aboutsummaryrefslogtreecommitdiffstats
path: root/activerecord/lib/active_record/relation/calculations.rb
blob: 801e312658e76cbd8872fd6efcadf69226175828 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
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
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
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
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
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
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
# frozen_string_literal: true

module ActiveRecord
  module Calculations
    # 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}[rdoc-ref:QueryMethods#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}[rdoc-ref:QueryMethods#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", "business"]=>0, ["published", "technology"]=>2}
    #
    # If #count is used with {Relation#select}[rdoc-ref:QueryMethods#select], it will count the selected columns:
    #
    #   Person.select(:age).count
    #   # => counts the number of different age values
    #
    # Note: not all valid {Relation#select}[rdoc-ref:QueryMethods#select] expressions are valid #count expressions. The specifics differ
    # between databases. In invalid cases, an error from the database is thrown.
    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

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

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

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

    # 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
    def sum(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(:sum, column_name)
      end
    end

    # 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
    def calculate(operation, column_name)
      if has_include?(column_name)
        relation = apply_join_dependency

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

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

    # Use #pluck as a shortcut to select one or more attributes without
    # loading a bunch of records just to grab the attributes you want.
    #
    #   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]
    #
    #   Person.pluck('DATEDIFF(updated_at, created_at)')
    #   # SELECT DATEDIFF(updated_at, created_at) FROM people
    #   # => ['0', '27761', '173']
    #
    # See also #ids.
    #
    def pluck(*column_names)
      if loaded? && (column_names.map(&:to_s) - @klass.attribute_names - @klass.attribute_aliases.keys).empty?
        return records.pluck(*column_names)
      end

      if has_include?(column_names.first)
        relation = apply_join_dependency
        relation.pluck(*column_names)
      else
        klass.disallow_raw_sql!(column_names)
        relation = spawn
        relation.select_values = column_names
        result = skip_query_cache_if_necessary { klass.connection.select_all(relation.arel, nil) }
        result.cast_values(klass.attribute_types)
      end
    end

    # Pick the value(s) from the named column(s) in the current relation.
    # This is short-hand for <tt>relation.limit(1).pluck(*column_names).first</tt>, 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', 'david@loudthinking.com' ]
    def pick(*column_names)
      limit(1).pluck(*column_names).first
    end

    # Pluck all the ID's for the relation using the table's primary key
    #
    #   Person.ids # SELECT people.id FROM people
    #   Person.joins(:companies).ids # SELECT people.id FROM people INNER JOIN companies ON companies.person_id = people.id
    def ids
      pluck primary_key
    end

    private
      def has_include?(column_name)
        eager_loading? || (includes_values.present? && column_name && column_name != :all)
      end

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

        # If #count is used with #distinct (i.e. `relation.distinct.count`) it is
        # considered distinct.
        distinct = distinct_value

        if operation == "count"
          column_name ||= select_for_count
          if column_name == :all
            if !distinct
              distinct = distinct_select?(select_for_count) if group_values.empty?
            elsif group_values.any? || select_values.empty? && order_values.empty?
              column_name = primary_key
            end
          elsif distinct_select?(column_name)
            distinct = nil
          end
        end

        if group_values.any?
          execute_grouped_calculation(operation, column_name, distinct)
        else
          execute_simple_calculation(operation, column_name, distinct)
        end
      end

      def distinct_select?(column_name)
        column_name.is_a?(::String) && /\bDISTINCT[\s(]/i.match?(column_name)
      end

      def aggregate_column(column_name)
        return column_name if Arel::Expressions === column_name

        if @klass.has_attribute?(column_name) || @klass.attribute_alias?(column_name)
          @klass.arel_attribute(column_name)
        else
          Arel.sql(column_name == :all ? "*" : column_name.to_s)
        end
      end

      def operation_over_aggregate_column(column, operation, distinct)
        operation == "count" ? column.count(distinct) : column.send(operation)
      end

      def execute_simple_calculation(operation, column_name, distinct) #:nodoc:
        column_alias = column_name

        if operation == "count" && (column_name == :all && distinct || has_limit_or_offset?)
          # Shortcut when limit is zero.
          return 0 if limit_value == 0

          query_builder = build_count_subquery(spawn, column_name, distinct)
        else
          # PostgreSQL doesn't like ORDER BY when there are no GROUP BY
          relation = unscope(:order).distinct!(false)

          column = aggregate_column(column_name)

          select_value = operation_over_aggregate_column(column, operation, distinct)
          if operation == "sum" && distinct
            select_value.distinct = true
          end

          column_alias = select_value.alias
          column_alias ||= @klass.connection.column_name_for_operation(operation, select_value)
          relation.select_values = [select_value]

          query_builder = relation.arel
        end

        result = skip_query_cache_if_necessary { @klass.connection.select_all(query_builder, nil) }
        row    = result.first
        value  = row && row.values.first
        type   = result.column_types.fetch(column_alias) do
          type_for(column_name)
        end

        type_cast_calculated_value(value, type, operation)
      end

      def execute_grouped_calculation(operation, column_name, distinct) #:nodoc:
        group_fields = group_values

        if group_fields.size == 1 && group_fields.first.respond_to?(:to_sym)
          association  = klass._reflect_on_association(group_fields.first)
          associated   = association && association.belongs_to? # only count belongs_to associations
          group_fields = Array(association.foreign_key) if associated
        end
        group_fields = arel_columns(group_fields)

        group_aliases = group_fields.map { |field|
          field = connection.visitor.compile(field) if Arel.arel_node?(field)
          column_alias_for(field.to_s.downcase)
        }
        group_columns = group_aliases.zip(group_fields)

        aggregate_alias = column_alias_for("#{operation}_#{column_name.to_s.downcase}")

        select_values = [
          operation_over_aggregate_column(
            aggregate_column(column_name),
            operation,
            distinct).as(aggregate_alias)
        ]
        select_values += self.select_values unless having_clause.empty?

        select_values.concat group_columns.map { |aliaz, field|
          if field.respond_to?(:as)
            field.as(aliaz)
          else
            "#{field} AS #{aliaz}"
          end
        }

        relation = except(:group).distinct!(false)
        relation.group_values  = group_aliases
        relation.select_values = select_values

        calculated_data = skip_query_cache_if_necessary { @klass.connection.select_all(relation.arel, nil) }

        if association
          key_ids     = calculated_data.collect { |row| row[group_aliases.first] }
          key_records = association.klass.base_class.where(association.klass.base_class.primary_key => key_ids)
          key_records = Hash[key_records.map { |r| [r.id, r] }]
        end

        Hash[calculated_data.map do |row|
          key = group_columns.map { |aliaz, col_name|
            type = type_for(col_name) do
              calculated_data.column_types.fetch(aliaz, Type.default_value)
            end
            type_cast_calculated_value(row[aliaz], type)
          }
          key = key.first if key.size == 1
          key = key_records[key] if associated

          type = calculated_data.column_types.fetch(aggregate_alias) { type_for(column_name) }
          [key, type_cast_calculated_value(row[aggregate_alias], type, operation)]
        end]
      end

      # Converts the given field to the value that the database adapter returns as
      # a usable column name:
      #
      #   column_alias_for("users.id")                 # => "users_id"
      #   column_alias_for("sum(id)")                  # => "sum_id"
      #   column_alias_for("count(distinct users.id)") # => "count_distinct_users_id"
      #   column_alias_for("count(*)")                 # => "count_all"
      def column_alias_for(field)
        return field if field.match?(/\A\w{,#{connection.table_alias_length}}\z/)

        column_alias = +field
        column_alias.gsub!(/\*/, "all")
        column_alias.gsub!(/\W+/, " ")
        column_alias.strip!
        column_alias.gsub!(/ +/, "_")

        connection.table_alias_for(column_alias)
      end

      def type_for(field, &block)
        field_name = field.respond_to?(:name) ? field.name.to_s : field.to_s.split(".").last
        @klass.type_for_attribute(field_name, &block)
      end

      def type_cast_calculated_value(value, type, operation = nil)
        case operation
        when "count"   then value.to_i
        when "sum"     then type.deserialize(value || 0)
        when "average" then value&.respond_to?(:to_d) ? value.to_d : value
        else type.deserialize(value)
        end
      end

      def select_for_count
        if select_values.present?
          return select_values.first if select_values.one?
          select_values.join(", ")
        else
          :all
        end
      end

      def build_count_subquery(relation, column_name, distinct)
        if column_name == :all
          column_alias = Arel.star
          relation.select_values = [ Arel.sql(FinderMethods::ONE_AS_ONE) ] unless distinct
        else
          column_alias = Arel.sql("count_column")
          relation.select_values = [ aggregate_column(column_name).as(column_alias) ]
        end

        subquery_alias = Arel.sql("subquery_for_count")
        select_value = operation_over_aggregate_column(column_alias, "count", false)

        relation.build_subquery(subquery_alias, select_value)
      end
  end
end