Module: ActiveRecord::Calculations

Included in:
Relation
Defined in:
lib/active_record/relation/calculations.rb

Overview

Active Record Calculations

Defined Under Namespace

Classes: ColumnAliasTracker

Instance Method Summary collapse

Instance Method Details

#async_average(column_name) ⇒ Object

Same as #average, but performs the query asynchronously and returns an ActiveRecord::Promise.



122
123
124
 
# File 'lib/active_record/relation/calculations.rb', line 122

def async_average(column_name)
  async.average(column_name)
end

#async_count(column_name = nil) ⇒ Object

Same as #count, but performs the query asynchronously and returns an ActiveRecord::Promise.



108
109
110
 
# File 'lib/active_record/relation/calculations.rb', line 108

def async_count(column_name = nil)
  async.count(column_name)
end

#async_ids ⇒ Object

Same as #ids, but performs the query asynchronously and returns an ActiveRecord::Promise.



409
410
411
 
# File 'lib/active_record/relation/calculations.rb', line 409

def async_ids
  async.ids
end

#async_maximum(column_name) ⇒ Object

Same as #maximum, but performs the query asynchronously and returns an ActiveRecord::Promise.



152
153
154
 
# File 'lib/active_record/relation/calculations.rb', line 152

def async_maximum(column_name)
  async.maximum(column_name)
end

#async_minimum(column_name) ⇒ Object

Same as #minimum, but performs the query asynchronously and returns an ActiveRecord::Promise.



137
138
139
 
# File 'lib/active_record/relation/calculations.rb', line 137

def async_minimum(column_name)
  async.minimum(column_name)
end

#async_pick(*column_names) ⇒ Object

Same as #pick, but performs the query asynchronously and returns an ActiveRecord::Promise.



363
364
365
 
# File 'lib/active_record/relation/calculations.rb', line 363

def async_pick(*column_names)
  async.pick(*column_names)
end

#async_pluck(*column_names) ⇒ Object

Same as #pluck, but performs the query asynchronously and returns an ActiveRecord::Promise.



334
335
336
 
# File 'lib/active_record/relation/calculations.rb', line 334

def async_pluck(*column_names)
  async.pluck(*column_names)
end

#async_sum(identity_or_column = nil) ⇒ Object

Same as #sum, but performs the query asynchronously and returns an ActiveRecord::Promise.



182
183
184
 
# File 'lib/active_record/relation/calculations.rb', line 182

def async_sum(identity_or_column = nil)
  async.sum(identity_or_column)
end

#average(column_name) ⇒ Object

Calculates the average value on a given column. Returns nil if there’s no row. See #calculate for examples with options.

Person.average(:age) # => 35.8



116
117
118
 
# File 'lib/active_record/relation/calculations.rb', line 116

def average(column_name)
  calculate(:average, column_name)
end

#calculate(operation, column_name) ⇒ Object

This calculates aggregate values in the given column. Methods for #count, #sum, #average, #minimum, and #maximum have been added as shortcuts.

Person.calculate(:count, :all) # The same as Person.count
Person.average(:age) # SELECT AVG(age) FROM people...

# Selects the minimum age for any family without any minors
Person.group(:last_name).having("min(age) > 17").minimum(:age)

Person.sum("2 * age")

There are two basic forms of output:

  • Single aggregate value: The single value is type cast to Integer for COUNT, Float for AVG, and the given column’s type for everything else.

  • Grouped values: This returns an ordered hash of the values and groups them. It takes either a column name, or the name of a belongs_to association.

    values = Person.group('last_name').maximum(:age)
puts values["Drake"]
# => 43

drake  = Family.find_by(last_name: 'Drake')
values = Person.group(:family).maximum(:age) # Person belongs_to :family
puts values[drake]
# => 43

values.each do |family, max_age|
  ...
end



217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
 
# File 'lib/active_record/relation/calculations.rb', line 217

def calculate(operation, column_name)
  operation = operation.to_s.downcase

  if @none
    case operation
    when "count", "sum"
      result = group_values.any? ? Hash.new : 0
      return @async ? Promise::Complete.new(result) : result
    when "average", "minimum", "maximum"
      result = group_values.any? ? Hash.new : nil
      return @async ? Promise::Complete.new(result) : result
    end
  end

  if has_include?(column_name)
    relation = apply_join_dependency

    if operation == "count"
      unless distinct_value || distinct_select?(column_name || select_for_count)
        relation.distinct!
        relation.select_values = Array(model.primary_key || table[Arel.star])
      end
      # PostgreSQL: ORDER BY expressions must appear in SELECT list when using DISTINCT
      relation.order_values = [] if group_values.empty?
    end

    relation.calculate(operation, column_name)
  else
    perform_calculation(operation, column_name)
  end
end

#count(column_name = nil) ⇒ Object

Count the records.

Person.count
# => the total count of all people

Person.count(:age)
# => returns the total count of all people whose age is present in database

Person.count(:all)
# => performs a COUNT(*) (:all is an alias for '*')

Person.distinct.count(:age)
# => counts the number of different age values

If #count is used with Relation#group, it returns a Hash whose keys represent the aggregated column, and the values are the respective amounts:

Person.group(:city).count
# => { 'Rome' => 5, 'Paris' => 3 }

If #count is used with Relation#group for multiple columns, it returns a Hash whose keys are an array containing the individual values of each column and the value of each key would be the #count.

Article.group(:status, :category).count
# =>  {["draft", "business"]=>10, ["draft", "technology"]=>4, ["published", "technology"]=>2}

If #count is used with Relation#select, it will count the selected columns:

Person.select(:age).count
# => counts the number of different age values

Note: not all valid Relation#select expressions are valid #count expressions. The specifics differ between databases. In invalid cases, an error from the database is thrown.

When given a block, loads all records in the relation, if the relation hasn’t been loaded yet. Calls the block with each record in the relation. Returns the number of records for which the block returns a truthy value.

Person.count { |person| person.age > 21 }
# => counts the number of people older that 21

Note: If there are a lot of records in the relation, loading all records could result in performance issues.



94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/active_record/relation/calculations.rb', line 94

def count(column_name = nil)
  if block_given?
    unless column_name.nil?
      raise ArgumentError, "Column name argument is not supported when a block is passed."
    end

    super()
  else
    calculate(:count, column_name)
  end
end

#ids ⇒ Object

Returns the base model’s ID’s for the relation using the table’s primary key

Person.ids # SELECT people.id FROM people
Person.joins(:company).ids # SELECT people.id FROM people INNER JOIN companies ON companies.id = people.company_id



371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
 
# File 'lib/active_record/relation/calculations.rb', line 371

def ids
  primary_key_array = Array(primary_key)

  if loaded?
    result = records.map do |record|
      if primary_key_array.one?
        record._read_attribute(primary_key_array.first)
      else
        primary_key_array.map { |column| record._read_attribute(column) }
      end
    end
    return @async ? Promise::Complete.new(result) : result
  end

  if has_include?(primary_key)
    relation = apply_join_dependency.group(*primary_key_array)
    return relation.ids
  end

  columns = arel_columns(primary_key_array)
  relation = spawn
  relation.select_values = columns

  result = if relation.where_clause.contradiction?
    ActiveRecord::Result.empty
  else
    skip_query_cache_if_necessary do
      model.with_connection do |c|
        c.select_all(relation, "#{model.name} Ids", async: @async)
      end
    end
  end

  result.then { |result| type_cast_pluck_values(result, columns) }
end

#maximum(column_name) ⇒ Object

Calculates the maximum value on a given column. The value is returned with the same data type of the column, or nil if there’s no row. See #calculate for examples with options.

Person.maximum(:age) # => 93



146
147
148
 
# File 'lib/active_record/relation/calculations.rb', line 146

def maximum(column_name)
  calculate(:maximum, column_name)
end

#minimum(column_name) ⇒ Object

Calculates the minimum value on a given column. The value is returned with the same data type of the column, or nil if there’s no row. See #calculate for examples with options.

Person.minimum(:age) # => 7



131
132
133
 
# File 'lib/active_record/relation/calculations.rb', line 131

def minimum(column_name)
  calculate(:minimum, column_name)
end

#pick(*column_names) ⇒ Object

Pick the value(s) from the named column(s) in the current relation. This is short-hand for relation.limit(1).pluck(*column_names).first, and is primarily useful when you have a relation that’s already narrowed down to a single row.

Just like #pluck, #pick will only load the actual value, not the entire record object, so it’s also more efficient. The value is, again like with pluck, typecast by the column type.

Person.where(id: 1).pick(:name)
# SELECT people.name FROM people WHERE id = 1 LIMIT 1
# => 'David'

Person.where(id: 1).pick(:name, :email_address)
# SELECT people.name, people.email_address FROM people WHERE id = 1 LIMIT 1
# => [ 'David', '[email protected]' ]



352
353
354
355
356
357
358
359
 
# File 'lib/active_record/relation/calculations.rb', line 352

def pick(*column_names)
  if loaded? && all_attributes?(column_names)
    result = records.pick(*column_names)
    return @async ? Promise::Complete.new(result) : result
  end

  limit(1).pluck(*column_names).then(&:first)
end

#pluck(*column_names) ⇒ Object

Use #pluck as a shortcut to select one or more attributes without loading an entire record object per row.

Person.pluck(:name)

instead of

Person.all.map(&:name)

Pluck returns an Array of attribute values type-casted to match the plucked column names, if they can be deduced. Plucking an SQL fragment returns String values by default.

Person.pluck(:name)
# SELECT people.name FROM people
# => ['David', 'Jeremy', 'Jose']

Person.pluck(:id, :name)
# SELECT people.id, people.name FROM people
# => [[1, 'David'], [2, 'Jeremy'], [3, 'Jose']]

Person.distinct.pluck(:role)
# SELECT DISTINCT role FROM people
# => ['admin', 'member', 'guest']

Person.where(age: 21).limit(5).pluck(:id)
# SELECT people.id FROM people WHERE people.age = 21 LIMIT 5
# => [2, 3]

Comment.joins(:person).pluck(:id, person: :id)
# SELECT comments.id, person.id FROM comments INNER JOIN people person ON person.id = comments.person_id
# => [[1, 2], [2, 2]]

Comment.joins(:person).pluck(:id, person: [:id, :name])
# SELECT comments.id, person.id, person.name FROM comments INNER JOIN people person ON person.id = comments.person_id
# => [[1, 2, 'David'], [2, 2, 'David']]

Person.pluck(Arel.sql('DATEDIFF(updated_at, created_at)'))
# SELECT DATEDIFF(updated_at, created_at) FROM people
# => ['0', '27761', '173']

See also #ids.



291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
 
# File 'lib/active_record/relation/calculations.rb', line 291

def pluck(*column_names)
  if @none
    if @async
      return Promise::Complete.new([])
    else
      return []
    end
  end

  if loaded? && all_attributes?(column_names)
    result = records.pluck(*column_names)
    if @async
      return Promise::Complete.new(result)
    else
      return result
    end
  end

  if has_include?(column_names.first)
    relation = apply_join_dependency
    relation.pluck(*column_names)
  else
    model.disallow_raw_sql!(flattened_args(column_names))
    relation = spawn
    columns = relation.arel_columns(column_names)
    relation.select_values = columns
    result = skip_query_cache_if_necessary do
      if where_clause.contradiction?
        ActiveRecord::Result.empty(async: @async)
      else
        model.with_connection do |c|
          c.select_all(relation.arel, "#{model.name} Pluck", async: @async)
        end
      end
    end
    result.then do |result|
      type_cast_pluck_values(result, columns)
    end
  end
end

#sum(initial_value_or_column = 0, &block) ⇒ Object

Calculates the sum of values on a given column. The value is returned with the same data type of the column, 0 if there’s no row. See #calculate for examples with options.

Person.sum(:age) # => 4562

When given a block, loads all records in the relation, if the relation hasn’t been loaded yet. Calls the block with each record in the relation. Returns the sum of initial_value_or_column and the block return values:

Person.sum { |person| person.age } # => 4562
Person.sum(1000) { |person| person.age } # => 5562

Note: If there are a lot of records in the relation, loading all records could result in performance issues.



172
173
174
175
176
177
178
 
# File 'lib/active_record/relation/calculations.rb', line 172

def sum(initial_value_or_column = 0, &block)
  if block_given?
    map(&block).sum(initial_value_or_column)
  else
    calculate(:sum, initial_value_or_column)
  end
end