elasticsearch - Elasticsearch发布聚合字符串过滤器

Question

我有一个系统，其中的设备通过某些网关进行通信，然后在后端中将度量标准保存在elasticsearch中。

我想知道现在正在通过特定gateway_id通信的传感器。

我有一个这样的映射:

{
  "mappings": {
    "properties": {
      "context": {
        "properties": {
          "gateway": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          },
          "id": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          }
}},
      "timeserver": {
        "type": "date"
      },
      "timestamp": {
        "type": "date"
      },
      "type": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "value": {
        "type": "double"
      }
    }
  }
}

在网关字段中，将每个指标使用的网关的ID作为字符串保存。

我可以使用以下查询获取每个设备的最新通信:

GET _search
{
  "size": 0,
  "aggs": {
    "id_agg": {
      "terms": {
        "field": "context.id.keyword"
        , "size": 10000
      },
      "aggs": {
        "group_docs": {
          "top_hits": {
            "size": 1,
            "sort": [
              {
                "timestamp": {
                  "order": "desc"
                }
              }
            ]
          }
        }
      }
    }
  },
  "query": {
    "bool": {
      "filter": [
        {
          "term": {
            "_index": "measurements.group.*"
          }
        }
      ]
    }
  }
}

但是，如何过滤此聚合结果，以仅获取当前正在使用特定网关的传感器？添加类似: "filter": {"term":{"context.gateway": {"value": "request_gateway_serial" }} },
我已经搜索了bucket_selector聚合和管道聚合，但是没有找到方法，并且在我看来，它们仅适用于数值，没有字符串，例如我的网关字段。

查询示例返回:(每个设备的最新通信列表)

"aggregations" : {
          {
            "key" : "1234",

                "context" : {
                  "gateway" : "123456",
                  "id" : "1234", 
          },{
            "key" : "12345",
                      "context" : {
                        "gateway" : "1234567",
                        "id" : "12345",
          }, {
             "key" : "12345678",
                     "context" : {
                        "gateway" : "1234567",
                        "id" : "12345678",
}} 

然后，我的预期结果是过滤“gateway”:“1234567”，并且仅获得“key”:“12345”和“key”:“12345678”

Answer 1

您可以使用filter aggregation

GET sensors/_search
{
  "size": 0,
  "aggs": {
    "filter_gateway": {
      "filter": {
        "term": {
          "context.gateway.keyword": "request_gateway_serial"
        }
      },
      "aggs": {
        "id_agg": {
          "terms": {
            "field": "context.id.keyword",
            "size": 10000
          },
          "aggs": {
            "group_docs": {
              "top_hits": {
                "size": 1,
                "sort": [
                  {
                    "timestamp": {
                      "order": "desc"
                    }
                  }
                ]
              }
            }
          }
        }
      }
    }
  },
  "query": {
    "bool": {
      "filter": [
        {
          "term": {
            "_index": "measurements.group.*"
          }
        }
      ]
    }
  }
}

根据您的要求，您还可以过滤查询部分中的文档，然后对其进行汇总。

编辑1:

在下面的查询中，我正在获取设备ID下的最大时间戳
以及在给定网关上过滤的最大时间戳。如果两个日期相同，它将提供与网关最后通信的设备ID。

例如

查询:

GET sensors/_search
{
  "size": 0,
  "aggs": {
    "id_agg": {
      "terms": {
        "field": "context.id.keyword",
        "size": 10000
      },
      "aggs": {
        "maxDate": {
          "max": {
            "field": "context.timestamp"
          }
        },
        "Filter": {
          "filter": {
            "term": {
              "context.gateway": "1234568"
            }
          },
          "aggs": {
            "filtered_maxdate": {
              "max": {
                "field": "context.timestamp"
              }
            }
          }
        },
        "last_geteway_filter": {
          "bucket_selector": {
            "buckets_path": {
              "filtereddate": "Filter>filtered_maxdate",
              "maxDate": "maxDate"
            },
            "script": "params.filtereddate==params.maxDate"
          }
        }
      }
    }
  }
}

数据:

 [
      {
        "_index" : "sensors",
        "_type" : "_doc",
        "_id" : "eiZ1pW0BcOVYVz455V6s",
        "_score" : 1.0,
        "_source" : {
          "context.gateway" : "1234567",
          "context.id" : 1234,
          "context.timestamp" : "2019-10-02"
        }
      },
      {
        "_index" : "sensors",
        "_type" : "_doc",
        "_id" : "eyZ2pW0BcOVYVz45B14T",
        "_score" : 1.0,
        "_source" : {
          "context.gateway" : "1234568",
          "context.id" : 1234,
          "context.timestamp" : "2019-10-03"
        }
      },
      {
        "_index" : "sensors",
        "_type" : "_doc",
        "_id" : "fCZ2pW0BcOVYVz45Jl6m",
        "_score" : 1.0,
        "_source" : {
          "context.gateway" : "1234569",
          "context.id" : 1234,
          "context.timestamp" : "2019-10-04"
        }
      },
      {
        "_index" : "sensors",
        "_type" : "_doc",
        "_id" : "fSZ2pW0BcOVYVz45dV48",
        "_score" : 1.0,
        "_source" : {
          "context.gateway" : "1234567",
          "context.id" : 1235,
          "context.timestamp" : "2019-10-02"
        }
      },
      {
        "_index" : "sensors",
        "_type" : "_doc",
        "_id" : "fiZ2pW0BcOVYVz45l17A",
        "_score" : 1.0,
        "_source" : {
          "context.gateway" : "1234568",
          "context.id" : 1235,
          "context.timestamp" : "2019-10-03"
        }
      }
    ]
  }

结果:

Device 12345 had last document under gateway 1234568

"buckets" : [
        {
          "key" : "1235",
          "doc_count" : 2,
          "Filter" : {
            "doc_count" : 1,
            "filtered_maxdate" : {
              "value" : 1.5700608E12,
              "value_as_string" : "2019-10-03T00:00:00.000Z"
            }
          },
          "maxDate" : {
            "value" : 1.5700608E12,
            "value_as_string" : "2019-10-03T00:00:00.000Z"
          }
        }
      ]