使用聚合框架将值数组减少为对象及其计数

Question

我们正在使用 MongoDB 来记录统计信息。该方法是将对象的每个操作记录在其自己的文档中，然后按小时汇总它们并将它们存储在不同的集合中。示例文件如下：

[{
    "_id" : ObjectId("5e05de1e86029610dc2c6f9c"),
    "object_type" : 1,
    "object_id" : 1003,
    "browser" : "chrome",
    "os" : "osx",
    "device" : "android",
    "category" : 3,
    "country" : "gb",
    "action" : "impression",
    "date_added" : ISODate("2019-12-26T19:00:00.000Z")
},{
    "_id" : ObjectId("5e06226586029610db417b7a"),
    "object_type" : 1,
    "object_id" : 1003,
    "browser" : "firefox",
    "os" : "osx",
    "device" : "lg_tv",
    "category" : 1,
    "country" : "pe",
    "action" : "impression",
    "date_added" : ISODate("2019-12-25T19:00:00.000Z")
},{
    "_id" : ObjectId("5e06226586029610db417b7b"),
    "object_type" : 1,
    "object_id" : 1009,
    "browser" : "uc_browser",
    "os" : "osx",
    "device" : "android",
    "category" : 4,
    "country" : "ru",
    "action" : "view",
    "date_added" : ISODate("2019-12-25T19:00:00.000Z")
}]

输出应该是：

[{
    "object_id": 1003,
    "object_type": 1,
    "action": "impression",
    "total": 2,
    "date": "2019-12-26 19:00:00",
    "browsers": { "firefox": 1, "chrome": 1 },
    "systems": { "osx": 2 },
    "countries": { "gb": 1, "pe": 1 },
    "devices": { "android": 1, "lg_tv": 1 },
    "categories": { "3": 1, "1": 1 }
},
{
    "object_id": 1009,
    "object_type": 1,
    "action": "view",
    "total": 1,
    "date": "2019-12-26 19:00:00",
    "browsers": { "uc_browser": 1 },
    "systems": { "osx": 1 },
    "countries": { "ru": 1 },
    "devices": { "android": 1 },
    "categories": { "4": 1 }
}]

聚合管道：

[
  {
    "$match": {
      "date_added": {
        "$gte": {
          "$date": {
            "$numberLong": "1576820825000"
          }
        }
      }
    }
  },
  {
    "$group": {
      "_id": {
        "object_id": "$object_id",
        "object_type": "$object_type",
        "action": "$action",
        "date": {
          "$dateToString": {
            "format": "%Y-%m-%d %H-00-00",
            "date": "$date_added"
          }
        }
      },
      "total": {
        "$sum": 1
      },
      "countries": {
        "$push": "$country"
      }
    }
  },
  {
    "$project": {
      "action": "$_id.action",
      "object_id": "$_id.object_id",
      "object_type": "$_id.object_type",
      "date": "$_id.date",
      "total": 1,
      "countries": 1,
      "systems": 1,
      "devices": 1,
      "categories": 1,
      "_id": 0
    }
  },
  {
    "$sort": {
      "total": -1
    }
  }
]

此管道在给定时间为特定操作提供对象的总数，并将每个国家/地区推入 countries 数组 - 为了便于阅读，从 $group 中删除了其他索引。

我坚持将countries 数组转换为所需的对象。两个问题在我脑海中浮现。

1. 是否可以使用单个聚合管道？
2. 我应该只使用上述管道返回文档并使用脚本处理其余索引吗？

Answer 1

有可能，但有点乏味...

你需要$group下一阶段的每个新字段并累积以前的字段。

假设

您对 "object_id": 1003 和 total:2 的预期结果，但 date_added 是 2019-12-26 和 2019-12-25。所以，我把这两个文件都改成了 2019-12-26。

db.collection.aggregate([
  {
    "$match": {
      "date_added": {
        "$gte": {
          "$date": {
            "$numberLong": "1576820825000"
          }
        }
      }
    }
  },
  {
    $group: {
      _id: {
        "object_id": "$object_id",
        "object_type": "$object_type",
        "action": "$action",
        "date": {
          "$dateToString": {
            "format": "%Y-%m-%d %H-00-00",
            "date": "$date_added",
            timezone: "GMT"
          }
        }
      },
      data: {
        "$push": "$$ROOT"
      },
      total: {
        $sum: 1
      }
    }
  },
  {
    $unwind: "$data"
  },
  {
    $group: {
      _id: {
        _id: "$_id",
        "tmp": "$data.category"
      },
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      count: {
        $sum: 1
      }
    }
  },
  {
    $group: {
      _id: "$_id._id",
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      categories: {
        $push: {
          k: {
            $toString: "$_id.tmp"
          },
          v: "$count"
        }
      }
    }
  },
  {
    $unwind: "$data"
  },
  {
    $unwind: "$data"
  },
  {
    $group: {
      _id: {
        _id: "$_id",
        "tmp": "$data.device"
      },
      categories: {
        $first: "$categories"
      },
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      count: {
        $sum: 1
      }
    }
  },
  {
    $group: {
      _id: "$_id._id",
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      categories: {
        $first: "$categories"
      },
      devices: {
        $push: {
          k: "$_id.tmp",
          v: "$count"
        }
      }
    }
  },
  {
    $unwind: "$data"
  },
  {
    $unwind: "$data"
  },
  {
    $group: {
      _id: {
        _id: "$_id",
        "tmp": "$data.country"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      count: {
        $sum: 1
      }
    }
  },
  {
    $group: {
      _id: "$_id._id",
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      countries: {
        $push: {
          k: "$_id.tmp",
          v: "$count"
        }
      }
    }
  },
  {
    $unwind: "$data"
  },
  {
    $unwind: "$data"
  },
  {
    $group: {
      _id: {
        _id: "$_id",
        "tmp": "$data.os"
      },
      countries: {
        $first: "$countries"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      count: {
        $sum: 1
      }
    }
  },
  {
    $group: {
      _id: "$_id._id",
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      countries: {
        $first: "$countries"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      systems: {
        $push: {
          k: "$_id.tmp",
          v: "$count"
        }
      }
    }
  },
  {
    $unwind: "$data"
  },
  {
    $unwind: "$data"
  },
  {
    $group: {
      _id: {
        _id: "$_id",
        "tmp": "$data.browser"
      },
      systems: {
        $first: "$systems"
      },
      countries: {
        $first: "$countries"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      count: {
        $sum: 1
      }
    }
  },
  {
    $group: {
      _id: "$_id._id",
      data: {
        $push: "$data"
      },
      total: {
        $first: "$total"
      },
      systems: {
        $first: "$systems"
      },
      countries: {
        $first: "$countries"
      },
      devices: {
        $first: "$devices"
      },
      categories: {
        $first: "$categories"
      },
      browsers: {
        $push: {
          k: "$_id.tmp",
          v: "$count"
        }
      }
    }
  },
  {
    $project: {
      _id: 0,
      action: "$_id.action",
      date: "$_id.date",
      object_id: "$_id.object_id",
      object_type: "$_id.object_type",
      total: 1,
      categories: {
        $arrayToObject: "$categories"
      },
      countries: {
        $arrayToObject: "$countries"
      },
      devices: {
        $arrayToObject: "$devices"
      },
      systems: {
        $arrayToObject: "$systems"
      },
      browsers: {
        $arrayToObject: "$browsers"
      }
    }
  },
  {
    $sort: {
      object_id: 1,
      date: 1
    }
  }
])

MongoPlayground

注意：其他方法是使用$facet单独创建字段，然后将它们合并到最终对象中，但是MongoPlayground sometimes worked buggy（点击运行按钮几次，你会得到不同的结果）