在我的 Rails 3.2 项目中，我使用 MongoDB (Mongoid) 使用 map/reduce 对一些结果进行分组，例如:

  def count_and_group_by(context)
    raise "No #{context} attribute" unless %w(action browser country).include? context

    map = %Q{
      function() {
        key = this.#{context};
        value = {count: 1};
        emit(key, value);
      }
    }

    reduce = %Q{
      function(key, values) {
        var reducedValue = {count: 0};
        values.forEach(function(value) {
          reducedValue.count += value.count; 
        });
        return reducedValue;
      }
    }

    map_reduce = self.map_reduce(map, reduce).out(inline: true)

    Hash[map_reduce.map {|v| [v["_id"],v["value"]["count"].to_i]}]
  end  

一旦我使用类似MyClass.count_and_group_by("action") 的方法，我得到的结果格式如下:

{"change_password"=>31, "invalid_ip"=>32, "login_failure"=>74, "login_success"=>63, "logout"=>34}

现在我通常做的是尝试根据属性对结果进行分组，比如根据action 属性、browser 和city 属性，我分别对每个属性进行新调用，例如:MyClass.count_and_group_by("action")、MyClass.count_and_group_by("browser")， MyClass.count_and_group_by("city")。

有没有办法一次发出多个键，这样我就可以一次对结果进行分组并得到类似这样的结果:

{"action" => { 
  "change_password"=>31, 
  "invalid_ip"=>32, 
  "login_failure"=>74, 
  "login_success"=>63, 
  "logout"=>34},
 "browser" => {}
 "city" => {}}

最佳答案

这通常应该是可行的，但实际上对于这种类型的操作，您可以通过使用聚合框架来获得更高的性能。目前在用 Mongoid 定义的类上没有“聚合”方法，但是有一个 .collection 访问器可以公开底层驱动程序对象。所以你可以调用.aggregate()从这里开始:

result = this.collection.aggregate([

    # Include each field and an array for "type" in all documents
    { "$project" => {
        "action" => 1,
        "browser" => 1,
        "country" => 1,
        "type" => { "$const" => [ "action", "browser", "country" ] },
    }},

    # Unwind that "type" array
    { "$unwind" => "$type" },

    # Group by "type" and the values of each field which matches
    { "$group" => {
        "_id" => {
            "type" => "$type",
            "value" => {
                "$cond" => [
                    { "$eq" => [ "$type", "action" ] },
                    "$action",
                    { "$cond" => [ 
                        { "$eq" => [ "$type", "browser" ] },
                        "$browser",
                        "$country"
                    ]}
                ]
            }
        },
        "count" => { "$sum" => 1 }
    }},

    # Just in case all fields were not present in all documents
    { "$match" => { "_id.value" => { "$ne" => null } } },

    # Group to a single document with each "type" as the keys
    { "$group" => {
        "_id" => null,
        "action" => { 
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "action" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       },
       "browser" => {
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "browser" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       },
       "country" => {
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "country" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       }
   }},

   # Filter out any null values from the conditional allocation
   { "$project" => {
       "action" => { "$setDifference" => [ "$action", [null] ] },
       "browser" => { "$setDifference" => [ "$browser", [null] ] },
       "country" => { "$setDifference" => [ "$country", [null] ] }
   }}
])

这利用了新推出的 MongoDB 2.6 $setDifference运算符以便从结果数组中过滤掉任何空值。同样的事情可以用以前的版本完成，对处理的影响很小，只是更多的步骤:

result = this.collection.aggregate([

    # Include each field and an array for "type" in all documents
    { "$project" => {
        "action" => 1,
        "browser" => 1,
        "country" => 1,
        "type" => { "$const" => [ "action", "browser", "country" ] },
    }},

    # Unwind that "type" array
    { "$unwind" => "$type" },

    # Group by "type" and the values of each field which matches
    { "$group" => {
        "_id" => {
            "type" => "$type",
            "value" => {
                "$cond" => [
                    { "$eq" => [ "$type", "action" ] },
                    "$action",
                    { "$cond" => [ 
                        { "$eq" => [ "$type", "browser" ] },
                        "$browser",
                        "$country"
                    ]}
                ]
            }
        },
        "count" => { "$sum" => 1 }
    }},

    # Just in case all fields were not present in all documents
    { "$match" => { "_id.value" => { "$ne" => null } } },

    # Group to a single document with each "type" as the keys
    { "$group" => {
        "_id" => null,
        "action" => { 
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "action" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       },
       "browser" => {
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "browser" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       },
       "country" => {
           "$addToSet" => {
               "$cond" => [
                   { "$eq" => [ "$_id.type", "country" ] },
                   { "value" => "$_id.value", "count": "$count" },
                   null
               ]
           }
       }
   }},

   # Filter out any null values from the conditional allocation
   { "$unwind": "$country" },
   { "$match": { "country": { "$ne": null } } },
   { "$group": {
       "_id": "$_id",
       "action": { "$first": "$action" },
       "browser": { "$first": "$browser" },
       "country": { "$push": "$country" }
   }},
   { "$unwind": "$browser" },
   { "$match": { "browser": { "$ne": null } } },
   { "$group": {
       "_id": "$_id",
       "action": { "$first": "$action" },
       "browser": { "$push": "$browser" },
       "country": { "$first": "$country" }
   }},
   { "$unwind": "$action" },
   { "$match": { "action": { "$ne": null } } },
   { "$group": {
       "_id": "$_id",
       "action": { "$push": "$action" },
       "browser": { "$first": "$browser" },
       "country": { "$first": "$country" }
   }}
])

输出与键/值形式略有不同，但可以很容易地操纵成一个与您目前正在做的后处理大致相同的形式。所以像这样的输入:

{ "action" : "change_password", "browser" : "ie", "country" : "US" }
{ "action" : "change_password", "browser" : "ie", "country" : "UK" }
{ "action" : "change_password", "browser" : "chrome", "country" : "AU" }

得到的结果是这样的:

{
    "_id" : null,
    "action" : [
        {
            "value" : "change_password",
            "count" : 3
        }
    ],
    "browser" : [
        {
            "value" : "ie",
            "count" : 2
        },
        {
            "value" : "chrome",
            "count" : 1
        }
    ],
    "country" : [
        {
            "value" : "US",
            "count" : 1
        },
        {
            "value" : "UK",
            "count" : 1
        },
        {
            "value" : "AU",
            "count" : 1
        }
    ]
}

所以您在 mapReduce 的输出中有一些不同，但是无论如何，任何 mapReduce 输出也将“不完全”是您想要的输出格式。在 native 代码中实现，聚合框架运行速度更快

关于mongodb - 如何使用 Map/Reduce 和 MongoDB 对多个键进行分组？发出多个键？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/25396086/