elasticsearch - 使用min_doc_count = 0的 Elasticsearch 聚合返回与查询结果或命中无关的所有存储桶

Question

这是我的查询-

{
    "from": 0,
    "size": 100,
    "query": {
        "bool": {
            "filter": [
                {
                    "terms": {
                        "folderId.keyword": [
                            "ff98505e-cdff-43aa-8b05-197bc3f3265e"
                        ],
                        "boost": 1
                    }
                },
                {
                    "terms": {
                        "objectType.keyword": [
                            "File"
                        ],
                        "boost": 1
                    }
                },
                {
                    "term": {
                        "tenantId": {
                            "value": "34202",
                            "boost": 1
                        }
                    }
                }
            ],
            "adjust_pure_negative": true,
            "boost": 1
        }
    },
      "aggs":{
        "_byformat":{
            "terms":{
               "field":"format.keyword",
               "min_doc_count":0,
               "size":200
            }
        }
   }
}

min_doc_count = 0的结果-

  "took" : 1,  "timed_out" : false,  "_shards" : {    "total" : 1,    "successful" : 1,    "skipped" : 0,    "failed" : 0  },  "hits" : {    "total" : 3,    "max_score" : 0.0,    "hits" : [      {        "_index" : "plnesdv1-34202-1",        "_type" : "_doc",        "_id" : "6adbda83-53ad-457f-a2ab-d5b04c643005",        "_score" : 0.0,        "_source" : {          "format" : "vnd.openxmlformats-officedocument.spreadsheetml.sheet",          "externalSharing" : "N",          "description" : null,          "dateModified" : null,          "type" : "application",          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",          "tags" : [ ],          "objectType" : "File",          "dateCreated" : null,          "name" : "New XLSX file",          "tenantId" : "34202",          "modifiedBy" : "rdt001",          "id" : "6adbda83-53ad-457f-a2ab-d5b04c643005",          "status" : "active",          "expirationDate" : null        }      },      {        "_index" : "plnesdv1-34202-1",        "_type" : "_doc",        "_id" : "b1000a15-2d80-41f4-a5df-ba5c27f8e9c6",        "_score" : 0.0,        "_source" : {          "format" : "vnd.ms-excel",          "externalSharing" : "N",          "description" : null,          "dateModified" : null,          "type" : "application",          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",          "tags" : [ ],          "objectType" : "File",          "dateCreated" : null,          "name" : "New XLS file",          "tenantId" : "34202",          "modifiedBy" : "rdt001",          "id" : "b1000a15-2d80-41f4-a5df-ba5c27f8e9c6",          "status" : "active",          "expirationDate" : null        }      },      {        "_index" : "plnesdv1-34202-1",        "_type" : "_doc",        "_id" : "630e9f49-3368-408d-a091-03f253127004",        "_score" : 0.0,        "_source" : {          "format" : "msword",          "externalSharing" : "N",          "description" : null,          "dateModified" : null,          "type" : "application",          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",          "tags" : [ ],          "objectType" : "File",          "dateCreated" : null,          "name" : "New DOC file",          "tenantId" : "34202",          "modifiedBy" : "rdt001",          "id" : "630e9f49-3368-408d-a091-03f253127004",          "status" : "active",          "expirationDate" : null        }      }    ]  },  "aggregations" : {    "_byformat" : {      "doc_count_error_upper_bound" : 0,      "sum_other_doc_count" : 0,      "buckets" : [        {          "key" : "msword",          "doc_count" : 1        },        {          "key" : "vnd.ms-excel",          "doc_count" : 1        },        {          "key" : "vnd.openxmlformats-officedocument.spreadsheetml.sheet",          "doc_count" : 1        },        {          "key" : "bmp",          "doc_count" : 0        },        {          "key" : "gif",          "doc_count" : 0        },        {          "key" : "html",          "doc_count" : 0        }             ]    }  }}

result with min_doc_count = 1 -

{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : 3,
    "max_score" : 0.0,
    "hits" : [
      {
        "_index" : "plnesdv1-34202-1",
        "_type" : "_doc",
        "_id" : "6adbda83-53ad-457f-a2ab-d5b04c643005",
        "_score" : 0.0,
        "_source" : {
          "format" : "vnd.openxmlformats-officedocument.spreadsheetml.sheet",
          "externalSharing" : "N",
          "description" : null,
          "dateModified" : null,
          "type" : "application",
          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",
          "tags" : [ ],
          "objectType" : "File",
          "dateCreated" : null,
          "name" : "New XLSX file",
          "tenantId" : "34202",
          "modifiedBy" : "rdt001",
          "id" : "6adbda83-53ad-457f-a2ab-d5b04c643005",
          "status" : "active",
          "expirationDate" : null
        }
      },
      {
        "_index" : "plnesdv1-34202-1",
        "_type" : "_doc",
        "_id" : "b1000a15-2d80-41f4-a5df-ba5c27f8e9c6",
        "_score" : 0.0,
        "_source" : {
          "format" : "vnd.ms-excel",
          "externalSharing" : "N",
          "description" : null,
          "dateModified" : null,
          "type" : "application",
          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",
          "tags" : [ ],
          "objectType" : "File",
          "dateCreated" : null,
          "name" : "New XLS file",
          "tenantId" : "34202",
          "modifiedBy" : "rdt001",
          "id" : "b1000a15-2d80-41f4-a5df-ba5c27f8e9c6",
          "status" : "active",
          "expirationDate" : null
        }
      },
      {
        "_index" : "plnesdv1-34202-1",
        "_type" : "_doc",
        "_id" : "630e9f49-3368-408d-a091-03f253127004",
        "_score" : 0.0,
        "_source" : {
          "format" : "msword",
          "externalSharing" : "N",
          "description" : null,
          "dateModified" : null,
          "type" : "application",
          "folderId" : "ff98505e-cdff-43aa-8b05-197bc3f3265e",
          "tags" : [ ],
          "objectType" : "File",
          "dateCreated" : null,
          "name" : "New DOC file",
          "tenantId" : "34202",
          "modifiedBy" : "rdt001",
          "id" : "630e9f49-3368-408d-a091-03f253127004",
          "status" : "active",
          "expirationDate" : null
        }
      }
    ]
  },
  "aggregations" : {
    "_byformat" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "msword",
          "doc_count" : 1
        },
        {
          "key" : "vnd.ms-excel",
          "doc_count" : 1
        },
        {
          "key" : "vnd.openxmlformats-officedocument.spreadsheetml.sheet",
          "doc_count" : 1
        }
      ]
    }
  }
}

当min_doc_count = 1时，聚合是正确的，并且仅提取与匹配项相关的存储桶。
谁能告诉我为什么设置了min_doc_count = 0时聚合会提取所有存储桶。我已经浏览了 flex 搜索文档，它指出此行为是设计使然，也可以通过其他任何方式仅针对匹配以及零计数来获取聚合存储桶。

Answer 1

似乎您在汇总时误解了min_doc_count，
设置min_doc_count=0还将返回存储桶，以查找与任何命中的不匹配的字词
使用min_doc_count选项，只能返回匹配的匹配项数量超过配置的匹配项:

 "aggs":{
        "_byformat":{
            "terms":{
               "field":"format.keyword",
               "min_doc_count":0,
               "size":200
            }
        }
   }

上述汇总只会返回在 0个匹配或以上中找到的关键字。 0表示所有有/无，1表示至少1个文档应具有该关键字。