一、ElasticSearch 简介
1、简介
ElasticSearch 是一个基于 Lucene 的搜索服务器。它提供了一个分布式多员工能力的全文搜索引擎,基于 RESTful web 接口。Elasticsearch 是用 Java 语言开发的,并作为 Apache 许可条款下的开放源码发布,是一种流行的企业级搜索引擎。
ElasticSearch 用于云计算中,能够达到实时搜索,稳定,可靠,快速,安装使用方便。
2、特性
分布式的文档存储引擎
分布式的搜索引擎和分析引擎
分布式,支持PB级数据
3、使用场景
搜索领域:如百度、谷歌,全文检索等。
门户网站:访问统计、文章点赞、留言评论等。
广告推广:记录员工行为数据、消费趋势、员工群体进行定制推广等。
信息采集:记录应用的埋点数据、访问日志数据等,方便大数据进行分析。
二、ElasticSearch 基础概念
1、ElaticSearch 和 DB 的关系
在 Elasticsearch 中,文档归属于一种类型 type,而这些类型存在于索引 index 中,我们可以列一些简单的不同点,来类比传统关系型数据库:
Relational DB -> Databases -> Tables -> Rows -> Columns
Elasticsearch -> Indices -> Types -> Documents -> Fields
Elasticsearch 集群可以包含多个索引 indices,每一个索引可以包含多个类型 types,每一个类型包含多个文档 documents,然后每个文档包含多个字段 Fields。而在 DB 中可以有多个数据库 Databases,每个库中可以有多张表 Tables,没个表中又包含多行Rows,每行包含多列Columns。
2、索引
索引基本概念(indices):
索引是含义相同属性的文档集合,是 ElasticSearch 的一个逻辑存储,可以理解为关系型数据库中的数据库,ElasticSearch 可以把索引数据存放到一台服务器上,也可以 sharding 后存到多台服务器上,每个索引有一个或多个分片,每个分片可以有多个副本。
索引类型(index_type):
索引可以定义一个或多个类型,文档必须属于一个类型。在 ElasticSearch 中,一个索引对象可以存储多个不同用途的对象,通过索引类型可以区分单个索引中的不同对象,可以理解为关系型数据库中的表。每个索引类型可以有不同的结构,但是不同的索引类型不能为相同的属性设置不同的类型。
3、文档
文档(document):
文档是可以被索引的基本数据单位。存储在 ElasticSearch 中的主要实体叫文档 document,可以理解为关系型数据库中表的一行记录。每个文档由多个字段构成,ElasticSearch 是一个非结构化的数据库,每个文档可以有不同的字段,并且有一个唯一的标识符。
4、映射
映射(mapping):
ElasticSearch 的 Mapping 非常类似于静态语言中的数据类型:声明一个变量为 int 类型的变量,以后这个变量都只能存储 int 类型的数据。同样的,一个 number 类型的 mapping 字段只能存储 number 类型的数据。
同语言的数据类型相比,Mapping 还有一些其他的含义,Mapping 不仅告诉 ElasticSearch 一个 Field 中是什么类型的值, 它还告诉 ElasticSearch 如何索引数据以及数据是否能被搜索到。
ElaticSearch 默认是动态创建索引和索引类型的 Mapping 的。这就相当于无需定义 Solr 中的 Schema,无需指定各个字段的索引规则就可以索引文件,很方便。但有时方便就代表着不灵活。比如,ElasticSearch 默认一个字段是要做分词的,但我们有时要搜索匹配整个字段却不行。如有统计工作要记录每个城市出现的次数。对于 name 字段,若记录 new york 文本,ElasticSearch 可能会把它拆分成 new 和 york 这两个词,分别计算这个两个单词的次数,而不是我们期望的 new york。
三、SpringBoot 项目引入 ElasticSearch 依赖
下面介绍下 SpringBoot 如何通过 elasticsearch-rest-high-level-client 工具操作 ElasticSearch,这里需要说一下,为什么没有使用 Spring 家族封装的 spring-data-elasticsearch。
主要原因是灵活性和更新速度,Spring 将 ElasticSearch 过度封装,让开发者很难跟 ES 的 DSL 查询语句进行关联。再者就是更新速度,ES 的更新速度是非常快,但是 spring-data-elasticsearch 更新速度比较缓慢。
由于上面两点,所以选择了官方推出的 Java 客户端 elasticsearch-rest-high-level-client,它的代码写法跟 DSL 语句很相似,懂 ES 查询的使用其上手很快。
【注意SpringBoot的版本-es的版本对应】
1、Maven 引入相关依赖
- lombok:lombok 工具依赖。
- fastjson:用于将 JSON 转换对象的依赖。
- spring-boot-starter-web: SpringBoot 的 Web 依赖。
- elasticsearch:ElasticSearch:依赖,需要和 ES 版本保持一致。
- elasticsearch-rest-high-level-client:用于操作 ES 的 Java 客户端。
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.example</groupId>
<artifactId>elasticsearch</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>elasticsearch</name>
<description>Demo project for Spring Boot</description>
<properties>
<java.version>1.8</java.version>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
<spring-boot.version>2.3.12.RELEASE</spring-boot.version>
</properties>
<dependencies>
<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>
<exclusions>
<exclusion>
<groupId>org.junit.vintage</groupId>
<artifactId>junit-vintage-engine</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<optional>true</optional>
</dependency>
<!--fastjson-->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.61</version>
</dependency>
<!--elasticsearch-->
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>elasticsearch-rest-high-level-client</artifactId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch</artifactId>
<version>7.6.1</version>
</dependency>
</dependencies>
<dependencyManagement>
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-dependencies</artifactId>
<version>${spring-boot.version}</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-maven-plugin</artifactId>
<version>${spring-boot.version}</version>
<configuration>
<mainClass>com.example.elasticsearch.ElasticsearchApplication</mainClass>
<skip>true</skip>
</configuration>
<executions>
<execution>
<id>repackage</id>
<goals>
<goal>repackage</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
2、ElasticSearch 连接配置
(1)、application.yml 配置文件
为了方便更改连接 ES 的连接配置,所以我们将配置信息放置于 application.yml 中:
server:
port: 8080
servlet:
context-path: /search
elasticsearch:
schema: http
address: 127.0.0.1:9200
connectTimeout: 10000
socketTimeout: 10000
connectionRequestTimeout: 10000
maxConnectNum: 100
maxConnectPerRoute: 100
myindex: testindex
(2)、java 连接配置类
这里需要写一个 Java 配置类读取 application 中的配置信息:
package com.example.elasticsearch.demos.config;
import org.apache.http.HttpHost;
import org.elasticsearch.client.RestClient;
import org.elasticsearch.client.RestClientBuilder;
import org.elasticsearch.client.RestHighLevelClient;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import java.util.ArrayList;
import java.util.List;
/**
* ElasticSearch 配置
*/
@Configuration
public class ElasticSearchConfig {
/** 协议 */
@Value("${elasticsearch.schema:http}")
private String schema;
/** 集群地址,如果有多个用“,”隔开 */
@Value("${elasticsearch.address}")
private String address;
/** 连接超时时间 */
@Value("${elasticsearch.connectTimeout:5000}")
private int connectTimeout;
/** Socket 连接超时时间 */
@Value("${elasticsearch.socketTimeout:10000}")
private int socketTimeout;
/** 获取连接的超时时间 */
@Value("${elasticsearch.connectionRequestTimeout:5000}")
private int connectionRequestTimeout;
/** 最大连接数 */
@Value("${elasticsearch.maxConnectNum:100}")
private int maxConnectNum;
/** 最大路由连接数 */
@Value("${elasticsearch.maxConnectPerRoute:100}")
private int maxConnectPerRoute;
@Bean
public RestHighLevelClient restHighLevelClient() {
// 拆分地址
List<HttpHost> hostLists = new ArrayList<>();
String[] hostList = address.split(",");
for (String addr : hostList) {
String host = addr.split(":")[0];
String port = addr.split(":")[1];
hostLists.add(new HttpHost(host, Integer.parseInt(port), schema));
}
// 转换成 HttpHost 数组
HttpHost[] httpHost = hostLists.toArray(new HttpHost[]{});
// 构建连接对象
RestClientBuilder builder = RestClient.builder(httpHost);
// 异步连接延时配置
builder.setRequestConfigCallback(requestConfigBuilder -> {
requestConfigBuilder.setConnectTimeout(connectTimeout);
requestConfigBuilder.setSocketTimeout(socketTimeout);
requestConfigBuilder.setConnectionRequestTimeout(connectionRequestTimeout);
return requestConfigBuilder;
});
// 异步连接数配置
builder.setHttpClientConfigCallback(httpClientBuilder -> {
httpClientBuilder.setMaxConnTotal(maxConnectNum);
httpClientBuilder.setMaxConnPerRoute(maxConnectPerRoute);
return httpClientBuilder;
});
return new RestHighLevelClient(builder);
}
}
四、索引操作示例
这里示例会指出通过Postman的 Restful 工具操作与对应的 Java 代码操作的两个示例。
1、Restful 操作示例
创建索引
创建名为 testindex 的索引与对应 Mapping。
PUT http://localhost:9200/testindex
{
"mappings": {
"doc": {
"dynamic": true,
"properties": {
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword"
}
}
},
"address": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword"
}
}
},
"remark": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword"
}
}
},
"age": {
"type": "integer"
},
"salary": {
"type": "float"
},
"birthDate": {
"type": "date",
"format": "yyyy-MM-dd"
},
"createTime": {
"type": "date"
}
}
}
}
}
删除索引
删除 mydlq-user 索引。
DELETE http://localhost:9200/testindex
2、Java 代码示例
package com.example.elasticsearch.demos.web.service.base;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.admin.indices.create.CreateIndexRequest;
import org.elasticsearch.action.admin.indices.create.CreateIndexResponse;
import org.elasticsearch.action.admin.indices.delete.DeleteIndexRequest;
import org.elasticsearch.action.admin.indices.get.GetIndexRequest;
import org.elasticsearch.action.support.master.AcknowledgedResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.xcontent.XContentBuilder;
import org.elasticsearch.common.xcontent.XContentFactory;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 索引操作
*/
@Slf4j
@Service
public class IndexService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 验证索引是否存在
*/
public Object existsIndex(String indexName) {
Object result = "";
try {
// 获取索引请求
GetIndexRequest request = new GetIndexRequest();
// 设置要查询的索引名称
request.indices(indexName);
// 执行请求,验证索引是否存在
boolean isExist = restHighLevelClient.indices().exists(request, RequestOptions.DEFAULT);
log.info("是否存在:{}", isExist);
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = isExist;
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 创建索引
*/
public Object createIndex(String indexName) {
Object result = "";
try {
// 创建 Mapping
XContentBuilder mapping = XContentFactory.jsonBuilder()
.startObject()
.field("dynamic", true)
.startObject("properties")
.startObject("name")
.field("type","text")
.startObject("fields")
.startObject("keyword")
.field("type","keyword")
.endObject()
.endObject()
.endObject()
.startObject("address")
.field("type","text")
.startObject("fields")
.startObject("keyword")
.field("type","keyword")
.endObject()
.endObject()
.endObject()
.startObject("remark")
.field("type","text")
.startObject("fields")
.startObject("keyword")
.field("type","keyword")
.endObject()
.endObject()
.endObject()
.startObject("age")
.field("type","integer")
.endObject()
.startObject("salary")
.field("type","float")
.endObject()
.startObject("birthDate")
.field("type","date")
.field("format", "yyyy-MM-dd")
.endObject()
.startObject("createTime")
.field("type","date")
.endObject()
.endObject()
.endObject();
// 创建索引配置信息,配置
Settings settings = Settings.builder()
.put("index.number_of_shards", 1)
.put("index.number_of_replicas", 0)
.build();
// 新建创建索引请求对象,然后设置索引类型(ES 7.0 将不存在索引类型)和 mapping 与 index 配置
CreateIndexRequest request = new CreateIndexRequest(indexName, settings);
request.mapping("doc", mapping);
// RestHighLevelClient 执行创建索引
CreateIndexResponse createIndexResponse = restHighLevelClient.indices().create(request, RequestOptions.DEFAULT);
// 判断是否创建成功
boolean isCreated = createIndexResponse.isAcknowledged();
log.info("是否创建成功:{}", isCreated);
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = isCreated;
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 删除索引
*/
public Object deleteIndex(String indexName) {
Object result = "";
try {
// 新建删除索引请求对象
DeleteIndexRequest request = new DeleteIndexRequest(indexName);
// 执行删除索引
AcknowledgedResponse acknowledgedResponse = restHighLevelClient.indices().delete(request, RequestOptions.DEFAULT);
// 判断是否删除成功
boolean siDeleted = acknowledgedResponse.isAcknowledged();
log.info("是否删除成功:{}", siDeleted);
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = siDeleted;
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
五、文档操作示例
1、Restful 操作示例
增加文档信息
在索引 mydlq-user 中增加一条文档信息。
POST http://localhost:9200/testindex/doc
{
"address": "北京市",
"age": 29,
"birthDate": "1990-01-10",
"createTime": 1579530727699,
"name": "张三",
"remark": "来自北京市的张先生",
"salary": 100
}
//返回
{
"_index": "testindex",
"_type": "doc",
"_id": "hZo5_4oBFE0BmNy_GMUN", //这个是插入生成的随机id
"_version": 1,
"result": "created",
"_shards": {
"total": 1,
"successful": 1,
"failed": 0
},
"_seq_no": 29,
"_primary_term": 3
}
获取文档信息
获取 testindex的索引 id=hZo5_4oBFE0BmNy_GMUN 的文档信息。
GET http://localhost:9200/testindex/doc/hZo5_4oBFE0BmNy_GMUN
//返回
{
"_index": "testindex",
"_type": "doc",
"_id": "hZo5_4oBFE0BmNy_GMUN",
"_version": 1,
"_seq_no": 29,
"_primary_term": 3,
"found": true,
"_source": {
"address": "北京市",
"age": 29,
"birthDate": "1990-01-10",
"createTime": 1579530727699,
"name": "张三",
"remark": "来自北京市的张先生",
"salary": 100
}
}
更新文档信息
更新之前创建的 id=hZo5_4oBFE0BmNy_GMUN 的文档信息。
PUT http://localhost:9200/testindex/doc/hZo5_4oBFE0BmNy_GMUN
//请求
{
"address": "北京市",
"age": 29,
"birthDate": "1990-01-10",
"createTime": 1579530727699,
"name": "张三(改名字)",
"remark": "来自北京市的张先生",
"salary": 100
}
删除文档信息
删除之前创建的 id=hZo5_4oBFE0BmNy_GMUN 的文档信息。
DELETE http://localhost:9200/testindex/doc/hZo5_4oBFE0BmNy_GMUN
2、Java 代码示例
package com.example.elasticsearch.demos.web.service.base;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.DocDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.delete.DeleteRequest;
import org.elasticsearch.action.delete.DeleteResponse;
import org.elasticsearch.action.get.GetRequest;
import org.elasticsearch.action.get.GetResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.index.IndexResponse;
import org.elasticsearch.action.update.UpdateRequest;
import org.elasticsearch.action.update.UpdateResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.xcontent.XContentType;
import org.elasticsearch.search.fetch.subphase.FetchSourceContext;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.Date;
/**
* 文档操作
*/
@Slf4j
@Service
public class DocumentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
public Object existsDocument(DocDto docDto) {
Object result = "";
try {
// 获取请求对象
GetRequest getRequest = new GetRequest(docDto.getIndexName(), docDto.getDocId());
// 是否获取源码内容
getRequest.fetchSourceContext(new FetchSourceContext(false));
// 执行请求,验证文档是否存在
boolean isExist = restHighLevelClient.exists(getRequest, RequestOptions.DEFAULT);
log.info("文档是否存在:{}", isExist);
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = isExist;
} catch (IOException e) {
log.error("", e);
}
return result;
}
public Object getDocument(DocDto docDto) {
Object result = "";
try {
// 获取请求对象
GetRequest getRequest = new GetRequest(docDto.getIndexName(), docDto.getDocId());
// 获取文档信息
GetResponse getResponse = restHighLevelClient.get(getRequest, RequestOptions.DEFAULT);
// 将 JSON 转换成对象
if (getResponse.isExists()) {
UserInfo userInfo = JSON.parseObject(getResponse.getSourceAsBytes(), UserInfo.class);
log.info("用户信息:{}", userInfo);
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = getResponse;
} catch (IOException e) {
log.error("", e);
}
return result;
}
public Object addDocument(DocDto docDto) {
Object result = "";
try {
// 创建索引请求对象
IndexRequest indexRequest = new IndexRequest(docDto.getIndexName());
// 创建用户信息
UserInfo userInfo = new UserInfo();
userInfo.setName(docDto.getName());
userInfo.setAge(docDto.getAge());
userInfo.setSalary(docDto.getSalary());
userInfo.setAddress(docDto.getAddress());
userInfo.setRemark(docDto.getRemark());
userInfo.setCreateTime(new Date());
userInfo.setBirthDate(docDto.getBirthDate());
// 将对象转换为 byte 数组
byte[] json = JSON.toJSONBytes(userInfo);
// 设置文档内容
indexRequest.source(json, XContentType.JSON);
// 执行增加文档
IndexResponse response = restHighLevelClient.index(indexRequest, RequestOptions.DEFAULT);
log.info("创建状态:{}", response.status());
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = response;
} catch (Exception e) {
log.error("", e);
}
return result;
}
public Object updateDocument(DocDto docDto) {
Object result = "";
try {
// 创建索引请求对象
UpdateRequest updateRequest = new UpdateRequest(docDto.getIndexName(), docDto.getDocId());
// UpdateRequest updateRequest = new UpdateRequest(docDto.getIndexName(), "doc", docDto.getDocId());
// 设置用户更新信息
UserInfo userInfo = new UserInfo();
userInfo.setSalary(docDto.getSalary());
userInfo.setAddress(docDto.getAddress());
// 将对象转换为 byte 数组
byte[] json = JSON.toJSONBytes(userInfo);
// 设置更新文档内容
updateRequest.doc(json, XContentType.JSON);
// 执行更新文档
UpdateResponse response = restHighLevelClient.update(updateRequest, RequestOptions.DEFAULT);
log.info("创建状态:{}", response.status());
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = response;
} catch (Exception e) {
log.error("", e);
}
return result;
}
public Object deleteDocument(DocDto docDto) {
Object result = "";
try {
// 创建删除请求对象
DeleteRequest deleteRequest = new DeleteRequest(docDto.getIndexName(), docDto.getDocId());
// 执行删除文档
DeleteResponse response = restHighLevelClient.delete(deleteRequest, RequestOptions.DEFAULT);
log.info("删除状态:{}", response.status());
// 根据具体业务逻辑返回不同结果,这里为了方便直接将结果返回
result = response;
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
六、插入初始化数据
执行查询示例前,先往索引中插入一批数据:
1、单条插入
POST http://localhost:9200/testindex/doc
//请求
{
"name": "零零",
"address": "北京市丰台区",
"remark": "低层员工",
"age": 29,
"salary": 3000,
"birthDate": "1990-11-11",
"createTime": "2019-11-11T08:18:00.000Z"
}
2、批量插入
POST http://localhost:9200/_bulk
//header
Content-Type: application/json
//body
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"刘一","address":"北京市丰台区","remark":"低层员工","age":30,"salary":3000,"birthDate":"1989-11-11","createTime":"2019-03-15T08:18:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"陈二","address":"北京市昌平区","remark":"中层员工","age":27,"salary":7900,"birthDate":"1992-01-25","createTime":"2019-11-08T11:15:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"张三","address":"北京市房山区","remark":"中层员工","age":28,"salary":8800,"birthDate":"1991-10-05","createTime":"2019-07-22T13:22:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"李四","address":"北京市大兴区","remark":"高层员工","age":26,"salary":9000,"birthDate":"1993-08-18","createTime":"2019-10-17T15:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"王五","address":"北京市密云区","remark":"低层员工","age":31,"salary":4800,"birthDate":"1988-07-20","createTime":"2019-05-29T09:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"赵六","address":"北京市通州区","remark":"中层员工","age":32,"salary":6500,"birthDate":"1987-06-02","createTime":"2019-12-10T18:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"孙七","address":"北京市朝阳区","remark":"中层员工","age":33,"salary":7000,"birthDate":"1986-04-15","createTime":"2019-06-06T13:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"周八","address":"北京市西城区","remark":"低层员工","age":32,"salary":5000,"birthDate":"1987-09-26","createTime":"2019-01-26T14:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"吴九","address":"北京市海淀区","remark":"高层员工","age":30,"salary":11000,"birthDate":"1989-11-25","createTime":"2019-09-07T13:34:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"郑十","address":"北京市东城区","remark":"低层员工","age":29,"salary":5000,"birthDate":"1990-12-25","createTime":"2019-03-06T12:08:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"萧十一","address":"北京市平谷区","remark":"低层员工","age":29,"salary":3300,"birthDate":"1990-11-11","createTime":"2019-03-10T08:17:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"曹十二","address":"北京市怀柔区","remark":"中层员工","age":27,"salary":6800,"birthDate":"1992-01-25","createTime":"2019-12-03T11:09:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"吴十三","address":"北京市延庆区","remark":"中层员工","age":25,"salary":7000,"birthDate":"1994-10-05","createTime":"2019-07-27T14:22:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"冯十四","address":"北京市密云区","remark":"低层员工","age":25,"salary":3000,"birthDate":"1994-08-18","createTime":"2019-04-22T15:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"蒋十五","address":"北京市通州区","remark":"低层员工","age":31,"salary":2800,"birthDate":"1988-07-20","createTime":"2019-06-13T10:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"苗十六","address":"北京市门头沟区","remark":"高层员工","age":32,"salary":11500,"birthDate":"1987-06-02","createTime":"2019-11-11T18:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"鲁十七","address":"北京市石景山区","remark":"高员工","age":33,"salary":9500,"birthDate":"1986-04-15","createTime":"2019-06-06T14:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"沈十八","address":"北京市朝阳区","remark":"中层员工","age":31,"salary":8300,"birthDate":"1988-09-26","createTime":"2019-09-25T14:00:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"吕十九","address":"北京市西城区","remark":"低层员工","age":31,"salary":4500,"birthDate":"1988-11-25","createTime":"2019-09-22T13:34:00.000Z"}
{"index":{"_index":"testindex","_type":"doc"}}
{"name":"丁二十","address":"北京市东城区","remark":"低层员工","age":33,"salary":2100,"birthDate":"1986-12-25","createTime":"2019-03-07T12:08:00.000Z"}
3、查询数据
插入完成后再查询数据,查看之前插入的数据是否存在:
GET http://localhost:9200/testindex/_search
//返回
{
"took": 6,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 2,
"relation": "eq"
},
"max_score": 2.302585,
"hits": [
{
"_index": "testindex",
"_type": "doc",
"_id": "3iDh-IoByPOFA_QWinlo",
"_score": 2.302585,
"_source": {
"name": "赵六",
"address": "北京市通州区",
"remark": "中层员工",
"age": 32,
"salary": 6500,
"birthDate": "1987-06-02",
"createTime": "2019-12-10T18:00:00.000Z"
}
},
{
"_index": "testindex",
"_type": "doc",
"_id": "5yDh-IoByPOFA_QWinlo",
"_score": 2.302585,
"_source": {
"name": "蒋十五",
"address": "北京市通州区",
"remark": "低层员工",
"age": 31,
"salary": 2800,
"birthDate": "1988-07-20",
"createTime": "2019-06-13T10:00:00.000Z"
}
}
...
]
}
}
七、查询操作示例
1、精确查询(term)
(1)、Restful 操作示例
精确查询
精确查询,查询地址为 北京市通州区 的人员信息:
查询条件不会进行分词,但是查询内容可能会分词,导致查询不到。之前在创建索引时设置 Mapping 中 address 字段存在 keyword 字段是专门用于不分词查询的子字段。
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"term": {
"address.keyword": {
"value": "北京市通州区"
}
}
}
}
//返回
{
"took": 6,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 2,
"relation": "eq"
},
"max_score": 2.302585,
"hits": [
{
"_index": "testindex",
"_type": "doc",
"_id": "3iDh-IoByPOFA_QWinlo",
"_score": 2.302585,
"_source": {
"name": "赵六",
"address": "北京市通州区",
"remark": "中层员工",
"age": 32,
"salary": 6500,
"birthDate": "1987-06-02",
"createTime": "2019-12-10T18:00:00.000Z"
}
},
{
"_index": "testindex",
"_type": "doc",
"_id": "5yDh-IoByPOFA_QWinlo",
"_score": 2.302585,
"_source": {
"name": "蒋十五",
"address": "北京市通州区",
"remark": "低层员工",
"age": 31,
"salary": 2800,
"birthDate": "1988-07-20",
"createTime": "2019-06-13T10:00:00.000Z"
}
}
...
]
}
}
精确查询-多内容查询
精确查询,查询地址为 北京市丰台区、北京市昌平区 或 北京市大兴区 的人员信息:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"terms": {
"address.keyword": [
"北京市丰台区",
"北京市昌平区",
"北京市大兴区"
]
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.TermsQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.Arrays;
/**
* 精确查询
*/
@Slf4j
@Service
public class TermQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 精确查询(查询条件不会进行分词,但是查询内容可能会分词,导致查询不到)
* @param queryDto
*/
public Object termQuery(TermsQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件(注意:termQuery 支持多种格式查询,如 boolean、int、double、string 等,这里使用的是 string 的查询)
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.termQuery(queryDto.getKey() + ".keyword", queryDto.getValue()));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 多个内容在一个字段中进行查询
* @param queryDto
*/
public Object termsQuery(TermsQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件(注意:termsQuery 支持多种格式查询,如 boolean、int、double、string 等,这里使用的是 string 的查询)
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.termsQuery(queryDto.getKey() + ".keyword", queryDto.getValues()));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
2、匹配查询(match)
(1)、Restful 操作示例
匹配查询全部数据与分页
匹配查询符合条件的所有数据,并且设置以 salary 字段升序排序,并设置分页:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"match_all": {}
},
"from": 0,
"size": 10,
"sort": [
{
"salary": {
"order": "asc"
}
}
]
}
匹配查询数据
匹配查询地址为 通州区 的数据:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"match": {
"address": "通州区"
}
}
}
词语匹配查询
词语匹配进行查询,匹配 address 中为 北京市通州区 的员工信息:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"match_phrase": {
"address": "北京市通州区"
}
}
}
内容多字段查询
查询在字段 address、remark 中存在 北京 内容的员工信息:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"multi_match": {
"query": "北京",
"fields": ["address","remark"]
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.index.query.MatchAllQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.search.sort.SortOrder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 匹配查询
*/
@Slf4j
@Service
public class MatchQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 匹配查询符合条件的所有数据,并设置分页
* @param queryDto
*/
public Object matchAllQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
MatchAllQueryBuilder matchAllQueryBuilder = QueryBuilders.matchAllQuery();
// 创建查询源构造器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(matchAllQueryBuilder);
// 设置分页
searchSourceBuilder.from((queryDto.getRows() - 1) * queryDto.getSize());
searchSourceBuilder.size(queryDto.getSize());
// 设置排序
searchSourceBuilder.sort("salary", SortOrder.ASC);
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 匹配查询数据-or的方式
* @param queryDto
*/
public Object matchQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.matchQuery(queryDto.getKey(), queryDto.getValue()));
// searchSourceBuilder.query(QueryBuilders.matchQuery("address", "通州区"));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 词语匹配查询
* @param queryDto
*/
public Object matchPhraseQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.matchPhraseQuery(queryDto.getKey(), queryDto.getValue()));
// searchSourceBuilder.query(QueryBuilders.matchPhraseQuery("address", "北京市通州区"));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 内容在多字段中进行查询
* @param queryDto
*/
public Object matchMultiQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.multiMatchQuery(queryDto.getKey(), queryDto.getValues()));
// searchSourceBuilder.query(QueryBuilders.multiMatchQuery("北京市", "address", "remark"));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
3、模糊查询(fuzzy)
(1)、Restful 操作示例
模糊查询所有以 三 结尾的姓名
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"fuzzy": {
"name": "三"
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.unit.Fuzziness;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 模糊查询
*/
@Slf4j
@Service
public class FuzzyQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 模糊查询所有以 “三” 结尾的姓名
* @param queryDto
*/
public Object fuzzyQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.fuzzyQuery(queryDto.getKey(), queryDto.getValue()).fuzziness(Fuzziness.AUTO));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
4、范围查询(range)
(1)、Restful 操作示例
查询岁数 ≥ 30 岁的员工数据:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"range": {
"age": {
"gte": 30
}
}
}
}
查询生日距离现在 30 年间的员工数据:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"range": {
"birthDate": {
"gte": "now-30y"
}
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 范围查询
*/
@Slf4j
@Service
public class RangeQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 查询岁数 ≥ 30 岁的员工数据
* @param queryDto
*/
public Object rangeQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.rangeQuery("age").gte(30));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
/**
* 查询距离现在 30 年间的员工数据
* [年(y)、月(M)、星期(w)、天(d)、小时(h)、分钟(m)、秒(s)]
* 例如:
* now-1h 查询一小时内范围
* now-1d 查询一天内时间范围
* now-1y 查询最近一年内的时间范围
* @param queryDto
*/
public Object dateRangeQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
// // includeLower(是否包含下边界)、includeUpper(是否包含上边界)
// searchSourceBuilder.query(QueryBuilders.rangeQuery("birthDate")
// .gte("now-30y").includeLower(true).includeUpper(true));
searchSourceBuilder.query(QueryBuilders.rangeQuery("birthDate").gte(queryDto.getFrom()).lte(queryDto.getEnd()));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
5、通配符查询(wildcard)
(1)、Restful 操作示例
查询所有以 “三” 结尾的姓名:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"wildcard": {
"name.keyword": {
"value": "*三"
}
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 通配符查询
*/
@Slf4j
@Service
public class WildcardQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 查询所有以 “三” 结尾的姓名
* <p>
* *:表示多个字符(0个或多个字符)
* ?:表示单个字符
* @param queryDto
*/
public Object wildcardQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 构建查询条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(QueryBuilders.wildcardQuery(queryDto.getKey() + ".keyword", "*" + queryDto.getValue()));
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
6、布尔查询(bool)
(1)、Restful 操作示例
查询出生在 1990-1995 年期间,且地址在 北京市昌平区、北京市大兴区、北京市房山区 的员工信息:
GET http://localhost:9200/testindex/_search
//请求
{
"query": {
"bool": {
"filter": {
"range": {
"birthDate": {
"format": "yyyy",
"gte": 1990,
"lte": 1995
}
}
},
"must": [
{
"terms": {
"address.keyword": [
"北京市昌平区",
"北京市大兴区",
"北京市房山区"
]
}
}
]
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.query;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.index.query.BoolQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 布尔查询
*/
@Slf4j
@Service
public class BoolQueryService {
@Autowired
private RestHighLevelClient restHighLevelClient;
/**
* 布尔查询
* @param queryDto
*/
public Object boolQuery(MatchQueryDto queryDto) {
Object result = "";
try {
// 创建 Bool 查询构建器
BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery();
// 构建查询条件
boolQueryBuilder.must(QueryBuilders.termsQuery("address.keyword", "北京市昌平区", "北京市大兴区", "北京市房山区"))
.filter().add(QueryBuilders.rangeQuery("birthDate").format("yyyy").gte("1990").lte("1995"));
// 构建查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.query(boolQueryBuilder);
// 创建查询请求对象,将查询对象配置到其中
SearchRequest searchRequest = new SearchRequest(queryDto.getIndexName());
searchRequest.source(searchSourceBuilder);
// 执行查询,然后处理响应结果
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 根据状态和数据条数验证是否返回了数据
if (RestStatus.OK.equals(searchResponse.status()) && searchResponse.getHits().getTotalHits().value > 0) {
SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits) {
// 将 JSON 转换成对象
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
// 输出查询信息
log.info(userInfo.toString());
}
}
result = searchResponse.getHits();
} catch (IOException e) {
log.error("", e);
}
return result;
}
}
八、聚合查询操作示例
1、Metric 聚合分析
(1)、Restful 操作示例
GET http://localhost:9200/testindex/_search
1、统计员工总数、工资最高值、工资最低值、工资平均工资、工资总和:
//请求
{
"size": 0,
"aggs": {
"salary_stats": {
"stats": {
"field": "salary"
}
}
}
}
2、统计员工工资最低值:
//请求
{
"size": 0,
"aggs": {
"salary_min": {
"min": {
"field": "salary"
}
}
}
}
3、统计员工工资最高值:
//请求
{
"size": 0,
"aggs": {
"salary_max": {
"max": {
"field": "salary"
}
}
}
}
4、统计员工工资平均值:
//请求
{
"size": 0,
"aggs": {
"salary_avg": {
"avg": {
"field": "salary"
}
}
}
}
5、统计员工工资总值:
//请求
{
"size": 0,
"aggs": {
"salary_sum": {
"sum": {
"field": "salary"
}
}
}
}
6、统计员工总数:
//请求
{
"size": 0,
"aggs": {
"employee_count": {
"value_count": {
"field": "salary"
}
}
}
}
7、统计员工工资百分位:
//请求
{
"size": 0,
"aggs": {
"salary_percentiles": {
"percentiles": {
"field": "salary"
}
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.aggregation;
import com.example.elasticsearch.demos.web.model.dto.MatchQueryDto;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.aggregations.AggregationBuilder;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.Aggregations;
import org.elasticsearch.search.aggregations.metrics.*;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Component;
import org.springframework.stereotype.Service;
import java.io.IOException;
/**
* 聚合 Metric
*/
@Slf4j
@Service
public class AggrMetricService {
@Autowired
private RestHighLevelClient restHighLevelClient;
@Value("${myindex}")
private String indexName;
/**
* stats 统计员工总数、工资最高值、工资最低值、工资平均工资、工资总和
* @param queryDto
*/
public Object aggregationStats(MatchQueryDto queryDto) {
String responseResult = "";
try {
// 设置聚合条件
String field = queryDto.getKey();
AggregationBuilder aggr = AggregationBuilders.stats(field + "_stats").field(field);
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
// 设置查询结果不返回,只返回聚合结果
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Stats 对象
ParsedStats aggregation = aggregations.get(field + "_stats");
log.info("-------------------------------------------");
log.info("聚合信息: {}", field);
log.info("count:{}", aggregation.getCount());
log.info("avg:{}", aggregation.getAvg());
log.info("max:{}", aggregation.getMax());
log.info("min:{}", aggregation.getMin());
log.info("sum:{}", aggregation.getSum());
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* min 统计员工工资最低值
*/
public Object aggregationMin() {
String responseResult = "";
try {
// 设置聚合条件
AggregationBuilder aggr = AggregationBuilders.min("salary_min").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Min 对象
ParsedMin aggregation = aggregations.get("salary_min");
log.info("-------------------------------------------");
log.info("聚合信息:");
log.info("min:{}", aggregation.getValue());
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* max 统计员工工资最高值
*/
public Object aggregationMax() {
String responseResult = "";
try {
// 设置聚合条件
AggregationBuilder aggr = AggregationBuilders.max("salary_max").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Max 对象
ParsedMax aggregation = aggregations.get("salary_max");
log.info("-------------------------------------------");
log.info("聚合信息:");
log.info("max:{}", aggregation.getValue());
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* avg 统计员工工资平均值
*/
public Object aggregationAvg() {
String responseResult = "";
try {
// 设置聚合条件
AggregationBuilder aggr = AggregationBuilders.avg("salary_avg").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Avg 对象
ParsedAvg aggregation = aggregations.get("salary_avg");
log.info("-------------------------------------------");
log.info("聚合信息:");
log.info("avg:{}", aggregation.getValue());
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* sum 统计员工工资总值
*/
public Object aggregationSum() {
String responseResult = "";
try {
// 设置聚合条件
SumAggregationBuilder aggr = AggregationBuilders.sum("salary_sum").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Sum 对象
ParsedSum aggregation = aggregations.get("salary_sum");
log.info("-------------------------------------------");
log.info("聚合信息:");
log.info("sum:{}", String.valueOf((aggregation.getValue())));
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* count 统计员工总数
*/
public Object aggregationCount() {
String responseResult = "";
try {
// 设置聚合条件
AggregationBuilder aggr = AggregationBuilders.count("employee_count").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 ValueCount 对象
ParsedValueCount aggregation = aggregations.get("employee_count");
log.info("-------------------------------------------");
log.info("聚合信息:");
log.info("count:{}", aggregation.getValue());
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
/**
* percentiles 统计员工工资百分位
*/
public Object aggregationPercentiles() {
String responseResult = "";
try {
// 设置聚合条件
AggregationBuilder aggr = AggregationBuilders.percentiles("salary_percentiles").field("salary");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.aggregation(aggr);
searchSourceBuilder.size(0);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status()) || aggregations != null) {
// 转换为 Percentiles 对象
ParsedPercentiles aggregation = aggregations.get("salary_percentiles");
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Percentile percentile : aggregation) {
log.info("百分位:{}:{}", percentile.getPercent(), percentile.getValue());
}
log.info("-------------------------------------------");
}
// 根据具体业务逻辑返回不同结果,这里为了方便直接将返回响应对象Json串
responseResult = response.toString();
} catch (IOException e) {
log.error("", e);
}
return responseResult;
}
}
2、Bucket 聚合分析
(1)、Restful 操作示例
GET http://localhost:9200/testindex/_search
1、按岁数进行聚合分桶,统计各个岁数员工的人数:
//请求
{
"size": 0,
"aggs": {
"age_bucket": {
"terms": {
"field": "age",
"size": "10"
}
}
}
}
2、按工资范围进行聚合分桶,统计工资在 3000-5000、5000-9000 和 9000 以上的员工信息:
//请求
{
"aggs": {
"salary_range_bucket": {
"range": {
"field": "salary",
"ranges": [
{
"key": "低级员工",
"to": 3000
},{
"key": "中级员工",
"from": 5000,
"to": 9000
},{
"key": "高级员工",
"from": 9000
}
]
}
}
}
}
3、按照时间范围进行分桶,统计 1985-1990 年和 1990-1995 年出生的员工信息:
//请求
{
"size": 10,
"aggs": {
"date_range_bucket": {
"date_range": {
"field": "birthDate",
"format": "yyyy",
"ranges": [
{
"key": "出生日期1985-1990的员工",
"from": "1985",
"to": "1990"
},{
"key": "出生日期1990-1995的员工",
"from": "1990",
"to": "1995"
}
]
}
}
}
}
4、按工资多少进行聚合分桶,设置统计的最小值为 0,最大值为 12000,区段间隔为 3000:
//请求
{
"size": 0,
"aggs": {
"salary_histogram": {
"histogram": {
"field": "salary",
"extended_bounds": {
"min": 0,
"max": 12000
},
"interval": 3000
}
}
}
}
5、按出生日期进行分桶:
//请求
{
"size": 0,
"aggs": {
"birthday_histogram": {
"date_histogram": {
"format": "yyyy",
"field": "birthDate",
"interval": "year"
}
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.aggregation;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.aggregations.AggregationBuilder;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.Aggregations;
import org.elasticsearch.search.aggregations.bucket.histogram.DateHistogramInterval;
import org.elasticsearch.search.aggregations.bucket.histogram.Histogram;
import org.elasticsearch.search.aggregations.bucket.range.Range;
import org.elasticsearch.search.aggregations.bucket.terms.Terms;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
/**
* 聚合 Bucket
*/
@Slf4j
@Service
public class AggrBucketService {
@Autowired
private RestHighLevelClient restHighLevelClient;
@Value("${myindex}")
private String indexName;
/**
* 按岁数进行聚合分桶,统计各个岁数员工的人数:
*/
public Object aggrBucketTerms() {
Map<String, Long> keyCountMap = new HashMap<>();
try {
AggregationBuilder aggr = AggregationBuilders.terms("age_bucket").field("age");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(10);
searchSourceBuilder.aggregation(aggr);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Terms byCompanyAggregation = aggregations.get("age_bucket");
List<? extends Terms.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Terms.Bucket bucket : buckets) {
keyCountMap.put(bucket.getKeyAsString(), bucket.getDocCount());
log.info("桶名:{} | 总数:{}", bucket.getKeyAsString(), bucket.getDocCount());
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return keyCountMap;
}
/**
* 按工资范围进行聚合分桶,统计工资在 3000-5000、5000-9000 和 9000 以上的员工信息:
*/
public Object aggrBucketRange() {
Map<String, Long> keyCountMap = new HashMap<>();
try {
AggregationBuilder aggr = AggregationBuilders.range("salary_range_bucket")
.field("salary")
.addUnboundedTo("低级员工", 3000)
.addRange("中级员工", 5000, 9000)
.addUnboundedFrom("高级员工", 9000);
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.aggregation(aggr);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Range byCompanyAggregation = aggregations.get("salary_range_bucket");
List<? extends Range.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Range.Bucket bucket : buckets) {
keyCountMap.put(bucket.getKeyAsString(), bucket.getDocCount());
log.info("桶名:{} | 总数:{}", bucket.getKeyAsString(), bucket.getDocCount());
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return keyCountMap;
}
/**
* 按照时间范围进行分桶,统计 1985-1990 年和 1990-1995 年出生的员工信息:
*/
public Object aggrBucketDateRange() {
Map<String, Long> keyCountMap = new HashMap<>();
try {
AggregationBuilder aggr = AggregationBuilders.dateRange("date_range_bucket")
.field("birthDate")
.format("yyyy")
.addRange("出生日期1985-1990的员工", "1985", "1990")
.addRange("出生日期1990-1995的员工", "1990", "1995");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.aggregation(aggr);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Range byCompanyAggregation = aggregations.get("date_range_bucket");
List<? extends Range.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Range.Bucket bucket : buckets) {
keyCountMap.put(bucket.getKeyAsString(), bucket.getDocCount());
log.info("桶名:{} | 总数:{}", bucket.getKeyAsString(), bucket.getDocCount());
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return keyCountMap;
}
/**
* 按工资多少进行聚合分桶
*/
public Object aggrBucketHistogram() {
Map<String, Long> keyCountMap = new HashMap<>();
try {
//按工资多少进行聚合分桶,设置统计的最小值为 0,最大值为 12000,区段间隔为 3000:
AggregationBuilder aggr = AggregationBuilders.histogram("salary_histogram")
.field("salary")
.extendedBounds(0, 12000)
.interval(3000);
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.aggregation(aggr);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Histogram byCompanyAggregation = aggregations.get("salary_histogram");
List<? extends Histogram.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Histogram.Bucket bucket : buckets) {
keyCountMap.put(bucket.getKeyAsString(), bucket.getDocCount());
log.info("桶名:{} | 总数:{}", bucket.getKeyAsString(), bucket.getDocCount());
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return keyCountMap;
}
/**
* 按出生日期进行分桶:
*/
public Object aggrBucketDateHistogram() {
Map<String, Long> keyCountMap = new HashMap<>();
try {
AggregationBuilder aggr = AggregationBuilders.dateHistogram("birthday_histogram")
.field("birthDate")
.interval(1)
.dateHistogramInterval(DateHistogramInterval.YEAR)
.format("yyyy");
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.aggregation(aggr);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Histogram byCompanyAggregation = aggregations.get("birthday_histogram");
List<? extends Histogram.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Histogram.Bucket bucket : buckets) {
keyCountMap.put(bucket.getKeyAsString(), bucket.getDocCount());
log.info("桶名:{} | 总数:{}", bucket.getKeyAsString(), bucket.getDocCount());
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return keyCountMap;
}
}
3、Metric 与 Bucket 聚合分析
(1)、Restful 操作示例
按照员工岁数分桶、然后统计每个岁数员工工资最高值:
GET http://localhost:9200/testindex/_search
//请求
{
"size": 0,
"aggs": {
"salary_bucket": {
"terms": {
"field": "age",
"size": "10"
},
"aggs": {
"salary_max_user": {
"top_hits": {
"size": 1,
"sort": [
{
"salary": {
"order": "desc"
}
}
]
}
}
}
}
}
}
(2)、Java 代码示例
package com.example.elasticsearch.demos.web.service.aggregation;
import com.alibaba.fastjson.JSON;
import com.example.elasticsearch.demos.web.model.entity.UserInfo;
import lombok.extern.slf4j.Slf4j;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.aggregations.AggregationBuilder;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.Aggregations;
import org.elasticsearch.search.aggregations.bucket.terms.Terms;
import org.elasticsearch.search.aggregations.metrics.ParsedTopHits;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.search.sort.SortOrder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
/**
* 聚合 Bucket 与 Metric
*/
@Slf4j
@Service
public class AggrBucketMetricService {
@Autowired
private RestHighLevelClient restHighLevelClient;
@Value("${myindex}")
private String indexName;
/**
* topHits 按照员工岁数分桶、然后统计每个岁数员工工资最高值
*/
public Object aggregationTopHits() {
Map<String, Float> ageMaxSalaryMap = new HashMap<>();
try {
AggregationBuilder testTop = AggregationBuilders.topHits("salary_max_user")
.size(1)
.sort("salary", SortOrder.DESC);
AggregationBuilder salaryBucket = AggregationBuilders.terms("salary_bucket")
.field("age")
.size(10);
salaryBucket.subAggregation(testTop);
// 查询源构建器
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.aggregation(salaryBucket);
// 创建查询请求对象,将查询条件配置到其中
SearchRequest request = new SearchRequest(indexName);
request.source(searchSourceBuilder);
// 执行请求
SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
// 获取响应中的聚合信息
Aggregations aggregations = response.getAggregations();
// 输出内容
if (RestStatus.OK.equals(response.status())) {
// 分桶
Terms byCompanyAggregation = aggregations.get("salary_bucket");
List<? extends Terms.Bucket> buckets = byCompanyAggregation.getBuckets();
// 输出各个桶的内容
log.info("-------------------------------------------");
log.info("聚合信息:");
for (Terms.Bucket bucket : buckets) {
log.info("桶名:{}", bucket.getKeyAsString());
ParsedTopHits topHits = bucket.getAggregations().get("salary_max_user");
for (SearchHit hit : topHits.getHits()) {
UserInfo userInfo = JSON.parseObject(hit.getSourceAsString(), UserInfo.class);
ageMaxSalaryMap.put(bucket.getKeyAsString(), userInfo.getSalary());
log.info(hit.getSourceAsString());
}
}
log.info("-------------------------------------------");
}
} catch (IOException e) {
log.error("", e);
}
return ageMaxSalaryMap;
}
}
九、项目源码及对应ES安装包
1、elasticsearch-7.6.1安装包
elasticsearch7.6.1https://download.csdn.net/download/asd051377305/88397087
2、项目源代码
基于SpringBoot+elasticsearch的操作项目https://download.csdn.net/download/asd051377305/88397090
版权归原作者 Venlenter 所有, 如有侵权,请联系我们删除。