Elasticsearch：RestClient+SearchSourceBuilder使用案例

jackyrar

1 前言
　　RestClient是较低层的API，这里使用基于其封装的高层API，即RestHighLevelClient。
　　需要添加的依赖如下：


org.elasticsearch
elasticsearch
5.6.10


org.elasticsearch.client
elasticsearch-rest-high-level-client
5.6.10

　　较低版本的es可能不支持RestHighLevelClient。
查看一下其maven中央仓库：https://mvnrepository.com/artifact/org.elasticsearch.client/elasticsearch-rest-high-level-client
可以看到，5.6以上的版本才有。

2 测试案例
　　测试代码如下：

package com.xpleaf.es.leaf;
import org.apache.http.HttpHost;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RestClient;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.index.query.*;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.search.sort.SortOrder;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
/**
* @author xpleaf
* @GitHub https://github.com/xpleaf
* @Blog http://blog.运维网.com/xpleaf
* @date 2018/10/7 下午12:05
*/
public class RestHighLevelClientTest {
private HttpHost[] esHosts = new HttpHost[]{
new HttpHost("localhost", 9200)
};
private RestClient restClient = null;
private RestHighLevelClient client = null;
private BoolQueryBuilder boolQueryBuilder = null;
@Before
public void init() throws Exception {
// 1.创建RestClient对象
restClient = RestClient.builder(esHosts).build();
client = new RestHighLevelClient(restClient);
// 2.创建BoolQueryBuilder对象
boolQueryBuilder = new BoolQueryBuilder();
// 3.设置boolQueryBuilder条件
MatchPhraseQueryBuilder matchPhraseQueryBuilder = QueryBuilders
.matchPhraseQuery("key_word", "广东");
MatchPhraseQueryBuilder matchPhraseQueryBuilder2 = QueryBuilders
.matchPhraseQuery("key_word", "湖人");
RangeQueryBuilder rangeQueryBuilder = QueryBuilders
.rangeQuery("postdate")
.from("2016-01-01 00:00:00");
// 子boolQueryBuilder条件条件，用来表示查询条件or的关系
BoolQueryBuilder childBoolQueryBuilder = new BoolQueryBuilder()
.should(matchPhraseQueryBuilder)
.should(matchPhraseQueryBuilder2);
// 4.添加查询条件到boolQueryBuilder中
boolQueryBuilder
.must(childBoolQueryBuilder)
.must(rangeQueryBuilder);
}
// 测试SearchSourceBuilder的搜索
@Test
public void test01() throws Exception {
// 1.创建并设置SearchSourceBuilder对象
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
// 查询条件--->生成DSL查询语句
searchSourceBuilder.query(boolQueryBuilder);
// 第几页
searchSourceBuilder.from(0);
// 每页多少条数据
searchSourceBuilder.size(100);
// 获取的字段（列）和不需要获取的列
searchSourceBuilder.fetchSource(new String[]{"postdate", "key_word"}, new String[]{});
// 设置排序规则
searchSourceBuilder.sort("postdate", SortOrder.ASC);
// 设置超时时间为2s
searchSourceBuilder.timeout(new TimeValue(2000));
// 2.创建并设置SearchRequest对象
SearchRequest searchRequest = new SearchRequest();
// 设置request要搜索的索引和类型
searchRequest.indices("spnews").types("news");
// 设置SearchSourceBuilder查询属性
searchRequest.source(searchSourceBuilder);
// 3.查询
SearchResponse searchResponse = client.search(searchRequest);
System.out.println(searchResponse.toString());
}
@After
public void after() throws Exception {
restClient.close();
}
}
3 分析

3.1 Rest Json
　　上面测试案例的查询条件：

// 2.创建BoolQueryBuilder对象
boolQueryBuilder = new BoolQueryBuilder();
// 3.设置boolQueryBuilder条件
MatchPhraseQueryBuilder matchPhraseQueryBuilder = QueryBuilders
.matchPhraseQuery("key_word", "广东");
MatchPhraseQueryBuilder matchPhraseQueryBuilder2 = QueryBuilders
.matchPhraseQuery("key_word", "湖人");
RangeQueryBuilder rangeQueryBuilder = QueryBuilders
.rangeQuery("postdate")
.from("2016-01-01 00:00:00");
// 子boolQueryBuilder条件条件，用来表示查询条件or的关系
BoolQueryBuilder childBoolQueryBuilder = new BoolQueryBuilder()
.should(matchPhraseQueryBuilder)
.should(matchPhraseQueryBuilder2);
// 4.添加查询条件到boolQueryBuilder中
boolQueryBuilder
.must(childBoolQueryBuilder)
.must(rangeQueryBuilder);
　　实际上会转化为如下的es查询语句（可以debug一下，使用searchSourceBuilder就是用来做这种转换）：

{
"from" : 0,
"size" : 100,
"timeout" : "2000ms",
"query" : {
"bool" : {
"must" : [
{
"bool" : {
"should" : [
{
"match_phrase" : {
"key_word" : {
"query" : "广东",
"slop" : 0,
"boost" : 1.0
}
}
},
{
"match_phrase" : {
"key_word" : {
"query" : "湖人",
"slop" : 0,
"boost" : 1.0
}
}
}
],
"disable_coord" : false,
"adjust_pure_negative" : true,
"boost" : 1.0
}
},
{
"range" : {
"postdate" : {
"from" : "2016-01-01 00:00:00",
"to" : null,
"include_lower" : true,
"include_upper" : true,
"boost" : 1.0
}
}
}
],
"disable_coord" : false,
"adjust_pure_negative" : true,
"boost" : 1.0
}
},
"_source" : {
"includes" : [
"postdate",
"key_word"
],
"excludes" : [ ]
},
"sort" : [
{
"postdate" : {
"order" : "asc"
}
}
]
}
3.2 match query VS match_phrase query
　　注意其差别：

• match query：会对查询语句进行分词，分词后查询语句中的任何一个词项被匹配，文档就会被搜索到。如果想查询匹配所有关键词的文档，可以用and操作符连接；
  
• match_phrase query：满足下面两个条件才会被搜索到
  
  
  
  • （1）分词后所有词项都要出现在该字段中
    
  • （2）字段中的词项顺序要一致