ruby-on-rails - Rails 散列按它们的值组合

Question

我有一个问题列表，我需要将它们分开。关系是

Question_set has_many questions
BookVolume has_many questions
Subject has_many  book_volumes
Publisher has_many subjects
Section has_many :questions

现在我只把questions 和它们的相关模型id, name 放到 里面的hash 中数组。

data = []
question_set.questions.each do |q|
    data << {publisher: {id: q.publisher.id, name: q.publisher.name}, subject: {id: q.book_volume.subject.id, name: q.book_volume.subject.name}, volume: {id: q.book_volume_id, name: q.book_volume.name}, chapter: [{id: q.section_id, name: q.section.name}]}  
end

因此，data基本上就是

>>data

[
    {
        :publisher => {
              :id => 96,
            :name => "P1"
        },
          :subject => {
              :id => 233,
            :name => "S1"
        },
           :volume => {
              :id => 1136,
            :name => "V1"
        },
          :chapter => [
            {
                  :id => 16155,
                :name => "C1"
            }
        ]
    },
       {
        :publisher => {
              :id => 96,
            :name => "P1"
        },
          :subject => {
              :id => 233,
            :name => "S1"
        },
           :volume => {
              :id => 1136,
            :name => "V1"
        },
          :chapter => [
            {
                  :id => 16158,
                :name => "C2"
            }
        ]
    }
]

但是，如果 chapter 具有相同的 publisher、subject 和 volume，我希望合并它们所以，在这种情况下，它将是

>>data 

[
    {
        :publisher => {
              :id => 96,
            :name => "P1"
        },
          :subject => {
              :id => 233,
            :name => "S1"
        },
           :volume => {
              :id => 1136,
            :name => "V1"
        },
          :chapter => [
            {
                  :id => 16155,
                :name => "C2"
            },
            {
                  :id => 16158,
                :name => "C2"
            }
        ]
    }
]

Answer 1

代码

def group_em(data)
  data.group_by { |h| [h[:publisher], h[:subject], h[:volume]] }.
       map do |k,v|
         h = { publisher: k[0], subject: k[1], volume: k[2] }
         h.update(chapters: v.each_with_object([]) { |f,a|
           a << f[:chapter] }.flatten)
       end
end

示例

让 data 等于散列数组(上面的第一个数组)。

group_em(data)
  #=> [{:publisher=>{:id=>96, :name=>"P1"},
  #     :subject=>{:id=>233, :name=>"S1"},
  #     :volume=>{:id=>1136, :name=>"V1"},
  #     :chapters=>[{:id=>16155, :name=>"C1"}, {:id=>16158, :name=>"C2"}]
  #    } 
  #   ] 

此处 data 仅包含两个散列，并且这些散列对于键 :publisher、:subject 和 具有相同的值:音量。此代码允许数组具有任意数量的散列，并将通过这三个键的值的数组对它们进行分组，为这些组中的每一个生成一个散列。此外，键 :chapters 的值是包含单个散列的数组，但此代码允许该数组包含多个散列。 (如果该数组总是只有一个散列，请考虑将 :chapters 的值设为散列本身，而不是包含该散列的数组。)

解释

参见 Enumerable#group_by和 Hash#update (又名 Hash#merge!)。

步骤如下。

h = data.group_by { |h| [h[:publisher], h[:subject], h[:volume]] }
  #=> {
  #    [{:id=>96, :name=>"P1"},
  #     {:id=>233, :name=>"S1"},
  #     {:id=>1136, :name=>"V1"}
  #    ]=>[{:publisher=>{:id=>96, :name=>"P1"},
  #         :subject=>{:id=>233, :name=>"S1"},
  #         :volume=>{:id=>1136, :name=>"V1"},
  #         :chapter=>[{:id=>16155, :name=>"C1"}]
  #        },
  #        {:publisher=>{:id=>96, :name=>"P1"},
  #         :subject=>{:id=>233, :name=>"S1"},
  #         :volume=>{:id=>1136, :name=>"V1"},
  #         :chapter=>[{:id=>16158, :name=>"C2"}]
  #        }
  #       ]
  #   } 

第一个键值对传递给 map 的 block ，并分配 block 变量。

k,v = h.first
  #=> [[{:id=>96, :name=>"P1"}, {:id=>233, :name=>"S1"}, {:id=>1136, :name=>"V1"}],
  #   [{:publisher=>{:id=>96, :name=>"P1"}, :subject=>{:id=>233, :name=>"S1"},
  #     :volume=>{:id=>1136, :name=>"V1"}, :chapter=>[{:id=>16155, :name=>"C1"}]},
  #    {:publisher=>{:id=>96, :name=>"P1"}, :subject=>{:id=>233, :name=>"S1"},
  #     :volume=>{:id=>1136, :name=>"V1"}, :chapter=>[{:id=>16158, :name=>"C2"}]}]]
k #=> [{:id=>96, :name=>"P1"}, {:id=>233, :name=>"S1"}, {:id=>1136, :name=>"V1"}]
v #=> [{:publisher=>{:id=>96, :name=>"P1"},
  #     :subject=>{:id=>233, :name=>"S1"},
  #     :volume=>{:id=>1136, :name=>"V1"},
  #     :chapter=>[{:id=>16155, :name=>"C1"}]},
  #    {:publisher=>{:id=>96, :name=>"P1"},
  #     :subject=>{:id=>233, :name=>"S1"},
  #     :volume=>{:id=>1136, :name=>"V1"},
  #     :chapter=>[{:id=>16158, :name=>"C2"}]}] 

并进行分块计算。

h = { publisher: k[0], subject: k[1], volume: k[2] }
  #=> {:publisher=>{:id=>96, :name=>"P1"},
  #    :subject=>{:id=>233, :name=>"S1"},
  #    :volume=>{:id=>1136, :name=>"V1"}
  #   } 
a = v.each_with_object([]) { |f,a| a << f[:chapter] }
  #=> [[{:id=>16155, :name=>"C1"}], [{:id=>16158, :name=>"C2"}]] 
b = a.flatten
  #=> [{:id=>16155, :name=>"C1"}, {:id=>16158, :name=>"C2"}]
h.update(chapters: b)
  #=> {:publisher=>{:id=>96, :name=>"P1"},
  #    :subject=>{:id=>233, :name=>"S1"},
  #    :volume=>{:id=>1136, :name=>"V1"},
  #    :chapters=>[{:id=>16155, :name=>"C1"}, {:id=>16158, :name=>"C2"}]
  #   } 

Hash#merge可以用来代替 Hash#update。