elasticsearch bucket 之rare terms聚合使用詳解

PUT /index_person
{
  "settings": {
    "number_of_shards": 1
  },
  "mappings": {
    "properties": {
      "id": {
        "type": "long"
      },
      "name": {
        "type": "keyword"
      },
      "province": {
        "type": "keyword"
      },
      "sex": {
        "type": "keyword"
      },
      "age": {
        "type": "integer"
      },
      "pipeline_province_sex":{
        "type": "keyword"
      },
      "address": {
        "type": "text",
        "analyzer": "ik_max_word",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      }
    }
  }
}

PUT /_bulk
{"create":{"_index":"index_person","_id":1}}
{"id":1,"name":"張三","sex":"男","age":20,"province":"湖北","address":"湖北省黃岡市羅田縣匡河鎮"}
{"create":{"_index":"index_person","_id":2}}
{"id":2,"name":"李四","sex":"男","age":19,"province":"江蘇","address":"江蘇省南京市"}
{"create":{"_index":"index_person","_id":3}}
{"id":3,"name":"王武","sex":"女","age":25,"province":"湖北","address":"湖北省武漢市江漢區"}
{"create":{"_index":"index_person","_id":4}}
{"id":4,"name":"趙六","sex":"女","age":30,"province":"北京","address":"北京市東城區"}
{"create":{"_index":"index_person","_id":5}}
{"id":5,"name":"錢七","sex":"女","age":16,"province":"北京","address":"北京市西城區"}
{"create":{"_index":"index_person","_id":6}}
{"id":6,"name":"王八","sex":"女","age":45,"province":"北京","address":"北京市朝陽區"}
{"create":{"_index":"index_person","_id":7}}
{"id":7,"name":"九哥","sex":"男","age":25,"province":"上海市","address":"上海市嘉定區"}

GET /index_person/_search
{
  "size": 0,
  "aggs": {
    "agg_province": {
      "rare_terms": {
        "field": "province",
        "max_doc_count": 2,
        "precision": 0.01,
        "include": "(.*上.*|.*湖.*|.*江.*)",
        "exclude": ["江蘇"],
        "missing": "default省"
      }
    }
  }
}

@Test
@DisplayName("稀少的term聚合，類似按照 _count asc 排序的terms聚合，但是terms聚合中按照_count asc的結果是不準的，需要使用 rare terms 聚合")
public void agg01() throws IOException {
    SearchRequest searchRequest = new SearchRequest.Builder()
            .size(0)
            .index("index_person")
            .aggregations("agg_province", agg ->
                    agg.rareTerms(rare ->
                            // 稀有詞 的字段
                            rare.field("province")
                                    // 該稀有詞最多可以出現在幾個文檔中，最大值為100，如果要調整，需要修改search.max_buckets參數的值(嘗試修改這個值，不生效)
                                    // 在該例子中，隻要是出現的次數<=2的聚合都會返回
                                    .maxDocCount(2L)
                                    // 內部佈谷鳥過濾器的精度，精度越小越準，但是相應的消耗內存也越多，最小值為 0.00001，默認值為 0.01
                                    .precision(0.01)
                                    // 應該包含在聚合的term, 當是單個字段是，可以寫正則表達式
                                    .include(include -> include.regexp("(.*上.*|.*湖.*|.*江.*)"))
                                    // 排出在聚合中的term，當是集合時，需要寫準確的值
                                    .exclude(exclude -> exclude.terms(Collections.singletonList("江蘇")))
                                    // 當文檔中缺失province字段時，給默認值
                                    .missing("default省")
                    )
            )
            .build();
    System.out.println(searchRequest);
    SearchResponse<Object> response = client.search(searchRequest, Object.class);
    System.out.println(response);
}

# 臨時修改
PUT /_cluster/settings
{"transient": {"search.max_buckets": 65536}}
# 永久修改
PUT /_cluster/settings
{"persistent": {"search.max_buckets": 65536}}