Merge Ruby nested hashes with same keys

Question

I have several hashes in Ruby which have nested hashes inside of them an share very similar structure. They look something like this:

a = {
    "year_1": {
        "sub_type_a": {
            "label1": value1
        }
    },
    "year_2": {
        "sub_type_a": {
            "label2": value2
        }
    }
}

b = {
    "year_1": {
        "sub_type_a": {
            "label3": value3
        }
    },
    "year_2": {
        "sub_type_a": {
            "label4": value4
        }
    }
}

c = {
    "year_1": {
        "sub_type_a": {
            "label5": value5
        }
    },
    "year_2": {
        "sub_type_a": {
            "label6": value6
        }
    }
}

I want to combine them in one single hash which would have the nested data combined where possible without overwriting other values like this:

result = {
    "year_1": {
        "sub_type_a": {
            "label1": value1,
            "label3": value3,
            "label5": value5
        }
    },
    "year_2": {
        "sub_type_a": {
            "label2": value2,
            "label4": value4,
            "label6": value6
        }
    }
}

There could also be several sub types instead of just one but that's the general idea.

If I use the merge function it just overwrites the label-value data inside the sub_type hashes and I am left with only one record.

Is there a simple way to achieve this? I can write a function that iterates the hashes recursively and figure out inside what to add where but it feels like that there should be a simpler way.

score 4 · Answer 1 · answered Jun 15 '20 at 12:35

Something similar.

Combine each_with_object, each and merge so you can iterate trough each hash and assign the merged values when they exist to a temporal new one:

[a, b, c].each_with_object({}) do |years_data, hash|
  years_data.each do |year, data|
    hash[year] = (hash[year] || {}).merge(data) { |_, oldval, newval| oldval.merge(newval) }
  end
end
# {
#     :year_1 => {
#         :sub_type_a => {
#             :label1 => :value1,
#             :label3 => :value3,
#             :label5 => :value5
#         }
#     },
#     :year_2 => {
#         :sub_type_a => {
#             :label2 => :value2,
#             :label4 => :value4,
#             :label6 => :value6
#         }
#     }
# }

Cary Swoveland · Answer 2 · 2020-06-16T02:43:39.457

We are given the following.

a = {:year_1=>{:sub_type_a=>{:label1=>"value1"}},
     :year_2=>{:sub_type_a=>{:label2=>"value2"}}} 

b = {:year_1=>{:sub_type_a=>{:label3=>"value3"}},
     :year_2=>{:sub_type_a=>{:label4=>"value4"}}} 

c = {:year_1=>{:sub_type_a=>{:label5=>"value5"}},
     :year_2=>{:sub_type_a=>{:label6=>"value6"}}}

arr = [a, b, c]

We may construct the desired hash as follows.

arr.each_with_object({}) do |g,h|
  g.each do |yr,v|
    k,f = v.first
    h.update(yr=>{ k=>f }) { |_,o,n| { k=>o[k].merge(n[k]) } }
  end
end
  #=> {:year_1=>{:sub_type_a=>{:label1=>"value1", :label3=>"value3",
  #                            :label5=>"value5"}},
  #    :year_2=>{:sub_type_a=>{:label2=>"value2", :label4=>"value4",
  #                            :label6=>"value6"}}}

This uses the form of Hash#update (a.k.a merge!) that employs a block to determine the values of keys that are present in both hashes being merged. See the link for an explanation of that block's three block variables. I've used an underscore (a valid local variable) for the first block variable, the common key, to signal to the reader that it is not used in the block calculation. That is a common convention.

For anyone interested in the gory detail of the calculations (the one sure-fire way to understand what's going on) I will execute the code with some puts statements added.

arr.each_with_object({}) do |g,h|
  puts "g=#{g}"
  puts "h=#{h}"
  g.each do |yr,v|
    puts "  yr=#{yr}"
    puts "  v=#{v}"
    k,f = v.first
    puts "  k=#{k}"
    puts "  f=#{f}"
    puts "  yr=>{ k=>f } = #{yr}=>#{v} = #{{ yr=>v }}"
    h.update(yr=>{ k=>f }) do |_,o,n|
      puts "    _=#{_}"
      puts "    o=#{o}"
      puts "    n=#{n}"
      puts "    { k=>o[k].merge(n[k]) }"
      puts "      => { #{k}=>#{o[k]}.merge(#{n[k]}) }"           
      { k=>o[k].merge(n[k]) }.tap { |e| puts "      => #{e}" }
    end
  end
end

The following is displayed.

g={:year_1=>{:sub_type_a=>{:label1=>"value1"}},
   :year_2=>{:sub_type_a=>{:label2=>"value2"}}}
h={}
  yr=year_1
  v={:sub_type_a=>{:label1=>"value1"}}
  k=sub_type_a
  f={:label1=>"value1"}
  yr=>{ k=>f } = year_1=>{:sub_type_a=>{:label1=>"value1"}} = 
    {:year_1=>{:sub_type_a=>{:label1=>"value1"}}}
  yr=year_2
  v={:sub_type_a=>{:label2=>"value2"}}
  k=sub_type_a
  f={:label2=>"value2"}
  yr=>{ k=>f } = year_2=>{:sub_type_a=>{:label2=>"value2"}} =
    {:year_2=>{:sub_type_a=>{:label2=>"value2"}}}

g={:year_1=>{:sub_type_a=>{:label3=>"value3"}},
   :year_2=>{:sub_type_a=>{:label4=>"value4"}}}
h={:year_1=>{:sub_type_a=>{:label1=>"value1"}},
   :year_2=>{:sub_type_a=>{:label2=>"value2"}}}
  yr=year_1
  v={:sub_type_a=>{:label3=>"value3"}}
  k=sub_type_a
  f={:label3=>"value3"}
  yr=>{ k=>f } = year_1=>{:sub_type_a=>{:label3=>"value3"}} =
    {:year_1=>{:sub_type_a=>{:label3=>"value3"}}}
    _=year_1
    o={:sub_type_a=>{:label1=>"value1"}}
    n={:sub_type_a=>{:label3=>"value3"}}
    { k=>o[k].merge(n[k]) }
      => { sub_type_a=>{:label1=>"value1"}.
           merge({:label3=>"value3"}) }
      => {:sub_type_a=>{:label1=>"value1", :label3=>"value3"}}
yr=year_2
  v={:sub_type_a=>{:label4=>"value4"}}
  k=sub_type_a
  f={:label4=>"value4"}
  yr=>{ k=>f } = year_2=>{:sub_type_a=>{:label4=>"value4"}} =
    {:year_2=>{:sub_type_a=>{:label4=>"value4"}}}
    _=year_2
    o={:sub_type_a=>{:label2=>"value2"}}
    n={:sub_type_a=>{:label4=>"value4"}}
    { k=>o[k].merge(n[k]) }
      => { sub_type_a=>{:label2=>"value2"}.
           merge({:label4=>"value4"}) }
      => {:sub_type_a=>{:label2=>"value2", :label4=>"value4"}}

g={:year_1=>{:sub_type_a=>{:label5=>"value5"}},
   :year_2=>{:sub_type_a=>{:label6=>"value6"}}}
h={:year_1=>{:sub_type_a=>{:label1=>"value1", :label3=>"value3"}},
   :year_2=>{:sub_type_a=>{:label2=>"value2", :label4=>"value4"}}}
  yr=year_1
  v={:sub_type_a=>{:label5=>"value5"}}
  k=sub_type_a
  f={:label5=>"value5"}
  yr=>{ k=>f } = year_1=>{:sub_type_a=>{:label5=>"value5"}} =
    {:year_1=>{:sub_type_a=>{:label5=>"value5"}}}
    _=year_1
    o={:sub_type_a=>{:label1=>"value1", :label3=>"value3"}}
    n={:sub_type_a=>{:label5=>"value5"}}
    { k=>o[k].merge(n[k]) }
      => { sub_type_a=>{:label1=>"value1", :label3=>"value3"}.
           merge({:label5=>"value5"}) }
      => {:sub_type_a=>{:label1=>"value1", :label3=>"value3",
          :label5=>"value5"}}
  yr=year_2
  v={:sub_type_a=>{:label6=>"value6"}}
  k=sub_type_a
  f={:label6=>"value6"}
  yr=>{ k=>f } = year_2=>{:sub_type_a=>{:label6=>"value6"}} =
    {:year_2=>{:sub_type_a=>{:label6=>"value6"}}}
    _=year_2
    o={:sub_type_a=>{:label2=>"value2", :label4=>"value4"}}
    n={:sub_type_a=>{:label6=>"value6"}}
    { k=>o[k].merge(n[k]) }
      => { sub_type_a=>{:label2=>"value2", :label4=>"value4"}.
           merge({:label6=>"value6"}) }
      => {:sub_type_a=>{:label2=>"value2", :label4=>"value4",
                        :label6=>"value6"}}
 => {:year_1=>{:sub_type_a=>{:label1=>"value1", :label3=>"value3",
       :label5=>"value5"}},
     :year_2=>{:sub_type_a=>{:label2=>"value2", :label4=>"value4",
       :label6=>"value6"}}}

score 1 · Answer 3 · answered Jun 15 '20 at 12:37

1

If you are using Rails (or ActiveSupport) you might want to look at deep_merge, which handles merging of nested hashes for you

answered Jun 15 '20 at 12:37

johansenja

568
1
7
18

2

This should be a comment. – Cary Swoveland Jun 15 '20 at 19:15

score -1 · Answer 4 · answered Jun 15 '20 at 08:50

-1

Hash#merge takes an optional conflict resolution block, which will be called any time a key is present in both the subject and the parameter.

You can use this to e.g. recursively merge your hashes.

answered Jun 15 '20 at 08:50

Masklinn

34,759
3
38
57

1

This should be a comment. – Cary Swoveland Jun 15 '20 at 19:15
2

That makes no sense. It's an answer to the question, not a comment on it. – Masklinn Jun 16 '20 at 05:49

Merge Ruby nested hashes with same keys

4 Answers4