es: java-＞count统计、distinct去重

最新推荐文章于 2024-04-27 13:27:31 发布

我家小宝_朱朱

最新推荐文章于 2024-04-27 13:27:31 发布

阅读量922

点赞数

分类专栏： elastic 文章标签： elasticsearch java

本文链接：https://blog.csdn.net/zhuchunyan_aijia/article/details/133982662

版权

elastic 专栏收录该内容

23 篇文章 0 订阅

订阅专栏

1 统计count

GET /indexname/_count
{
   "query": {
    "range": {
      "dataTime": {
        "from": "2023-01-22",
        "to": null,
        "include_lower": true,
        "include_upper": true,
        "format": "yyyy-MM-dd HH:mm:ss||yyyy||yyyy-MM-dd",
        "boost": 1
      }
    }
  }
}


/**
 * 查询指定索引文档总数（可增加查询条件，如果为空，则查询所有）
 */
@Test
public void testCount() {
    SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
    CountRequest countRequest = new CountRequest();
    //构造查询条件
        RangeQueryBuilder rangeQueryBuilder = QueryBuilders.rangeQuery("dataTime").gte("2023-01-22").format("yyyy-MM-dd HH:mm:ss||yyyy||yyyy-MM-dd");
    searchSourceBuilder.query(rangeQueryBuilder);

    countRequest.indices("indexname").source(searchSourceBuilder);
    CountResponse countResponse = null;
    try {
        countResponse = restHighLevelClient.count(countRequest, RequestOptions.DEFAULT);
        return countResponse.getCount();
    } catch (IOException e) {
        log.error("[EsClientConfig.countDocumentSize][error][fail to count document size,param is {}]", countRequest);
    }
    return 0;
    log.info("[document size is {}, indexName is {}]", size, indexName);
}
\

2. 使用agge 统计

在过滤条件后,统计总数(count), dinsticn , count(distinct())

GET /indexName/_search
{
  "size": 0,
  "query": {
    "range": {
      "dataTime": {
        "from": "2023-01-22",
        "to": null,
        "include_lower": true,
        "include_upper": true,
        "format": "yyyy-MM-dd HH:mm:ss||yyyy||yyyy-MM-dd",
        "boost": 1
      }
    }
  },
  "aggregations": {
    "objtypename": {
      "terms": {
        "field": "externalObj",
        "size": 100,
        "min_doc_count": 1,
        "shard_min_doc_count": 0,
        "show_term_doc_count_error": false,
        "order": [
          {
            "_count": "desc"
          },
          {
            "_key": "asc"
          }
        ]
      }
    },
    "objtypecount": {
      "cardinality": {
        "field": "externalObj"
      }
    },
    "total_count":{
      "value_count": {
        "field": "id.keyword"
      }
    }
  }
}

RestHighLevelClient client = new RestHighLevelClient(RestClient.builder(httpHostsList.toArray(new HttpHost[httpHostsList.size()])));
        SearchRequest searchRequest = new SearchRequest();
        searchRequest.indices("indexName");

        SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
        RangeQueryBuilder rangeQueryBuilder = QueryBuilders.rangeQuery("dataTime").gte("2023-01-22").format("yyyy-MM-dd HH:mm:ss||yyyy||yyyy-MM-dd");
        TermsAggregationBuilder termsAggregationBuilder = AggregationBuilders.terms("objtypename").field("externalObj").size(100);
        CardinalityAggregationBuilder cardinalityAggregationBuilder = AggregationBuilders.cardinality("objtypecount").field("externalObj");
        ValueCountAggregationBuilder valueCountAggregationBuilder = AggregationBuilders.count("total_count").field("id.keyword");

        searchSourceBuilder.query(rangeQueryBuilder);
        searchSourceBuilder.aggregation(termsAggregationBuilder);
        searchSourceBuilder.aggregation(cardinalityAggregationBuilder);
        searchSourceBuilder.aggregation(valueCountAggregationBuilder);

        searchSourceBuilder.size(0);
        System.out.println("----"+searchSourceBuilder.toString());
        searchRequest.source(searchSourceBuilder);
        SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
       //  打印: objtypename,objtypecount,total_count
        Aggregations aggregations = searchResponse.getAggregations();
        for(Aggregation aggregation : aggregations.asList()){
            System.out.println("---"+aggregation.getName());
        }
// distict 
       Terms objtypenameTerms =  aggregations.get("objtypename");
        for(Terms.Bucket bucket : objtypenameTerms.getBuckets()){
            System.out.println("***"+ bucket.getKeyAsString()+"   :   "+bucket.getDocCount() );
        }

// count(disinct)
        Cardinality cardinality = aggregations.get("objtypecount");
        System.out.println("---"+cardinality.getValue());

//count
        ValueCount valueCount = aggregations.get("total_count");
        System.out.println("^^^"+ valueCount.getValue());