Java操作elasticSearch复杂查询以及解析数据

Posted 2021-12-07 溜达的大象

Java操作elasticSearch复杂查询以及解析数据

es的银行测试库，看一个Kibana操作 然后用java检索解析这个数据

#聚合搜索 address 中包含 mill 的所有人的年龄分布以及平均薪资
GET bank/_search
{
  "query":{
    "match": {
      "address": "mill"
    }
  },
  "aggs": {
    "ageAgg": {
      "terms": {
        "field": "age",
        "size": 10
      }
    },
    "balanceAvg":{
      "avg":{
        "field": "balance"
      }
    }
  },
  "size": 0
}

分解实现：

拆解操作数据

#聚合搜索 address 中包含 mill 的所有人的年龄分布以及平均年龄
GET bank/_search
{
“query”:{ “match”: { “address”: “mill” }
},
“aggs”: { “ageAgg”: { “terms”: { “field”: “age”, “size”: 10 } },

“balanceAvg”:{ “avg”:{ “field”: “balance” } } }, “size”: 0 }

构造一个查询器 指向索引

SearchRequest searchRequest = new SearchRequest();
//指定索引
searchRequest.indices("bank");

封装查询条件器

//指定DSL 检索条件
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
//构造检索条件
searchSourceBuilder.query(QueryBuilders.matchQuery("address","mill"));
//按照年龄只分布进行聚合
TermsAggregationBuilder ageAgg = AggregationBuilders.terms("ageAgg").field("age").size(10);
searchSourceBuilder.aggregation(ageAgg);
//计算平均薪资
AvgAggregationBuilder balanceAvg = AggregationBuilders.avg("balanceAvg").field("blance");
searchSourceBuilder.aggregation(balanceAvg);

//打印检索条件 打印结果与Kibana核对
System.out.println("检索条件："+searchSourceBuilder);

检索条件：{"query":{"match":{"address":{"query":"mill","operator":"OR","prefix_length":0,"max_expansions":50,"fuzzy_transpositions":true,"lenient":false,"zero_terms_query":"NONE","auto_generate_synonyms_phrase_query":true,"boost":1.0}}},"aggregations":{"ageAgg":{"terms":{"field":"age","size":10,"min_doc_count":1,"shard_min_doc_count":0,"show_term_doc_count_error":false,"order":[{"_count":"desc"},{"_key":"asc"}]}},"balanceAvg":{"avg":{"field":"blance"}}}}

封装的条件器置入查询器

searchRequest.source(searchSourceBuilder);

容器中的client调用查询：

//执行检索
SearchResponse search = client.search(searchRequest, GuilimallElasticSearchConfig.COMMON_OPTIONS);

解析查询结果

		System.out.println(search.toString());
//		Map map = JSON.parseObject(search.toString(), Map.class);
		//分析结果 查询结构
		SearchHits hits = search.getHits();
		SearchHit[] searchHits = hits.getHits();
		for (SearchHit hit: searchHits){
//			hit.getIndex();
//			hit.getId();
			String sourceAsString = hit.getSourceAsString();
			Accout accout = JSON.parseObject(sourceAsString, Accout.class);
			System.out.println(accout.toString());
		}
		//获取检索的分析信息
		Aggregations aggregations = search.getAggregations();
//		for (Aggregation aggregation : aggregations.asList()) {
//			System.out.println("当前聚合名字："+aggregation.getName());
//		}
		//分类聚合
		Terms ageAgg1 = aggregations.get("ageAgg");
		for (Terms.Bucket bucket : ageAgg1.getBuckets()) {
			String keyAsString = bucket.getKeyAsString();
			System.out.println("年龄：" + keyAsString + "人数："+bucket.getDocCount());
		}
		//平局值
		Avg balanceAvg1 = aggregations.get("balanceAvg");
		System.out.println("平均薪资"+ balanceAvg1.getValue());

{"took":1,"timed_out":false,"_shards":{"total":1,"successful":1,"skipped":0,"failed":0},"hits":{"total":{"value":4,"relation":"eq"},"max_score":5.4032025,"hits":[{"_index":"bank","_type":"account","_id":"970","_score":5.4032025,"_source":{"account_number":970,"balance":19648,"firstname":"Forbes","lastname":"Wallace","age":28,"gender":"M","address":"990 Mill Road","employer":"Pheast","email":"[e-mail]","city":"Lopezo","state":"AK"}},{"_index":"bank","_type":"account","_id":"136","_score":5.4032025,"_source":{"account_number":136,"balance":45801,"firstname":"Winnie","lastname":"Holland","age":38,"gender":"M","address":"198 Mill Lane","employer":"Neteria","email":"[e-mail]","city":"Urie","state":"IL"}},{"_index":"bank","_type":"account","_id":"345","_score":5.4032025,"_source":{"account_number":345,"balance":9812,"firstname":"Parker","lastname":"Hines","age":38,"gender":"M","address":"715 Mill Avenue","employer":"Baluba","email":"[e-mail]","city":"Blackgum","state":"KY"}},{"_index":"bank","_type":"account","_id":"472","_score":5.4032025,"_source":{"account_number":472,"balance":25571,"firstname":"Lee","lastname":"Long","age":32,"gender":"F","address":"288 Mill Street","employer":"Comverges","email":"[e-mail]","city":"Movico","state":"MT"}}]},"aggregations":{"lterms#ageAgg":{"doc_count_error_upper_bound":0,"sum_other_doc_count":0,"buckets":[{"key":38,"doc_count":2},{"key":28,"doc_count":1},{"key":32,"doc_count":1}]},"avg#balanceAvg":{"value":null}}}
GulimallSearchApplicationTests.Accout(account_number=970, balance=19648, firstname=Forbes, lastname=Wallace, age=28, gender=M, address=990 Mill Road, employer=Pheast, email=[e-mail], city=Lopezo, state=AK)
GulimallSearchApplicationTests.Accout(account_number=136, balance=45801, firstname=Winnie, lastname=Holland, age=38, gender=M, address=198 Mill Lane, employer=Neteria, email=[e-mail], city=Urie, state=IL)
GulimallSearchApplicationTests.Accout(account_number=345, balance=9812, firstname=Parker, lastname=Hines, age=38, gender=M, address=715 Mill Avenue, employer=Baluba, email=[e-mail], city=Blackgum, state=KY)
GulimallSearchApplicationTests.Accout(account_number=472, balance=25571, firstname=Lee, lastname=Long, age=32, gender=F, address=288 Mill Street, employer=Comverges, email=[e-mail], city=Movico, state=MT)
年龄：38人数：2
年龄：28人数：1
年龄：32人数：1
平均薪资Infinity

打印逐条记录时，可以把结构封装成一个model 借助一下：json.cn

完整操作：

	@ToString
		@Data
		static class Accout {

			private int account_number;
			private int balance;
			private String firstname;
			private String lastname;
			private int age;
			private String gender;
			private String address;
			private String employer;
			private String email;
			private String city;
			private String state;
		}

	@Test
	public void searchData() throws IOException {
		SearchRequest searchRequest = new SearchRequest();
		//指定索引
		searchRequest.indices("bank");
		//指定DSL 检索条件
		SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
		//构造检索条件

	/**
	 #聚合搜索 address 中包含 mill 的所有人的年龄分布以及平均年龄
	 GET bank/_search
	 {
	 "query":{ "match": { "address": "mill" }
	 },
	 "aggs": { "ageAgg": { "terms": { "field": "age", "size": 10 } },
	 "balanceAvg":{ "avg":{ "field": "balance" } } }, "size": 0 }
	 */

//		searchSourceBuilder.aggregation();
//		searchSourceBuilder.from();
//		searchSourceBuilder.size();
		searchSourceBuilder.query(QueryBuilders.matchQuery("address","mill"));
		//按照年龄只分布进行聚合
		TermsAggregationBuilder ageAgg = AggregationBuilders.terms("ageAgg").field("age").size(10);
		searchSourceBuilder.aggregation(ageAgg);
		//计算平均薪资
		AvgAggregationBuilder balanceAvg = AggregationBuilders.avg("balanceAvg").field("blance");
		searchSourceBuilder.aggregation(balanceAvg);

		//打印检索条件
 		System.out.println("检索条件："+searchSourceBuilder);


		searchRequest.source(searchSourceBuilder);
		//执行检索
		SearchResponse search = client.search(searchRequest, GuilimallElasticSearchConfig.COMMON_OPTIONS);

		//分析结果
//		searchRequest.
		System.out.println(search.toString());
//		Map map = JSON.parseObject(search.toString(), Map.class);
		//分析结果 查询结构
		SearchHits hits = search.getHits();
		SearchHit[] searchHits = hits.getHits();
		for (SearchHit hit: searchHits){
//			hit.getIndex();
//			hit.getId();
			String sourceAsString = hit.getSourceAsString();
			Accout accout = JSON.parseObject(sourceAsString, Accout.class);
			System.out.println(accout.toString());
		}
		//获取检索的分析信息
		Aggregations aggregations = search.getAggregations();
//		for (Aggregation aggregation : aggregations.asList()) {
//			System.out.println("当前聚合名字："+aggregation.getName());
//		}
		//分类聚合
		Terms ageAgg1 = aggregations.get("ageAgg");
		for (Terms.Bucket bucket : ageAgg1.getBuckets()) {
			String keyAsString = bucket.getKeyAsString();
			System.out.println("年龄：" + keyAsString + "人数："+bucket.getDocCount());
		}
		//平局值
		Avg balanceAvg1 = aggregations.get("balanceAvg");
		System.out.println("平均薪资"+ balanceAvg1.getValue());

	}