ES--script进行时间聚合(非使用date_histogram)

﹏ヽ暗。殇╰゛Y 2022-04-02 14:09 499阅读 0赞

> 由于产品线上 日期时间使用的非 ES的date数据结构，导致无法使用date\_histogram进行时间聚合的统计。因此这里使用了`script`来达到聚合的效果。

# 介绍 #

本次使用了3亿量的数据进行测试，效果还是蛮差的。这里先将一下使用方式。

*  `lang`代表使用的脚本方式
 *  `params`需要脚本传递的参数
 *  `inline`脚本字符串 (新版本请使用`source`)

GET _search
    {
      "query": {
        "match_phrase": {
          "csdq": "江苏省"
        }
      }
      , "aggs": {
        "date": {
          "terms": {
            "script": {
              "lang": "painless"
              , "params": {
                "filedName": "csrq",
                "type":"1"
              }
              , "inline": """
            String type = params.type;
            String filedName = params.filedName;
            int year = Integer.parseInt(doc[filedName].value.substring(0, 4));
            int month = Integer.parseInt(doc[filedName].value.substring(5, 7));
            int day = Integer.parseInt(doc[filedName].value.substring(8, 10));
            Calendar c = Calendar.getInstance();
            c.set(Calendar.YEAR, year);
            c.set(Calendar.MONTH, month - 1);
            c.set(Calendar.DAY_OF_MONTH, day);
            String tagName = "";
            if (type.equals("1")) {
                return c.get(Calendar.DAY_OF_WEEK);
            } else if (type.equals("2")) {
                return c.get(Calendar.DAY_OF_MONTH);
            } else if (type.equals("3")) {
                return c.get(Calendar.MONTH);
            }
            return tagName;
              """
            }
          }
        }
      }
    }

### 查询结果 ###

#! Deprecation: Deprecated field [inline] used, expected [source] instead
    {
      "took" : 11369,
      "timed_out" : false,
      "_shards" : {
        "total" : 194,
        "successful" : 194,
        "skipped" : 0,
        "failed" : 0
      },
      "hits" : {
        "total" : 13977621,
        "max_score" : 3.7853308,
        "hits" : [
          {
            "_index" : "test_person",
            "_type" : "person",
            "_id" : "YgYl6WcB4n2gTYRcBZf4",
            "_score" : 3.7853308,
            "_source" : {
          }
        ]
      },
      "aggregations" : {
        "date" : {
          "doc_count_error_upper_bound" : 0,
          "sum_other_doc_count" : 0,
          "buckets" : [
            {
              "key" : "6",
              "doc_count" : 1998324
            },
            {
              "key" : "7",
              "doc_count" : 1998120
            },
            {
              "key" : "1",
              "doc_count" : 1997858
            },
            {
              "key" : "3",
              "doc_count" : 1997501
            },
            {
              "key" : "2",
              "doc_count" : 1997068
            },
            {
              "key" : "4",
              "doc_count" : 1995166
            },
            {
              "key" : "5",
              "doc_count" : 1993584
            }
          ]
        }
      }
    }