当前位置：首页 > article >正文

ES（2）（仅供自己参考）

article 2025/1/24 17:43:07

Java代码的索引库：

package cn.itcast.hotel;

import lombok.AccessLevel;
import org.apache.http.HttpHost;
import org.elasticsearch.action.admin.indices.delete.DeleteIndexRequest;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestClient;
import org.elasticsearch.client.RestClientBuilder;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.client.indices.CreateIndexRequest;
import org.elasticsearch.client.indices.GetIndexRequest;
import org.elasticsearch.common.xcontent.XContentType;
import org.junit.jupiter.api.*;
import org.springframework.boot.test.context.SpringBootTest;

import java.io.IOException;

/**
 * es连接
 */
@SpringBootTest
public class HotelIndexTest {
    private RestHighLevelClient client;

    @BeforeEach
    void setUp() {
        this.client = new RestHighLevelClient(RestClient.builder(
                HttpHost.create("http://192.168.136.128:9200")
        ));
    }

    @Test
    public void init()
    {
        System.out.println(client);
    }

    /**
     * 创建索引库
     * @throws IOException
     */
    @Test
    public void createIndex() throws IOException {
        CreateIndexRequest request = new CreateIndexRequest("hotel");
        request.source("json", XContentType.JSON);
        client.indices().create(request, RequestOptions.DEFAULT);
    }

    /**
     * 删除一个索引库
     * @throws IOException
     */
    @Test
    public void deleteIndex() throws IOException {
        DeleteIndexRequest request = new DeleteIndexRequest("hotel");
        client.indices().delete(request,RequestOptions.DEFAULT);
    }

    /**
     * 查看一个索引库是否存在
     * @throws IOException
     */
    @Test
    public void exitsIndex() throws IOException {
        GetIndexRequest request = new GetIndexRequest("hotel");
        boolean exists = client.indices().exists(request, RequestOptions.DEFAULT);
        System.out.println(exists?"存在":"不存在");
    }



    @AfterEach
    void tearDown() {
        try {
            client.close();
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }
}

Java代码文档操作：

package cn.itcast.hotel;

import cn.itcast.hotel.pojo.Hotel;
import cn.itcast.hotel.pojo.HotelDoc;
import cn.itcast.hotel.service.IHotelService;
import com.alibaba.fastjson.JSON;
import com.baomidou.mybatisplus.extension.api.R;
import org.apache.http.HttpHost;
import org.elasticsearch.action.admin.indices.delete.DeleteIndexRequest;
import org.elasticsearch.action.bulk.BulkRequest;
import org.elasticsearch.action.delete.DeleteRequest;
import org.elasticsearch.action.get.GetRequest;
import org.elasticsearch.action.get.GetResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.update.UpdateRequest;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestClient;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.xcontent.XContentType;
import org.junit.jupiter.api.AfterEach;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.context.SpringBootTest;

import java.io.IOException;
import java.util.List;
import java.util.Map;

@SpringBootTest
public class HotelDocTest {

    private RestHighLevelClient client;
    @Autowired
    private IHotelService hotelService;

    @BeforeEach
    void setUp() {
        this.client = new RestHighLevelClient(RestClient.builder(
                HttpHost.create("http://192.168.136.128:9200")
        ));
    }

    @AfterEach
    void tearDown() {
        try {
            client.close();
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    /**
     * 往索引库中插入一条数据
     * @throws IOException
     */
    @Test
    public void addDocumentIndex() throws IOException {
        Hotel hotel = hotelService.getById(46829L);
        HotelDoc hotelDoc = new HotelDoc(hotel);

        IndexRequest request = new IndexRequest("hotel");
        request.source(JSON.toJSONString(hotelDoc), XContentType.JSON).id(hotel.getId().toString());
        client.index(request, RequestOptions.DEFAULT);
    }

    //查询某一条数据，根据id查询
    @Test
    public void queryIndex() throws IOException {
        GetRequest request = new GetRequest("hotel","46829");
        GetResponse document = client.get(request, RequestOptions.DEFAULT);
        String index = document.getIndex();
        Map<String, Object> source = document.getSource();
        System.out.println(source);
    }

    //更改某一个文档数据的内容
    @Test
    public void updateIndex() throws IOException {
        UpdateRequest request = new UpdateRequest("hotel","46829");

        request.doc(
                "pic","Cc",
                "score","115"
                );

        client.update(request,RequestOptions.DEFAULT);
    }

    //删除某一个id的文档数据
    @Test
    public void deleteIndex() throws IOException {
        DeleteRequest request = new DeleteRequest("hotel","46829");
        client.delete(request,RequestOptions.DEFAULT);
    }

    //批量操作，bulk，可以批量插入，删除，更新
    //批量插入
    @Test
    public void bulkIndex() throws IOException {
        BulkRequest request = new BulkRequest();
        List<Hotel> list = hotelService.list();
        list.stream().forEach((hotel)->{        //stream流操作，实现循环操作
            HotelDoc hotelDoc = new HotelDoc(hotel);
            IndexRequest indexRequest = new IndexRequest("hotel");
            indexRequest.source(JSON.toJSONString(hotelDoc),XContentType.JSON).id(hotel.getId().toString());
            request.add(indexRequest);
        });

        client.bulk(request,RequestOptions.DEFAULT);
    }


}

索引库查询搜索操作：

#全部查询，默认返回页数大小为10个
GET /hotel/_search
{
  "query": {
    "match_all": {}
  }
}

# 组合查询，根据符合的score值，做排序
GET /hotel/_search
{
  "query": {
    "match": {
      "all": "北京酒店"
    }
  }
}

#在多个字段中查询，跟组合查询差不多，但是这个浪费时间
GET /hotel/_search
{
  "query": {
    "multi_match": {
      "query": "外滩如家",
      "fields": ["name","brand","business"]
    }
  }
}

#精准查询，例如keyword或者其他数字。
GET /hotel/_search
{
  "query": {
    "term": {
      "city": {
        "value": "上海"
      }
    }
  }
}

#范围查询，根据某个数字的大小范围
GET /hotel/_search
{
  "query": {
    "range": {
      "price": {
        "gte": 10,   #大于等于
        "lte": 200   #小于等于
      }
    }
  }
}


#坐标查询，范围查询，根据当前坐标点，查询某个范围的
GET /hotel/_search
{
  "query": {
    "geo_distance":
    {
      "distance": "3km",
      "position": "31.21, 121.5"
    }
  }
}

DELETE /hotel


#functionscore查询，自己根据查出来的文档
#再将这些文档进行一个筛选
#让你想让他评分高的高，排在前面
GET /hotel/_search
{
  "query": {
    "function_score": {
      "query": {
        "match": {
          "all": "北京酒店"
        }
      },
      "functions": [
        {
          "filter": {
            "term": {
              "brand": "如家"
            }
          },
          "weight": 5
        }
      ],
      "boost_mode": "multiply"
    }
  }
}

复合查询：简单查询的组合，实现复杂的查询

相关性算分（function score）：算分查询，可以控制文档相关性算分，控制文档排名。例如百度竞价

bool查询：

GET /hotel/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "brand": {
              "value": "如家"
            }
          }
        }
      ],
      "must_not": [
        {
          "range": {
            "FIELD": {
              "gt": 400
            }
          }
        }
      ],
      "filter": [
        {
          "geo_distance": {
            "distance": "10km",
            "position": "31.2, 121.5"
          }
        }
      ]
    }
  }
}

数字排序sort：（双条件排序）

#sort排序，如果指定排序方式。默认的打分为null
GET /hotel/_search
{
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "score": {
        "order": "desc"
      },
      "price": {
        "order": "asc"
      }
    }
  ]
}

地理坐标排序（根据排序会给出sort距离）

#sort排序坐标121.612282,31.034661，按照这个坐标升序排序
GET /hotel/_search
{
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "_geo_distance": {
        "position": {
          "lat": 31.034661,
          "lon": 121.612282
        },
        "order": "asc",
        "unit": "km"
      }
    }
  ]
}

分页查询（类似于MySQL的 limit offset（开始的位置，偏移量），raw（行数））：

#分页查询(默认页大小为10，开始位置为0)
GET /hotel/_search
{
  "query": {
    "match_all": {}
  },
  "from": 0,  #从哪里开始
  "size": 3   #页数大小
}

from+size实现方式：

from+size是通过将0-某个数字的文档全部查询出来，然后通过截取方式获取某段文档。比如查询9990-10000的数据，es会首先查询出0-10000的数据，在对0-10000的数据截取，截取出9990-10000的文档数据。

如果是在分布式集群下面（es集群是为了尽可能多的存储数据，所以每个集群的数据不同）

你查询9990-10000的数据就是从每个集群中查询0-10000的数据，然后将所有文档数据排序，然后将数据截取。

造成的问题，每个集群查需要时间，数据之间的排序需要时间，耗费的时间很大很大。

查询高亮处理：（通过服务端给的标签<em></em>,前段给这个字段这是css）

#搜索的字段必须与高亮的字段匹配，如果不匹配可以设置"require_field_match": "false"
GET /hotel/_search
{
  "query": {
    "match": {
      "all": "如家"
    }
  },
  "highlight": {
    "fields": {
      "name": {
        "require_field_match": "false"
      }
    }
  }
}

查看全文

http://www.kler.cn/a/369919.html