gpt4 book ai didi

php - 在 Elasticsearch 5 上使用过滤器获取嵌套文档

转载 作者:行者123 更新时间:2023-12-02 22:30:27 25 4
gpt4 key购买 nike

我在 ES 5 中映射了以下文档:

{
"appName" : {
"mappings" : {
"market_audit" : {
"properties" : {
"generation_date": {
"type": "date"
},
"customers" : {
"type" : "nested",
"properties" : {
"customer_id" : {
"type" : "integer"
},
[... other properties ...]
}

“customers”节点中的多个条目可能具有相同的 customer_id,我试图仅检索具有特定 customer_id(即“1”)的条目以及顶级文档的“generation_date”(仅最新文件将被处理)。

我能够提出以下查询:
{
"query": {},
"sort": [
{ "generation_date": "desc" }
],
"size": 1,
"aggregations": {
"nested": {
"nested": {
"path": "customers"
},
"aggregations": {
"filter": {
"filter": {
"match": {
"customers.customer_id": {
"query": "1"
}
}
},
"aggregations": {
"tophits_agg": {
"top_hits": {}
}
}
}
}
}
}
}

这个查询让我获得了我感兴趣的数据,这些数据位于“聚合”数组中(以及包含整个文档的“命中”数组)。这里的问题是我使用的框架(ONGR 的 ElasticSearch 包以及 DSL 包,使用 Symfony3)每次尝试访问没有可用存储桶的实际数据时都会提示。

我已阅读 ES 文档,但无法提出添加存储桶的有效查询。我确定我遗漏了一些东西,一点帮助将非常受欢迎。如果您对如何适本地修改查询有一个想法,我想我可以想出 PHP 代码来生成它。

编辑:由于这个问题得到了一些观点并且没有答案(而且我仍然被困住),我会接受任何允许我从生成的最新文档中检索有关特定“客户”(使用 customer_id)信息的查询(根据“generation_date”字段)。我给出的查询正是我能够提出的,我很确定有更好的方法来做到这一点。建议可能吗?

编辑2:
这是发送到 ES 的数据:
{
"index": {
"_type": "market_data_audit_document"
}
}
{
"customers": [
{
"customer_id": 1,
"colocation_name": "colo1",
"colocation_id": 26,
"device_name": "device 1",
"channels": [
{
"name": "channel1-5",
"multicast":"1.2.1.5",
"sugar_state":4,
"network_state":1
}
]
},
{
"customer_id":2,
"colocation_name":"colo2",
"colocation_id":27,
"device_name":"device 2",
"channels": [
{
"name":"channel2-5",
"multicast":"1.2.2.5",
"sugar_state":4,
"network_state":1
}
]
},
{
"customer_id":3,
"colocation_name":"colo3",
"colocation_id":28,
"device_name":"device 3",
"channels": [
{
"name":"channel3-5",
"multicast":"1.2.3.5",
"sugar_state":4,
"network_state":1
}
]
},
{
"customer_id":4,
"colocation_name":"colo4",
"colocation_id":29,
"device_name":"device 4"
,"channels": [
{
"name":"channel4-5",
"multicast":"1.2.4.5",
"sugar_state":4,
"network_state":1
}
]
},
{
"customer_id":5,
"colocation_name":"colo5",
"colocation_id":30,
"device_name":"device 5",
"channels": [
{
"name":"channel5-5",
"multicast":"1.2.5.5",
"sugar_state":4,
"network_state":1
}
]
}
],
"generation_date":"2017-02-27T10:55:45+0100"
}

不幸的是,当我尝试发送这篇文章中列出的查询时,我发现聚合并没有像我预期的那样:它返回“好”数据,但来自 全部 存储的文件!这是一个输出示例:
{
"timed_out" : false,
"took" : 60,
"hits" : {
"total" : 2,
"hits" : [
{
"_source" : {
"customers" : [
{
"colocation_id" : 26,
"channels" : [
{
"name" : "channel1-5",
"sugar_state" : 4,
"network_state" : 1,
"multicast" : "1.2.1.5"
}
],
"customer_id" : 1,
"colocation_name" : "colo1",
"device_name" : "device 1"
},
{
"colocation_id" : 27,
"channels" : [
{
"multicast" : "1.2.2.5",
"network_state" : 1,
"name" : "channel2-5",
"sugar_state" : 4
}
],
"customer_id" : 2,
"device_name" : "device 2",
"colocation_name" : "colo2"
},
{
"device_name" : "device 3",
"colocation_name" : "colo3",
"customer_id" : 3,
"channels" : [
{
"multicast" : "1.2.3.5",
"network_state" : 1,
"sugar_state" : 4,
"name" : "channel3-5"
}
],
"colocation_id" : 28
},
{
"channels" : [
{
"sugar_state" : 4,
"name" : "channel4-5",
"multicast" : "1.2.4.5",
"network_state" : 1
}
],
"customer_id" : 4,
"colocation_id" : 29,
"colocation_name" : "colo4",
"device_name" : "device 4"
},
{
"device_name" : "device 5",
"colocation_name" : "colo5",
"colocation_id" : 30,
"channels" : [
{
"sugar_state" : 4,
"name" : "channel5-5",
"multicast" : "1.2.5.5",
"network_state" : 1
}
],
"customer_id" : 5
}
],
"generation_date" : "2017-02-27T11:45:37+0100"
},
"_type" : "market_data_audit_document",
"sort" : [
1488192337000
],
"_index" : "mars",
"_score" : null,
"_id" : "AVp_LPeJdrvi0cWb8CrL"
}
],
"max_score" : null
},
"aggregations" : {
"nested" : {
"doc_count" : 10,
"filter" : {
"doc_count" : 2,
"tophits_agg" : {
"hits" : {
"max_score" : 1,
"total" : 2,
"hits" : [
{
"_nested" : {
"offset" : 0,
"field" : "customers"
},
"_score" : 1,
"_source" : {
"channels" : [
{
"name" : "channel1-5",
"sugar_state" : 4,
"multicast" : "1.2.1.5",
"network_state" : 1
}
],
"customer_id" : 1,
"colocation_id" : 26,
"colocation_name" : "colo1",
"device_name" : "device 1"
}
},
{
"_source" : {
"colocation_id" : 26,
"customer_id" : 1,
"channels" : [
{
"multicast" : "1.2.1.5",
"network_state" : 1,
"name" : "channel1-5",
"sugar_state" : 4
}
],
"device_name" : "device 1",
"colocation_name" : "colo1"
},
"_nested" : {
"offset" : 0,
"field" : "customers"
},
"_score" : 1
}
]
}
}
}
}
},
"_shards" : {
"total" : 13,
"successful" : 1,
"failures" : [
{
"reason" : {
"index" : ".kibana",
"index_uuid" : "bTkwoysSQ0y8Tt9yYFRStg",
"type" : "query_shard_exception",
"reason" : "No mapping found for [generation_date] in order to sort on"
},
"shard" : 0,
"node" : "4ZUgOm4VRry6EtUK15UH3Q",
"index" : ".kibana"
},
{
"reason" : {
"index_uuid" : "lN2mVF9bRjuDtiBF2qACfA",
"index" : "archiv1_log",
"type" : "query_shard_exception",
"reason" : "No mapping found for [generation_date] in order to sort on"
},
"shard" : 0,
"node" : "4ZUgOm4VRry6EtUK15UH3Q",
"index" : "archiv1_log"
},
{
"index" : "archiv1_session",
"shard" : 0,
"node" : "4ZUgOm4VRry6EtUK15UH3Q",
"reason" : {
"type" : "query_shard_exception",
"index" : "archiv1_session",
"index_uuid" : "cmMAW04YTtCb0khEqHpNyA",
"reason" : "No mapping found for [generation_date] in order to sort on"
}
},
{
"shard" : 0,
"node" : "4ZUgOm4VRry6EtUK15UH3Q",
"reason" : {
"reason" : "No mapping found for [generation_date] in order to sort on",
"index" : "archiv1_users_dev",
"index_uuid" : "AH48gIf5T0CXSQaE7uvVRg",
"type" : "query_shard_exception"
},
"index" : "archiv1_users_dev"
}
],
"failed" : 12
}
}

最佳答案

根据您的描述:

  • 你将文档存储在具有一堆属性的elasticsearch
  • 每个文档都包含数组中的客户列表(嵌套文档)
  • 您只想提取与 customer.id 相关的嵌套文档
  • 你的库不管理没有桶的 Elasticsearch 响应
  • 您期望 Elasticsearch 返回嵌套文档

  • 问题

    它存在两种聚合:
  • 指标

  • 在您的情况下,您在 Nested Agg 下有 2 个聚合:过滤器和指标。
    筛选 :
  • Filter defines a single bucket of all the documents 但未在结果中提供“bucket”关键字。
  • Top hits 是一个 Metric,不提供桶。

  • 解决方法:

    我怀疑您的 PHP 库能否正确处理嵌套聚合结果,但您可以使用 Filter s 而不是 Filter Aggregations 来获取存储桶列表
    {
    "aggregations": {
    "nested": {
    "nested": {
    "path": "customers"
    },
    "aggregations": {
    "filters_customer": {
    "filters": {
    "filters": [
    {
    "match": {
    "customers.customer_id": "1"
    }
    }
    ]
    },
    "aggregations": {
    "top_hits_customer": {
    "top_hits": {}
    }
    }
    }
    }
    }
    }
    }

    将提供类似:
    {
    "aggregations": {
    "nested": {
    "doc_count": 15,
    "filters_customer": {
    "buckets": [
    {
    "doc_count": 3,
    "top_hits_customer": {
    "hits": {
    "total": 3,
    "max_score": 1,
    "hits": [
    {
    "_nested": {
    "field": "customers",
    "offset": 0
    },
    "_score": 1,
    "_source": {
    "customer_id": 1,
    "foo": "bar"
    }
    },
    {
    "_nested": {
    "field": "customers",
    "offset": 0
    },
    "_score": 1,
    "_source": {
    "customer_id": 1,
    "foo": "bar"
    }
    },
    {
    "_nested": {
    "field": "customers",
    "offset": 0
    },
    "_score": 1,
    "_source": {
    "customer_id": 1,
    "foo": "bar"
    }
    }
    ]
    }
    }
    }
    ]
    }
    }
    }
    }

    请注意您的 EDIT 2

    Elasticsearch 将根据您的报告日期搜索所有文档,而不是“TOP 1”文档。按报告拆分结果的一种方法是在报告日期使用术语桶:
    {
    "query": {},
    "size": 0,
    "aggregations": {
    "grp_report": {
    "terms": {
    "field": "generation_date"
    },
    "aggregations": {
    "nested_customers": {
    "nested": {
    "path": "customers"
    },
    "aggregations": {
    "filters_customer": {
    "filters": {
    "filters": [
    {
    "match": {
    "customers.customer_id": "1"
    }
    }
    ]
    },
    "aggregations": {
    "top_hits_customer": {
    "top_hits": {}
    }
    }
    }
    }
    }
    }
    }
    }
    }

    建议:

    避免复杂的文档,更喜欢将您的报告拆分为具有相关键(例如reportId)的小文档。您将能够轻松过滤和聚合,而无需任何嵌套文档。添加关于女巫的客户文档信息,您将过滤所有类型(在这种情况下,冗余不是问题)。

    用例示例:
  • 报告列表
  • 显示每个报告的客户信息
  • 跨多个报告显示客户的历史记录

  • 当前文档示例:/indexName/market_audit
    {
    "generation_date": "...",
    "customers": [
    {
    "id": 1,
    "foo": "bar 1"
    },
    {
    "id": 2,
    "foo": "bar 2"
    },
    {
    "id": 3,
    "foo": "bar 3"
    }
    ]
    }

    改版文件:

    /indexName/market_audit_report
    {
    "report_id" : "123456"
    "generation_date": "...",
    "foo":"bar"
    }

    /indexName/market_audit_customer 文件
    {
    "report_id" : "123456"
    "customer_id": 1,
    "foo": "bar 1"
    }


    {
    "report_id" : "123456"
    "customer_id": 2,
    "foo": "bar 2"
    }


    {
    "report_id" : "123456"
    "customer_id": 3,
    "foo": "bar 3"
    }

    如果您知道您的报告 ID,您将能够在一个请求中获取所有数据:
  • 对报告 ID
  • 的过滤器
  • 类型上的术语聚合
  • 类型报告的过滤器
  • 一个 top_hit 聚合得到报告
  • 过滤器聚合,仅获取类型客户和客户 ID 1
  • 对客户 1 信息的 top_hit 聚合

  • 或者
  • 对报告 ID
  • 的过滤器
  • 类型上的术语聚合
  • 类型报告的过滤器
  • 一个 top_hit 聚合得到报告
  • 客户 ID 上的术语聚合
  • 一个 top_hit 聚合来检索每个客户的信息

  • 热门点击聚合大小

    不要忘记在你的 top_hits 中提供一个 size 否则你只会得到 top 3

    关于php - 在 Elasticsearch 5 上使用过滤器获取嵌套文档,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/42255998/

    25 4 0
    Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
    广告合作:1813099741@qq.com 6ren.com