ElasticSearch API教程

一、ElasticSearch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用户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。

二、ElasticSearch编程操作

确保已经安装ElasticSearch，创建一个maven工程。

首先实现创建索引和映射。

• pom.xml

<?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.lxt</groupId>
    <artifactId>es-demo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.elasticsearch</groupId>
            <artifactId>elasticsearch</artifactId>
            <version>5.6.8</version>
        </dependency>
        <dependency>
            <groupId>org.elasticsearch.client</groupId>
            <artifactId>transport</artifactId>
            <version>5.6.8</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.9.1</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>1.7.24</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-simple</artifactId>
            <version>1.7.21</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.12</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
    </dependencies>

</project>

• ElasticSearchClientTest

public class ElasticSearchClientTest {

    TransportClient client;

    @Before
    public void init() throws Exception {
        //1.配置
        Settings settings = Settings.builder().put("cluster.name", "my-application").build();
        //2.客户端
        client = new PreBuiltTransportClient(settings);
        client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("192.168.0.111"),9300));
    }

    @Test
    public void createIndex() throws Exception{
        //3.使用api创建索引
        client.admin().indices().prepareCreate("index_hello").get();

        //4.关闭client
        client.close();
    }

    @Test
    public void setMappings() throws Exception{
        XContentBuilder builder = XContentFactory.jsonBuilder()
                .startObject()
                .startObject("article")
                .startObject("properties")
                .startObject("id")
                .field("type","integer").field("store","yes")
                .endObject()
                .startObject("title")
                .field("type","string").field("store","yes").field("analyzer","ik_smart")
                .endObject()
                .startObject("content")
                .field("type","string").field("store","yes").field("analyzer","ik_smart")
                .endObject()
                .endObject()
                .endObject()
                .endObject();

        //3.使用api创建映射
        client.admin().indices().preparePutMapping("index_hello").setType("article").setSource(builder).get();

        //4.关闭client
        client.close();
    }
}

接下来构建document对象，添加jackson依赖。

<dependency>
    <groupId>com.fasterxml.jackson.core</groupId>
    <artifactId>jackson-core</artifactId>
    <version>2.8.1</version>
</dependency>
<dependency>
    <groupId>com.fasterxml.jackson.core</groupId>
    <artifactId>jackson-databind</artifactId>
    <version>2.8.1</version>
</dependency>
<dependency>
    <groupId>com.fasterxml.jackson.core</groupId>
    <artifactId>jackson-annotations</artifactId>
    <version>2.8.1</version>
</dependency>

• ElasticSearchClientTest

/**
 * 使用XContentBuilder构建Document对象
 * @throws Exception
 */
@Test
public void testAddDocument() throws Exception{
    //创建一个client对象
    //创建一个文档对象
    XContentBuilder builder = XContentFactory.jsonBuilder()
            .startObject()
            .field("id",2l)
            .field("title","北方入秋速度明显加快 多地降温幅度最多可达10度22222")
            .field("content","阿联酋一架客机在纽约机场被隔离 10名乘客病倒")
            .endObject();
    //把文档对象添加到索引库
    client.prepareIndex()
            //设置索引名称
            .setIndex("index_hello")
            //设置type
            .setType("article")
            //设置文档的id，如果不设置的话自动地生成一个id
            .setId("2")
            //设置文档信息
            .setSource(builder)
            //执行操作
            .get();
    //关闭客户端
    client.close();
}

@Test
public void testAddDocument2() throws Exception{
    //创建一个Article对象
    Article article = new Article();
    //设置对象的属性
    article.setId(3);
    article.setTitle("MH370坠毁在柬埔寨密林?中国一公司调十颗卫星去拍摄");
    article.setContent("警惕荒唐的死亡游戏!俄15岁少年输掉游戏后用电锯自杀");
    ObjectMapper objectMapper = new ObjectMapper();
    String json = objectMapper.writeValueAsString(article);
    //把文档对象添加到索引库
    client.prepareIndex()
            //设置索引名称
            .setIndex("index_hello")
            //设置type
            .setType("article")
            //设置文档的id，如果不设置的话自动地生成一个id
            .setId("3")
            //设置文档信息
            .setSource(json, XContentType.JSON)
            //执行操作
            .get();
    //关闭客户端
    client.close();
}

@Test
public void testAddDocument3() throws Exception{
    for (int i = 4; i < 100; i++) {
        //创建一个Article对象
        Article article = new Article();
        //设置对象的属性
        article.setId(i);
        article.setTitle("女护士路遇昏迷男子跪地抢救：救人是职责更是本能" + i);
        article.setContent("江西变质营养餐事件已致24人就医 多名官员被调查" + i);
        //把article对象转化成json格式的字符串
        ObjectMapper objectMapper = new ObjectMapper();
        String jsonDocument = objectMapper.writeValueAsString(article);
        System.out.println(jsonDocument);
        //使用client对象把文档写入索引库
        client.prepareIndex("index_hello","article",i + "")
                .setSource(jsonDocument,XContentType.JSON)
                .get();
    }
    //关闭客户端
    client.close();
}

• Article

public class Article {

    private Integer id;
    private String title;
    private String content;
		...
}

操作查询API。

• IndexSearch

public class IndexSearch {

    TransportClient client;

    @Before
    public void init() throws Exception {
        //1.配置
        Settings settings = Settings.builder().put("cluster.name", "my-application").build();
        //2.客户端
        client = new PreBuiltTransportClient(settings);
        client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("192.168.0.111"),9300));
    }

    private void search(QueryBuilder queryBuilder) {
        //2.执行查询
        SearchResponse searchResponse = client.prepareSearch("index_hello")
                .setTypes("article")
                .setQuery(queryBuilder)
                .get();
        //3.处理结果
        SearchHits searchHits = searchResponse.getHits();
        System.out.println("总行数: " + searchHits.getTotalHits());
        Iterator<SearchHit> it = searchHits.iterator();
        while (it.hasNext()) {
            SearchHit searchHit = it.next();
            //source->document的json输出
            System.out.println(searchHit.getSourceAsString());
            System.out.println("----文档属性----");
            Map<String, Object> document = searchHit.getSource();
            System.out.println(document.get("id"));
            System.out.println(document.get("title"));
            System.out.println(document.get("content"));
        }
    }

    /**
     * 1.term查询
     * @throws Exception
     */
    @Test
    public void testQueryByTeam() throws Exception {
        //1.构建queryBuilder
        QueryBuilder queryBuilder = QueryBuilders.termQuery("title","女护士");
        search(queryBuilder);
    }

    /**
     * 2.queryStringQuery查询
     * @throws Exception
     */
    @Test
    public void testQueryByQueryString() throws Exception {
        //1.构建queryBuilder
        QueryBuilder queryBuilder = QueryBuilders.queryStringQuery("美丽的女护士").defaultField("title");
        //2.执行查询
        search(queryBuilder);
    }

    /**
     * 3.matchQuery查询
     * @throws Exception
     */
    @Test
    public void testQueryByMatchQuery() throws Exception {
        //1.构建queryBuilder
        QueryBuilder queryBuilder = QueryBuilders.matchQuery("title","美丽的女护士");
        //2.执行查询
        search(queryBuilder);
    }

    /**
     * 4.按照id查询
     * @throws Exception
     */
    @Test
    public void testSearchById() throws Exception {
        //1.构建queryBuilder
        QueryBuilder queryBuilder = QueryBuilders.idsQuery().addIds("1","2");
        search(queryBuilder);
    }

    /**
     * 5.分页查询
     * @throws Exception
     */
    @Test
    public void testSearchByMatchAll() throws Exception {
        //1.构建queryBuilder
        QueryBuilder queryBuilder = QueryBuilders.matchAllQuery();
        //2.执行查询
        SearchResponse searchResponse = client.prepareSearch("index_hello")
                .setTypes("article")
                .setQuery(queryBuilder)
                .setFrom(0)
                .setSize(5)
                .get();
        //3.处理结果
        SearchHits searchHits = searchResponse.getHits();
        System.out.println("总行数: " + searchHits.getTotalHits());
        Iterator<SearchHit> it = searchHits.iterator();
        while (it.hasNext()) {
            SearchHit searchHit = it.next();
            //source->document的json输出
            System.out.println(searchHit.getSourceAsString());
            System.out.println("----文档属性----");
            Map<String, Object> document = searchHit.getSource();
            System.out.println(document.get("id"));
            System.out.println(document.get("title"));
            System.out.println(document.get("content"));
        }
    }
}

在每个搜索结果中 高亮 部分文本片段，以便让用户知道为何该文档符合查询条件。在 Elasticsearch 中检索出高亮片段也很容易。

•  IndexSearch

/**
 * 6.高亮查询
 * @throws Exception
 */
@Test
public void testSearchByHighLight() throws Exception {
    //1.构建queryBuilder
//    QueryBuilder queryBuilder = QueryBuilders.matchQuery("title","北方");
    QueryBuilder queryBuilder = QueryBuilders.multiMatchQuery("10","title","content");

    HighlightBuilder highlightBuilder = new HighlightBuilder();
    highlightBuilder.field("title");
    highlightBuilder.field("content");
    highlightBuilder.preTags("<em>");
    highlightBuilder.postTags("</em>");

    //2.执行查询
    SearchResponse searchResponse = client.prepareSearch("index_hello")
            .setTypes("article")
            .setQuery(queryBuilder)
            .highlighter(highlightBuilder)
            .get();
    //3.处理结果
    SearchHits searchHits = searchResponse.getHits();
    System.out.println("总行数: " + searchHits.getTotalHits());
    Iterator<SearchHit> it = searchHits.iterator();
    while (it.hasNext()) {
        SearchHit searchHit = it.next();
        //source->document的json输出
        System.out.println("----文档内容----");
        System.out.println(searchHit.getSourceAsString());
        System.out.println("----高亮结果----");
        Map<String, HighlightField> highlightFields = searchHit.getHighlightFields();
        for(Map.Entry<String, HighlightField> entry : highlightFields.entrySet()) {
            System.out.println(entry.getKey() + ":\t" + Arrays.toString(entry.getValue().getFragments()));
        }
    }
}

三、Spring Data ElasticSearch

Spring Data是一个用于简化数据库访问的开源框架，Spring Data ElasticSearch是Spring Data家族中的一个引擎。

用Spring Initializr创建工程。

• pom.xml

<?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>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.1.16.RELEASE</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.lxt</groupId>
    <artifactId>es-demo2</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>es-demo2</name>
    <description>Demo project for Spring Boot</description>
    <properties>
        <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-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>

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

</project>

• application.yml

spring:
  data:
    elasticsearch:
      cluster-name: my-application
      cluster-nodes: 192.168.0.111:9300

• Article

@Document(indexName = "lxt_blog", type = "article")
public class Article {

    @Id
    @Field(type = FieldType.Long, store = true)
    private Long id;
    @Field(type = FieldType.Text, store = true, analyzer = "ik_smart")
    private String title;
    @Field(type = FieldType.Text, store = true, analyzer = "ik_smart")
    private String content;
		...
}

• ArticleDao

public interface ArticleDao extends ElasticsearchRepository<Article,Long> {

    public List<Article> findByTitleLike(String title);

    public List<Article> findByTitle(String title);

    public List<Article> findByTitleLikeOrContent(String title, String content);

    public List<Article> findByTitleOrContent(String title, String content, Pageable pageable);
}

• EsDemo2ApplicationTests

@RunWith(SpringRunner.class)
@SpringBootTest
public class EsDemo2ApplicationTests {

    @Autowired
    private ArticleDao dao;

    @Autowired
    private ElasticsearchTemplate template;

    /**
     * 创建索引
     */
    @Test
    public void createIndex() {
        template.createIndex(Article.class);

        //配置mapping
//        template.putMapping(Article.class);
    }

    /**
     * 增加数据
     * @throws Exception
     */
    @Test
    public void addDocument() throws Exception {
        for (int i = 1; i <= 20; i++) {
            //创建一个Article对象
            Article article = new Article();
            article.setId(new Long(i));
            article.setTitle("女护士路遇昏迷男子跪地抢救：救人是职责更是本能" + i);
            article.setContent("这是一个美丽的女护士妹妹" + i);
            //把文档写入索引库
            dao.save(article);
        }
    }

    /**
     * 删除数据
     * @throws Exception
     */
    @Test
    public void deleteDocumentById() throws Exception {
        dao.deleteById(3l);
    }

    /**
     * 查询所有
     */
    @Test
    public void findAll() {
        dao.findAll().forEach(System.out :: println);
    }

    /**
     * 查询单个
     */
    @Test
    public void findById() {
        System.out.println(dao.findById(1l));
    }

    /**
     * 查询标题
     */
    @Test
    public void findByTitle() {
        dao.findByTitle("美丽女护士").forEach(System.out :: println);  //使用match查询
    }

    /**
     * 查询标题和内容
     */
    @Test
    public void findByTitleOrContent() {
        //加like的话就会分词
        dao.findByTitleLikeOrContent("美丽女护士","女护士").forEach(System.out :: println);
    }

    /**
     * 分页查询
     */
    @Test
    public void findByTitlePage() {
        Pageable pageable = PageRequest.of(1,5);
        dao.findByTitleOrContent("女护士","女护士",pageable).forEach(System.out :: println);
    }

    /**
     * 本地查询，用原来的方法
     * @throws Exception
     */
    @Test
    public void testNativeSearchQuery() throws Exception {
        NativeSearchQuery query = new NativeSearchQueryBuilder()
                .withQuery(QueryBuilders.queryStringQuery("女护士").defaultField("title"))
                .withPageable(PageRequest.of(1,5))
                .build();
        template.queryForList(query,Article.class).forEach(System.out :: println);
    }
}