es - elasticsearch - aggs - bucket - diversified

世界上并没有完美的程序，但是我们并不因此而沮丧，因为写程序就是一个不断追求完美的过程。

问：diversified_sampler有什么特点？
答：

问：diversified_sampler如何使用？
答：

# 删除
DELETE /diversified_sampler_test

# 映射
PUT /diversified_sampler_test
{
  "mappings": {
    "properties": {
      "name": {"type": "keyword"},
      "type": {"type": "keyword"}
    }
  }
}

# 索引
POST /diversified_sampler_test/_bulk?routing=1&refresh
{"index": {"_id": 1}}
{"name": "hello", "type": "sample_1"}
{"index": {"_id": 2}}
{"name": "good", "type": "sample_2"}
{"index": {"_id": 3}}
{"name": "me", "type": "sample_3"}
{"index": {"_id": 4}}
{"name": "hello", "type": "sample_4"}
{"index": {"_id": 5}}
{"name": "good", "type": "sample_5"}


# 搜索
GET /diversified_sampler_test/_search?size=0
{
  "query": {
    "match_all": {}
  }, 
  "aggs": {
    "dv_sample_aggs": {
      "diversified_sampler": {
        "field": "type", 
        "shard_size": "100"
      },
      "aggs": {
        "name_aggs": {
          "terms": {
            "field": "name"
          }
        }
      }
    }
  }
}

# 结果
{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 5,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "dv_sample_aggs" : {
      "doc_count" : 5,
      "name_aggs" : {
        "doc_count_error_upper_bound" : 0,
        "sum_other_doc_count" : 0,
        "buckets" : [
          {
            "key" : "good",
            "doc_count" : 2
          },
          {
            "key" : "hello",
            "doc_count" : 2
          },
          {
            "key" : "me",
            "doc_count" : 1
          }
        ]
      }
    }
  }
}