Elasticsearch 总结

1.Maven配置

<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>3.8.1</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>org.elasticsearch</groupId>
			<artifactId>elasticsearch</artifactId>
			<version>5.6.1</version>
		</dependency>

		<dependency>
			<groupId>org.elasticsearch.client</groupId>
			<artifactId>transport</artifactId>
			<version>5.6.1</version>
		</dependency>

		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-core</artifactId>
			<version>2.9.0</version>
		</dependency>
	</dependencies>

2.log4j2报错

<?xml version="1.0" encoding="UTF-8"?>
<Configuration status="warn">
    <Appenders>
        <Console name="Console" target="SYSTEM_OUT">
            <PatternLayout pattern="%m%n"/>
        </Console>
    </Appenders>
    <Loggers>
        <Root level="INFO">
            <AppenderRef ref="Console"/>
        </Root>
    </Loggers>
</Configuration>

4.JAVA API操作

-----获取Client

(1)ElasticSearch服务默认端口9300。
(2)Web管理平台端口9200。

private TransportClient client;

	@SuppressWarnings("unchecked")
	@Before
	public void getClient() throws Exception {

		// 1 设置连接的集群名称
		Settings settings = Settings.builder().put("cluster.name", "my-application").build();

		// 2 连接集群
		client = new PreBuiltTransportClient(settings);
		client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("hadoop102"), 9300));

		// 3 打印集群名称
		System.out.println(client.toString());
	}

@SuppressWarnings(“unchecked”)的作用:
https://blog.csdn.net/tanga842428/article/details/75674591

-----创建索引

@Test
	public void createIndex_blog(){
		// 1 创建索引
		client.admin().indices().prepareCreate("blog2").get();
		
		// 2 关闭连接
		client.close();
	}

-----删除索引

@Test
	public void deleteIndex(){
		// 1 删除索引
		client.admin().indices().prepareDelete("blog2").get();
		
		// 2 关闭连接
		client.close();
	}

-----新建文档(源数据json串)(String拼接)

@Test
	public void createIndexByJson() throws UnknownHostException {

		// 1 文档数据准备
		String json = "{" + "\"id\":\"1\"," + "\"title\":\"基于Lucene的搜索服务器\","
				+ "\"content\":\"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\"" + "}";

		// 2 创建文档
		IndexResponse indexResponse = client.prepareIndex("blog", "article", "1").setSource(json).execute().actionGet();

		// 3 打印返回的结果
		System.out.println("index:" + indexResponse.getIndex());
		System.out.println("type:" + indexResponse.getType());
		System.out.println("id:" + indexResponse.getId());
		System.out.println("version:" + indexResponse.getVersion());
		System.out.println("result:" + indexResponse.getResult());

		// 4 关闭连接
		client.close();
	}

-----新建文档(源数据map方式添加json)

@Test
	public void createIndexByMap() {

		// 1 文档数据准备
		Map<String, Object> json = new HashMap<String, Object>();
		json.put("id", "2");
		json.put("title", "基于Lucene的搜索服务器");
		json.put("content", "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");

		// 2 创建文档
		IndexResponse indexResponse = client.prepareIndex("blog", "article", "2").setSource(json).execute().actionGet();

		// 3 打印返回的结果
		System.out.println("index:" + indexResponse.getIndex());
		System.out.println("type:" + indexResponse.getType());
		System.out.println("id:" + indexResponse.getId());
		System.out.println("version:" + indexResponse.getVersion());
		System.out.println("result:" + indexResponse.getResult());

		// 4 关闭连接
		client.close();
	}

-----新建文档(源数据es构建器添加json)

@Test
	public void createIndex() throws Exception {

		// 1 通过es自带的帮助类,构建json数据
		XContentBuilder builder = XContentFactory.jsonBuilder().startObject().field("id", 3).field("title", "基于Lucene的搜索服务器").field("content", "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。")
				.endObject();

		// 2 创建文档
		IndexResponse indexResponse = client.prepareIndex("blog", "article", "3").setSource(builder).get();

		// 3 打印返回的结果
		System.out.println("index:" + indexResponse.getIndex());
		System.out.println("type:" + indexResponse.getType());
		System.out.println("id:" + indexResponse.getId());
		System.out.println("version:" + indexResponse.getVersion());
		System.out.println("result:" + indexResponse.getResult());

		// 4 关闭连接
		client.close();
	}

-----搜索文档数据(单个索引)

@Test
	public void getData() throws Exception {
		
		// 1 查询文档
		GetResponse response = client.prepareGet("blog", "article", "1").get();
		
		// 2 打印搜索的结果
		System.out.println(response.getSourceAsString());
		
		// 3 关闭连接
		client.close();
	}

------搜索文档数据(多个索引)

@Test
	public void getMultiData() {
		
		// 1 查询多个文档
		MultiGetResponse response = client.prepareMultiGet().add("blog", "article", "1").add("blog", "article", "2", "3").add("blog", "article", "2").get();
		
		// 2 遍历返回的结果
		for(MultiGetItemResponse itemResponse:response){
			GetResponse getResponse = itemResponse.getResponse();
			
			// 如果获取到查询结果
			if (getResponse.isExists()) {
				String sourceAsString = getResponse.getSourceAsString();
				System.out.println(sourceAsString);
			}
		}
		
		// 3 关闭资源
		client.close();
	}

-----更新文档数据(update)

@Test
	public void updateData() throws Throwable {

		// 1 创建更新数据的请求对象
		UpdateRequest updateRequest = new UpdateRequest();
		updateRequest.index("blog");
		updateRequest.type("article");
		updateRequest.id("3");

		updateRequest.doc(XContentFactory.jsonBuilder().startObject()
				// 对没有的字段添加, 对已有的字段替换
				.field("title", "基于Lucene的搜索服务器")
				.field("content","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。大数据前景无限")
				.field("createDate", "2017-8-22").endObject());

		// 2 获取更新后的值
		UpdateResponse indexResponse = client.update(updateRequest).get();
		
		// 3 打印返回的结果
		System.out.println("index:" + indexResponse.getIndex());
		System.out.println("type:" + indexResponse.getType());
		System.out.println("id:" + indexResponse.getId());
		System.out.println("version:" + indexResponse.getVersion());
		System.out.println("create:" + indexResponse.getResult());

		// 4 关闭连接
		client.close();
	}

-----更新文档数据(upsert)(查找不到则添加,否者更新)

@Test
	public void testUpsert() throws Exception {

		// 设置查询条件, 查找不到则添加
		IndexRequest indexRequest = new IndexRequest("blog", "article", "5")
				.source(XContentFactory.jsonBuilder().startObject().field("title", "搜索服务器").field("content","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开发的,并作为Apache许可条款下的开放源码发布,是当前流行的企业级搜索引擎。设计用于云计算中,能够达到实时搜索,稳定,可靠,快速,安装使用方便。").endObject());
		
		// 设置更新, 查找到更新下面的设置
		UpdateRequest upsert = new UpdateRequest("blog", "article", "5")
				.doc(XContentFactory.jsonBuilder().startObject().field("user", "李四").endObject()).upsert(indexRequest);

		client.update(upsert).get();
		client.close();
	}

-----删除文档数据(prepareDelete)

@Test
	public void deleteData() {
		
		// 1 删除文档数据
		DeleteResponse indexResponse = client.prepareDelete("blog", "article", "5").get();

		// 2 打印返回的结果
		System.out.println("index:" + indexResponse.getIndex());
		System.out.println("type:" + indexResponse.getType());
		System.out.println("id:" + indexResponse.getId());
		System.out.println("version:" + indexResponse.getVersion());
		System.out.println("found:" + indexResponse.getResult());

		// 3 关闭连接
		client.close();
	}

5.条件查询QueryBuilder

—查询所有(matchAllQuery)—

@Test
	public void matchAllQuery() {
		
		// 1 执行查询
		SearchResponse searchResponse = client.prepareSearch("blog").setTypes("article")
				.setQuery(QueryBuilders.matchAllQuery()).get();

		// 2 打印查询结果
		SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
		System.out.println("查询结果有:" + hits.getTotalHits() + "条");

		for (SearchHit hit : hits) {
           System.out.println(hit.getSourceAsString());//打印出每条结果
        }

		// 3 关闭连接
		client.close();
	}

—对所有字段分词查询(queryStringQuery)—

@Test
	public void query() {
		// 1 条件查询
		SearchResponse searchResponse = client.prepareSearch("blog").setTypes("article")
				.setQuery(QueryBuilders.queryStringQuery("全文")).get();

		// 2 打印查询结果
		SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
		System.out.println("查询结果有:" + hits.getTotalHits() + "条");
		
		for (SearchHit hit : hits) {
           System.out.println(hit.getSourceAsString());//打印出每条结果
        }
		
		// 3 关闭连接
		client.close();
	}
	

—通配符查询(wildcardQuery)—

@Test
	public void wildcardQuery() {

		// 1 通配符查询
		SearchResponse searchResponse = client.prepareSearch("blog").setTypes("article")
				.setQuery(QueryBuilders.wildcardQuery("content", "*全*")).get();

		// 2 打印查询结果
		SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
		System.out.println("查询结果有:" + hits.getTotalHits() + "条");

		for (SearchHit hit : hits) {
           System.out.println(hit.getSourceAsString());//打印出每条结果
        }

		// 3 关闭连接
		client.close();
	}

—词条查询(TermQuery)—

@Test
	public void termQuery() {
		
		// 1 第一field查询
		SearchResponse searchResponse = client.prepareSearch("blog").setTypes("article")
				.setQuery(QueryBuilders.termQuery("content", "全文")).get();
		
		// 2 打印查询结果
		SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
		System.out.println("查询结果有:" + hits.getTotalHits() + "条");

		for (SearchHit hit : hits) {
           System.out.println(hit.getSourceAsString());//打印出每条结果
        }

		// 3 关闭连接
		client.close();
	}

—模糊查询(fuzzy)—

@Test
	public void fuzzy() {
		
		// 1 模糊查询
		SearchResponse searchResponse = client.prepareSearch("blog").setTypes("article")
				.setQuery(QueryBuilders.fuzzyQuery("title", "lucene")).get();
		
		// 2 打印查询结果
		SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
		System.out.println("查询结果有:" + hits.getTotalHits() + "条");

		Iterator<SearchHit> iterator = hits.iterator();

		while (iterator.hasNext()) {
			SearchHit searchHit = iterator.next(); // 每个查询对象

			System.out.println(searchHit.getSourceAsString()); // 获取字符串格式打印
		}

		// 3 关闭连接
		client.close();
	}

6.映射相关操作

@Test
	public void createMapping() throws Exception {
		
		// 1设置mapping
		XContentBuilder builder = XContentFactory.jsonBuilder()
				.startObject()
					.startObject("article")
						.startObject("properties")
							.startObject("id1")
								.field("type", "string")
								.field("store", "yes")
							.endObject()
							.startObject("title2")
								.field("type", "string")
								.field("store", "no")
							.endObject()
							.startObject("content")
								.field("type", "string")
								.field("store", "yes")
							.endObject()
						.endObject()
					.endObject()
				.endObject();

		// 2 添加mapping
		PutMappingRequest mapping = Requests.putMappingRequest("blog4").type("article").source(builder);
		
		client.admin().indices().putMapping(mapping).get();
		
		// 3 关闭资源
		client.close();
	}

7.IK分词器的安装

下载地址:https://github.com/medcl/elasticsearch-analysis-ik

安装方法(3种):
1.
./elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v6.1.1/elasticsearch-analysis-ik-6.1.1.zip

2.
cp elasticsearch-analysis-ik-6.1.1.zip ./elasticsearch-6.1.1/plugins/
unzip elasticsearch-analysis-ik-6.1.1.zip -d ik-analyzer

3、elasticsearch-plugin install -f file:///usr/local/elasticsearch-analysis-ik-6.1.1.zip

8.IK分词器的使用(命令行查看结果)

1)ik_smart模式

curl -H "Content-Type:application/json" -XGET 'http://192.168.109.133:9200/_analyze?pretty' -d '{"analyzer":"ik_smart","text":"中华人民共和国"}'
返回
{
  "tokens" : [
    {
      "token" : "中华人民共和国",
      "start_offset" : 0,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 0
    }
  ]
}

2)ik_max_word模式

curl -H "Content-Type:application/json" -XGET 'http://192.168.109.133:9200/_analyze?pretty' -d '{"analyzer":"ik_max_word","text":"中华人民共和国"}'
返回
{
  "tokens" : [
    {
      "token" : "中华人民共和国",
      "start_offset" : 0,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 0
    },
    {
      "token" : "中华人民",
      "start_offset" : 0,
      "end_offset" : 4,
      "type" : "CN_WORD",
      "position" : 1
    },
    {
      "token" : "中华",
      "start_offset" : 0,
      "end_offset" : 2,
      "type" : "CN_WORD",
      "position" : 2
    },
    {
      "token" : "华人",
      "start_offset" : 1,
      "end_offset" : 3,
      "type" : "CN_WORD",
      "position" : 3
    },
    {
      "token" : "人民共和国",
      "start_offset" : 2,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 4
    },
    {
      "token" : "人民",
      "start_offset" : 2,
      "end_offset" : 4,
      "type" : "CN_WORD",
      "position" : 5
    },
    {
      "token" : "共和国",
      "start_offset" : 4,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 6
    },
    {
      "token" : "共和",
      "start_offset" : 4,
      "end_offset" : 6,
      "type" : "CN_WORD",
      "position" : 7
    },
    {
      "token" : "国",
      "start_offset" : 6,
      "end_offset" : 7,
      "type" : "CN_CHAR",
      "position" : 8
    }
  ]
}

9.ik_smart(粗粒度搜索)模式和ik_max_word(细粒度索引)模式的应用场景

https://blog.csdn.net/weixin_44062339/article/details/85006948

10.IK分词器的使用(JAVAapi方式)

//创建使用ik分词器的mapping
    @Test
    public void createMapping() throws Exception {

        // 1设置mapping
        XContentBuilder builder = XContentFactory.jsonBuilder()
                .startObject()
                    .startObject("article")
                        .startObject("properties")
                        .startObject("id1")
                            .field("type", "string")
                            .field("store", "yes")
                            .field("analyzer","ik_smart")
                        .endObject()
                        .startObject("title2")
                            .field("type", "string")
                            .field("store", "no")
                            .field("analyzer","ik_smart")
                        .endObject()
                        .startObject("content")
                            .field("type", "string")
                            .field("store", "yes")
                            .field("analyzer","ik_smart")
                        .endObject()
                        .endObject()
                    .endObject()
                .endObject();

        // 2 添加mapping
        PutMappingRequest mapping = Requests.putMappingRequest("blog4").type("article").source(builder);
        client.admin().indices().putMapping(mapping).get();

        // 3 关闭资源
        client.close();
    }

11.elasticsearch 中的_all、_source和index、store解释

https://blog.csdn.net/dalong_bamboo/article/details/89051606

发布了151 篇原创文章 · 获赞 23 · 访问量 2万+

猜你喜欢

转载自blog.csdn.net/qq_33598343/article/details/97944329