-redis</artifactId>
<version>2.7.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.commons/commons-lang3 -->
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.12.0</version>
</dependency>
</dependencies>
2.3 application.yml配置
spring:
redis:
#数据库索引
database: 0
host: 192.168.222.131
port: 6379
password: 123456
lettuce:
pool:
#最大连接数
max-active: 8
#最大阻塞等待时间(负数表示没限制)
max-wait: -1
#最大空闲
max-idle: 8
#最小空闲
min-idle: 0
#连接超时时间
timeout: 10000
2.4 创建RedisKeyUtils工具类
package com.example.demo.Utils;
public class RedisKeyUtils {
/**
* 分隔符号
*/
private static final String SPLIT = ":";
private static final String SEARCH = "search";
private static final String SEARCH_HISTORY = "search-history";
private static final String HOT_SEARCH = "hot-search";
private static final String SEARCH_TIME = "search-time";
/**
* 每个用户的个人搜索记录hash
*/
public static String getSearchHistoryKey(String userId){
return SEARCH + SPLIT + SEARCH_HISTORY + SPLIT + userId;
}
/**
* 总的热搜zset
*/
public static String getHotSearchKey(){
return SEARCH + SPLIT + HOT_SEARCH;
}
/**
* 每个搜索记录的时间戳记录:key-value
*/
public static String getSearchTimeKey(String searchKey){
return SEARCH + SPLIT + SEARCH_TIME + SPLIT + searchKey;
}
}
2.5 核心搜索文件
redis搜索接口:
package com.example.demo.Service;
import java.util.List;
public interface RedisService {
//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
int addSearchHistoryByUserId(String userid, String searchkey);
//删除个人历史数据
Long delSearchHistoryByUserId(String userid, String searchkey);
//获取个人历史数据列表
List<String> getSearchHistoryByUserId(String userid);
//新增一条热词搜索记录,将用户输入的热词存储下来
int incrementScoreByUserId(String searchkey);
//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)
List<String> getHotList(String searchkey);
//每次点击给相关词searchkey热度 +1
int incrementScore(String searchkey);
}
接口实现类:
package com.example.demo.Service.Impl;
import com.example.demo.Service.RedisService;
import com.example.demo.Utils.RedisKeyUtils;
import org.apache.commons.lang3.StringUtils;
import org.springframework.data.redis.core.*;
import org.springframework.stereotype.Service;
import org.springframework.transaction.annotation.Transactional;
import javax.annotation.Resource;
import java.util.*;
import java.util.concurrent.TimeUnit;
@Transactional
@Service("redisService")
public class RedisServiceImpl implements RedisService {
//导入数据源
// @Resource(name = "redisSearchTemplate")
@Resource
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);
//key不为空的时候 推荐相关的最热前十名
if(StringUtils.isNotEmpty(searchkey)){
for (String val : value) {
if (StringUtils.containsIgnoreCase(val, key)) {
if (result.size() > 9) {//只返回最热的前十名
break;
}
Long time = Long.valueOf(valueOperations.get(val));
if ((now - time) < 2592000000L) {//返回最近一个月的数据
result.add(val);
} else {//时间超过一个月没搜索就把这个词热度归0
zSetOperations.add("title", val, 0);
}
}
}
}else{
for (String val : value) {
if (result.size() > 9) {//只返回最热的前十名
break;
}
Long time = Long.valueOf(valueOperations.get(val));
if ((now - time) < 2592000000L) {//返回最近一个月的数据
result.add(val);
} else {//时间超过一个月没搜索就把这个词热度归0
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;
}
}
2.6 不雅字过滤
实现原理
简单原理如下图所示,使用了DFA算法,创建结点类,里面包含是否是敏感词结束符,以及一个HashMap,哈希里key值存储的是敏感词的一个词,value指向下一个结点(即指向下一个词),一个哈希表中可以存放多个值,比如赌博、赌黄这两个都是敏感词。
实现方法
敏感词库的初始化,这里主要工作是读取敏感词文件,在内存中构建好敏感词的Map节点。
package com.example.demo.Config;
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HashMap中
private Set<String> readSensitiveWordFile() throws IOException {
Set<String> wordSet = null;
ClassPathResource classPathResource = new ClassPathResource("static/word1.txt");
InputStream inputStream = classPathResource.getInputStream();
//敏感词库
try {
// 读取文件输入流
InputStreamReader read = new InputStreamReader(inputStream, ENCODING);
// 文件是否是文件 和 是否存在
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();
// 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
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;
}
// 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
else {
// 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;
}
}
最后刚才的SensitiveWordInit.java里面用到了word.txt 文件,放到你项目里面的 resources 目录下的 static 目录中,这个文件就是不雅文字大全,也需要您与时俱进的更新,项目启动的时候会加载该文件。
敏感词过滤器
敏感词过滤器,主要功能是初始化敏感词库,敏感词的过滤以及替换
package com.example.demo.Filter;
import com.example.demo.Config.SensitiveWordInit;
import org.springframework.stereotype.Component;
import java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;
@Component
public class SensitiveFilter {
/**
* 敏感词过滤器:利用DFA算法 进行敏感词过滤
*/
private Map sensitiveWordMap = null;
/**
* 最小匹配规则,如:敏感词库["中国","中国人"],语句:"我是中国人",匹配结果:我是[中国]人
*/
public static int minMatchType = 1;
/**
* 最大匹配规则,如:敏感词库["中国","中国人"],语句:"我是中国人",匹配结果:我是[中国人]
*/
public static int maxMatchType = 2;
/**
* 敏感词替换词
*/
public static String placeHolder = "**";
// 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<>();
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,使用了默认的替换符合,默认最小匹配规则
*/
public String replaceSensitiveWord(String txt) {
return replaceSensitiveWord(txt, minMatchType ,placeHolder);
}
/**
* 替换敏感字字符,使用了默认的替换符合
*/
public String replaceSensitiveWord(String txt, int matchType) {
return replaceSensitiveWord(txt, matchType,placeHolder);
}
/**
* 替换敏感字字符
*/
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
*/
private String getReplaceChars(String replaceChar, int length) {
StringBuilder resultReplace = new StringBuilder(replaceChar);
for (int i = 1; i < length; i++) {
resultReplace.append(replaceChar);
}
return resultReplace.toString();
}
/**
* 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
* 核心
*/
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的情况结束
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 (SensitiveFilter.minMatchType == matchType) {
break;
}
}
}
// 不存在,直接返回
else {
break;
}
}
// 匹配长度如果匹配上了最小匹配长度或者最大匹配长度
if (SensitiveFilter.maxMatchType == matchType || SensitiveFilter.minMatchType == matchType){
//长度必须大于等于1,为词,或者敏感词库还没有结束(匹配了一半),flag为false
if(matchFlag < 2 || !flag){
matchFlag = 0;
}
}
return matchFlag;
}
}
测试不雅文字过滤器
package com.example.demo.Controller;
import com.example.demo.Filter.SensitiveFilter;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;
@RestController
public class SensitiveController {
private static Logger logger = LoggerFactory.getLogger(SensitiveController.class);
@Autowired
SensitiveFilter sensitiveFilter;
@GetMapping("/sensitive")
public String sensitive(String keyword){
String s = sensitiveFilter.replaceSensitiveWord(keyword);
return s;
}
}
直接测试
测试热点搜索接口
package com.example.demo.Controller;
import com.example.demo.Service.RedisService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;
import java.util.List;
@RestController
public class SearchHistoryController {
@Autowired
RedisService redisService;
@GetMapping("/add")
public String addSearchHistoryByUserId(String userId, String searchKey) {
redisService.addSearchHistoryByUserId(userId, searchKey);
redisService.incrementScore(searchKey);
return null;
}
/**
* 删除个人历史数据
*/
@GetMapping("/del")
public Long delSearchHistoryByUserId(String userId, String searchKey) {
return redisService.delSearchHistoryByUserId(userId, searchKey);
}
/**
* 获取个人历史数据列表
*/
@GetMapping("/getUser")
public List<String> getSearchHistoryByUserId(String userId) {
return redisService.getSearchHistoryByUserId(userId);
}
/**
* 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)
*/
@GetMapping("/getHot")
public List<String> getHotList(String searchKey) {
return redisService.getHotList(searchKey);
}
}
测试搜索接口
查询搜索热点
代码如下:https://download.csdn.net/download/u013938578/87390464?spm=1001.2014.3001.5503