ES的date_histogram 根据年月日做统计

原文链接https://blog.csdn.net/he37176427/article/details/104714284

只写了后台，前端请求带上dateType给后台，后端返回封装了json字符串的map

GsonUtil.getJsonStringByObject()是封装的Gson.toJson的方法

前端接受解析结果 并设置echatrs参数 即可完成图表绘制

/**
 * 消息趋势统计 dateType由前端传递 包括年月周
 * 按年则统计过去12个月
 * 按月则统计过去30天
 * 按周则统计过去7天
**/
public Map<String, String> msgTrendCount(String dateType) {
    //每个索引的时间field name 可能不同 根据索引设置
	String rangeField = "messageSendTime";
    //索引名
	String index = EsIndexName.TG_MESSAGE.getIndexName();
	return dateHistogram(rangeField, dateType, index);
}
 
 
 
 
private Map<String, String> dateHistogram(String rangeField, String dateType, String... indices) {
	Map<String, String> map = new HashMap<>(4);
	try {
 
		LocalDateTime now = LocalDateTime.now();
		DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd hh:mm:ss");
		String from;
		//extended bounds参数
		String boundsStart;
		String boundsEnd;
		String to = formatter.format(now);
		String format = "yyyy-MM-dd";
		//bounds的格式化类型需要和format相同
		DateTimeFormatter boundsFormatter = DateTimeFormatter.ofPattern(format);
		//间隔 年类型较为特殊
		DateHistogramInterval interval = DateHistogramInterval.DAY;
		switch (dateType) {
			case "week": {
				from = formatter.format(now.minusDays(6));
				boundsStart = boundsFormatter.format(now.minusDays(6));
				boundsEnd = boundsFormatter.format(now);
				break;
			}
			case "year": {
				from = formatter.format(now.minusMonths(11));
				format = "yyyy-MM";
				boundsFormatter = DateTimeFormatter.ofPattern(format);
				interval = DateHistogramInterval.MONTH;
				boundsStart = boundsFormatter.format(now.minusMonths(11));
				boundsEnd = boundsFormatter.format(now);
				break;
			}
			case "month":
			default: {
				from = formatter.format(now.minusDays(29));
				boundsStart = boundsFormatter.format(now.minusDays(29));
				boundsEnd = boundsFormatter.format(now);
				break;
			}
		}
 
		//范围查询
		BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery();
		boolQueryBuilder.must(QueryBuilders.rangeQuery(rangeField).from(from).to(to));
		//dateHistogram
		AggregationBuilder aggregationBuilder = AggregationBuilders.dateHistogram("dateHistogram")//自定义名称
				.dateHistogramInterval(interval)//设置间隔
				.minDocCount(0)//返回空桶
				.field(rangeField)//指定时间字段
				.format(format)//设定返回格式
				.extendedBounds(new ExtendedBounds(boundsStart, boundsEnd));//设定范围
 
		SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
		//指定size为0 不返回文档 因为只需要数量
		searchSourceBuilder.query(boolQueryBuilder).aggregation(aggregationBuilder).size(0);
 
		SearchRequest searchRequest = new SearchRequest();
		searchRequest.source(searchSourceBuilder);
		searchRequest.indices(indices);
		SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
		Aggregation agg = searchResponse.getAggregations().get("dateHistogram");
 
		List<? extends Histogram.Bucket> buckets = ((Histogram) agg).getBuckets();
		List<String> dateList = new ArrayList<>(30);
		List<String> countList = new ArrayList<>(30);
		for (Histogram.Bucket bucket : buckets) {
			// maybe：如果不是年 则将key中的年份去掉
			dateList.add(bucket.getKeyAsString());
			countList.add(String.valueOf(bucket.getDocCount()));
		}
		map.put("chartTime", GsonUtil.getJsonStringByObject(dateList));
		map.put("chartCount", GsonUtil.getJsonStringByObject(countList));
	} catch (Exception e) {
		log.error("统计日期直方图出错：" + e.getMessage());
	}
	return map;
}

之前费劲写的好多代码来做这个统计，分别用日期去一天天的查数量，最近学习了解了es自带的 date_histogram

完全契合需求，遂将原笨拙的代码删除改为es的自带聚合 (果然人还是要多读书呀。。。)

速度上目前文档数量不大，没有差别，但预计随着后期文档数量增加，肯定是es的聚合更加高效。
 

 

 

 

附上自己写的

 //创建search请求
        SearchRequest searchRequest = new SearchRequest("final_edition_mail_log");
        //用SearchSourceBuilder来构造查询请求体
        SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
        BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery();
        List<SuspiciousAccount> list = new ArrayList<SuspiciousAccount>();
            boolQueryBuilder
                    .must( QueryBuilders.termsQuery("fullName.keyword", param.get("orgName")))
                    .must(QueryBuilders.termsQuery("abroad.keyword","OUT"))//国外
                    //.must(QueryBuilders.existsQuery("credit"))
                    .must(QueryBuilders.termsQuery("behavior","1"))
                    .filter(QueryBuilders.rangeQuery("create_date")
                            .timeZone("GMT+8")
                            .gte(DateUtil.getFirstDayOfMonth()).lte(DateUtil.getLastDayOfMonth()));
            
             AggregationBuilder aggregationBuilder = AggregationBuilders.dateHistogram("create_date")//自定义名称
     				.fixedInterval(DateHistogramInterval.DAY)//设置间隔
     				.minDocCount(1)//返回空桶
     				.field("create_date")//指定时间字段
     				 ; 
              

            sourceBuilder.query(boolQueryBuilder).aggregation(aggregationBuilder).size(0);
            searchRequest.source(sourceBuilder);
           
            //发送请求
            SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
            Aggregation agg = searchResponse.getAggregations().get("create_date");
            
    		List<? extends Histogram.Bucket> buckets = ((Histogram) agg).getBuckets();
    		for (Histogram.Bucket bucket : buckets) {
    			SuspiciousAccount account = new SuspiciousAccount();
    			String longTime = bucket.getKeyAsString();
				log.info(""+bucket.getKeyAsString());
    			log.info(String.valueOf(bucket.getDocCount()));
    			account.setDayOf(DateUtil.timeStamp2Date(String.valueOf(Long.parseLong(longTime)/1000),"yyyy-MM-dd"));
    			account.setSuccessSum(String.valueOf(bucket.getDocCount()));
    			list.add(account);
    		}

GET final_edition_mail_log/_search
 {
   "size" : 0,
   "aggs": {
      "sales": {
         "date_histogram": {
            "field": "create_date",
            "interval": "day", 
            "format": "yyyy-MM-dd" 
         }
      }
   }
}




{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 10000,
      "relation" : "gte"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "sales" : {
      "buckets" : [
        {
          "key_as_string" : "yyyy-MM-dd1588809600000",
          "key" : 1588809600000,
          "doc_count" : 4064865
        },
        {
          "key_as_string" : "yyyy-MM-dd1588896000000",
          "key" : 1588896000000,
          "doc_count" : 8501193
        }
      ]
    }
  }
}