使用ElasticSearch完成百万级数据查询附近的人功能

上一篇文章介绍了ElasticSearch使用Repository和ElasticSearchTemplate完成构建复杂查询条件，简单介绍了ElasticSearch使用地理位置的功能。

这一篇我们来看一下使用ElasticSearch完成大数据量查询附近的人功能，搜索N米范围的内的数据。

准备环境

本机测试使用了ElasticSearch最新版5.5.1，SpringBoot1.5.4，spring-data-ElasticSearch2.1.4.

新建Springboot项目，勾选ElasticSearch和web。

pom文件如下

<?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 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>com.tianyalei</groupId>
	<artifactId>elasticsearch</artifactId>
	<version>0.0.1-SNAPSHOT</version>
	<packaging>jar</packaging>

	<name>elasticsearch</name>
	<description>Demo project for Spring Boot</description>

	<parent>
		<groupId>org.springframework.boot</groupId>
		<artifactId>spring-boot-starter-parent</artifactId>
		<version>1.5.4.RELEASE</version>
		<relativePath/> <!-- lookup parent from repository -->
	</parent>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
		<java.version>1.8</java.version>
	</properties>

	<dependencies>
		<dependency>
			<groupId>org.springframework.boot</groupId>
			<artifactId>spring-boot-starter-data-elasticsearch</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>
		<dependency>
			<groupId>com.sun.jna</groupId>
			<artifactId>jna</artifactId>
			<version>3.0.9</version>
		</dependency>
	</dependencies>

	<build>
		<plugins>
			<plugin>
				<groupId>org.springframework.boot</groupId>
				<artifactId>spring-boot-maven-plugin</artifactId>
			</plugin>
		</plugins>
	</build>

</project>

新建model类Person

package com.tianyalei.elasticsearch.model;

import org.springframework.data.annotation.Id;
import org.springframework.data.elasticsearch.annotations.Document;
import org.springframework.data.elasticsearch.annotations.GeoPointField;

import java.io.Serializable;

/**
 * model类
 */
@Document(indexName="elastic_search_project",type="person",indexStoreType="fs",shards=5,replicas=1,refreshInterval="-1")
public class Person implements Serializable {
    @Id
    private int id;

    private String name;

    private String phone;

    /**
     * 地理位置经纬度
     * lat纬度，lon经度 "40.715,-74.011"
     * 如果用数组则相反[-73.983, 40.719]
     */
    @GeoPointField
    private String address;

    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public String getPhone() {
        return phone;
    }

    public void setPhone(String phone) {
        this.phone = phone;
    }

    public String getAddress() {
        return address;
    }

    public void setAddress(String address) {
        this.address = address;
    }
}

我用address字段表示经纬度位置。注意，使用String[]和String分别来表示经纬度时是不同的，见注释。

import com.tianyalei.elasticsearch.model.Person;
import org.springframework.data.elasticsearch.repository.ElasticsearchRepository;

public interface PersonRepository extends ElasticsearchRepository<Person, Integer> {

}

看一下Service类，完成插入测试数据的功能，查询的功能我放在Controller里了，为了方便查看，正常是应该放在Service里

package com.tianyalei.elasticsearch.service;

import com.tianyalei.elasticsearch.model.Person;
import com.tianyalei.elasticsearch.repository.PersonRepository;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.elasticsearch.core.ElasticsearchTemplate;
import org.springframework.data.elasticsearch.core.query.IndexQuery;
import org.springframework.stereotype.Service;

import java.util.ArrayList;
import java.util.List;

@Service
public class PersonService {
    @Autowired
    PersonRepository personRepository;
    @Autowired
    ElasticsearchTemplate elasticsearchTemplate;

    private static final String PERSON_INDEX_NAME = "elastic_search_project";
    private static final String PERSON_INDEX_TYPE = "person";

    public Person add(Person person) {
        return personRepository.save(person);
    }

    public void bulkIndex(List<Person> personList) {
        int counter = 0;
        try {
            if (!elasticsearchTemplate.indexExists(PERSON_INDEX_NAME)) {
                elasticsearchTemplate.createIndex(PERSON_INDEX_TYPE);
            }
            List<IndexQuery> queries = new ArrayList<>();
            for (Person person : personList) {
                IndexQuery indexQuery = new IndexQuery();
                indexQuery.setId(person.getId() + "");
                indexQuery.setObject(person);
                indexQuery.setIndexName(PERSON_INDEX_NAME);
                indexQuery.setType(PERSON_INDEX_TYPE);

                //上面的那几步也可以使用IndexQueryBuilder来构建
                //IndexQuery index = new IndexQueryBuilder().withId(person.getId() + "").withObject(person).build();

                queries.add(indexQuery);
                if (counter % 500 == 0) {
                    elasticsearchTemplate.bulkIndex(queries);
                    queries.clear();
                    System.out.println("bulkIndex counter : " + counter);
                }
                counter++;
            }
            if (queries.size() > 0) {
                elasticsearchTemplate.bulkIndex(queries);
            }
            System.out.println("bulkIndex completed.");
        } catch (Exception e) {
            System.out.println("IndexerService.bulkIndex e;" + e.getMessage());
            throw e;
        }
    }
}

注意看bulkIndex方法，这个是批量插入数据用的，bulk也是ES官方推荐使用的批量插入数据的方法。这里是每逢500的整数倍就bulk插入一次。

package com.tianyalei.elasticsearch.controller;

import com.tianyalei.elasticsearch.model.Person;
import com.tianyalei.elasticsearch.service.PersonService;
import org.elasticsearch.common.unit.DistanceUnit;
import org.elasticsearch.index.query.GeoDistanceQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.sort.GeoDistanceSortBuilder;
import org.elasticsearch.search.sort.SortBuilders;
import org.elasticsearch.search.sort.SortOrder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.domain.PageRequest;
import org.springframework.data.domain.Pageable;
import org.springframework.data.elasticsearch.core.ElasticsearchTemplate;
import org.springframework.data.elasticsearch.core.query.NativeSearchQueryBuilder;
import org.springframework.data.elasticsearch.core.query.SearchQuery;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;

import java.text.DecimalFormat;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;

@RestController
public class PersonController {
    @Autowired
    PersonService personService;
    @Autowired
    ElasticsearchTemplate elasticsearchTemplate;

    @GetMapping("/add")
    public Object add() {
        double lat = 39.929986;
        double lon = 116.395645;

        List<Person> personList = new ArrayList<>(900000);
        for (int i = 100000; i < 1000000; i++) {
            double max = 0.00001;
            double min = 0.000001;
            Random random = new Random();
            double s = random.nextDouble() % (max - min + 1) + max;
            DecimalFormat df = new DecimalFormat("######0.000000");
            // System.out.println(s);
            String lons = df.format(s + lon);
            String lats = df.format(s + lat);
            Double dlon = Double.valueOf(lons);
            Double dlat = Double.valueOf(lats);

            Person person = new Person();
            person.setId(i);
            person.setName("名字" + i);
            person.setPhone("电话" + i);
            person.setAddress(dlat + "," + dlon);

            personList.add(person);
        }
        personService.bulkIndex(personList);

//        SearchQuery searchQuery = new NativeSearchQueryBuilder().withQuery(QueryBuilders.queryStringQuery("spring boot OR 书籍")).build();
//        List<Article> articles = elas、ticsearchTemplate.queryForList(se、archQuery, Article.class);
//        for (Article article : articles) {
//            System.out.println(article.toString());
//        }

        return "添加数据";
    }

    /**
     *
     geo_distance: 查找距离某个中心点距离在一定范围内的位置
     geo_bounding_box: 查找某个长方形区域内的位置
     geo_distance_range: 查找距离某个中心的距离在min和max之间的位置
     geo_polygon: 查找位于多边形内的地点。
     sort可以用来排序
     */
    @GetMapping("/query")
    public Object query() {
        double lat = 39.929986;
        double lon = 116.395645;

        Long nowTime = System.currentTimeMillis();
        //查询某经纬度100米范围内
        GeoDistanceQueryBuilder builder = QueryBuilders.geoDistanceQuery("address").point(lat, lon)
                .distance(100, DistanceUnit.METERS);

        GeoDistanceSortBuilder sortBuilder = SortBuilders.geoDistanceSort("address")
                .point(lat, lon)
                .unit(DistanceUnit.METERS)
                .order(SortOrder.ASC);

        Pageable pageable = new PageRequest(0, 50);

        NativeSearchQueryBuilder builder1 = new NativeSearchQueryBuilder().withFilter(builder).withSort(sortBuilder).withPageable(pageable);
        SearchQuery searchQuery = builder1.build();

        //queryForList默认是分页，走的是queryForPage，默认10个
        List<Person> personList = elasticsearchTemplate.queryForList(searchQuery, Person.class);

        System.out.println("耗时：" + (System.currentTimeMillis() - nowTime));
        return personList;
    }
}

看Controller类，在add方法中，我们插入90万条测试数据，随机产生不同的经纬度地址。

在查询方法中，我们构建了一个查询100米范围内、按照距离远近排序，分页每页50条的查询条件。如果不指明Pageable的话，ESTemplate的queryForList默认是10条，通过源码可以看到。

启动项目，先执行add，等待百万数据插入，大概几十秒。

然后执行查询，看一下结果。

第一次查询花费300多ms，再次查询后时间就大幅下降，到30ms左右，因为ES已经自动缓存到内存了。

可见，ES完成地理位置的查询还是非常快的。适用于查询附近的人、范围查询之类的功能。

参考：ES根据地理位置查询 http://blog.csdn.net/bingduanlbd/article/details/52253542