diff options
Diffstat (limited to 'activerecord')
| -rw-r--r-- | activerecord/CHANGELOG.md | 4 | ||||
| -rw-r--r-- | activerecord/lib/active_record/relation/batches.rb | 67 | ||||
| -rw-r--r-- | activerecord/lib/active_record/relation/batches/batch_enumerator.rb | 12 | ||||
| -rw-r--r-- | activerecord/test/cases/batches_test.rb | 45 |
4 files changed, 46 insertions, 82 deletions
diff --git a/activerecord/CHANGELOG.md b/activerecord/CHANGELOG.md index e14a9a972c..3d251f95cc 100644 --- a/activerecord/CHANGELOG.md +++ b/activerecord/CHANGELOG.md @@ -634,7 +634,7 @@ * Add `ActiveRecord::Relation#in_batches` to work with records and relations in batches. - Available options are `of` (batch size), `load`, `begin_at`, and `end_at`. + Available options are `of` (batch size), `load`, `start`, and `finish`. Examples: @@ -1282,7 +1282,7 @@ *Yves Senn* -* `find_in_batches` now accepts an `:end_at` parameter that complements the `:start` +* `find_in_batches` now accepts an `:finish` parameter that complements the `:start` parameter to specify where to stop batch processing. *Vipul A M* diff --git a/activerecord/lib/active_record/relation/batches.rb b/activerecord/lib/active_record/relation/batches.rb index 221bc73680..54587ae18e 100644 --- a/activerecord/lib/active_record/relation/batches.rb +++ b/activerecord/lib/active_record/relation/batches.rb @@ -29,15 +29,15 @@ module ActiveRecord # # ==== Options # * <tt>:batch_size</tt> - Specifies the size of the batch. Default to 1000. - # * <tt>:begin_at</tt> - Specifies the primary key value to start from, inclusive of the value. - # * <tt>:end_at</tt> - Specifies the primary key value to end at, inclusive of the value. + # * <tt>:start</tt> - Specifies the primary key value to start from, inclusive of the value. + # * <tt>:finish</tt> - Specifies the primary key value to end at, inclusive of the value. # This is especially useful if you want multiple workers dealing with # the same processing queue. You can make worker 1 handle all the records # between id 0 and 10,000 and worker 2 handle from 10,000 and beyond - # (by setting the +:begin_at+ and +:end_at+ option on each worker). + # (by setting the +:start+ and +:finish+ option on each worker). # # # Let's process for a batch of 2000 records, skipping the first 2000 rows - # Person.find_each(begin_at: 2000, batch_size: 2000) do |person| + # Person.find_each(start: 2000, batch_size: 2000) do |person| # person.party_all_night! # end # @@ -48,22 +48,15 @@ module ActiveRecord # # NOTE: You can't set the limit either, that's used to control # the batch sizes. - def find_each(begin_at: nil, end_at: nil, batch_size: 1000, start: nil) - if start - begin_at = start - ActiveSupport::Deprecation.warn(<<-MSG.squish) - Passing `start` value to find_each is deprecated, and will be removed in Rails 5.1. - Please pass `begin_at` instead. - MSG - end + def find_each(start: nil, finish: nil, batch_size: 1000) if block_given? - find_in_batches(begin_at: begin_at, end_at: end_at, batch_size: batch_size) do |records| + find_in_batches(start: start, finish: finish, batch_size: batch_size) do |records| records.each { |record| yield record } end else - enum_for(:find_each, begin_at: begin_at, end_at: end_at, batch_size: batch_size) do + enum_for(:find_each, start: start, finish: finish, batch_size: batch_size) do relation = self - apply_limits(relation, begin_at, end_at).size + apply_limits(relation, start, finish).size end end end @@ -88,15 +81,15 @@ module ActiveRecord # # ==== Options # * <tt>:batch_size</tt> - Specifies the size of the batch. Default to 1000. - # * <tt>:begin_at</tt> - Specifies the primary key value to start from, inclusive of the value. - # * <tt>:end_at</tt> - Specifies the primary key value to end at, inclusive of the value. + # * <tt>:start</tt> - Specifies the primary key value to start from, inclusive of the value. + # * <tt>:finish</tt> - Specifies the primary key value to end at, inclusive of the value. # This is especially useful if you want multiple workers dealing with # the same processing queue. You can make worker 1 handle all the records # between id 0 and 10,000 and worker 2 handle from 10,000 and beyond - # (by setting the +:begin_at+ and +:end_at+ option on each worker). + # (by setting the +:start+ and +:finish+ option on each worker). # # # Let's process the next 2000 records - # Person.find_in_batches(begin_at: 2000, batch_size: 2000) do |group| + # Person.find_in_batches(start: 2000, batch_size: 2000) do |group| # group.each { |person| person.party_all_night! } # end # @@ -107,24 +100,16 @@ module ActiveRecord # # NOTE: You can't set the limit either, that's used to control # the batch sizes. - def find_in_batches(begin_at: nil, end_at: nil, batch_size: 1000, start: nil) - if start - begin_at = start - ActiveSupport::Deprecation.warn(<<-MSG.squish) - Passing `start` value to find_in_batches is deprecated, and will be removed in Rails 5.1. - Please pass `begin_at` instead. - MSG - end - + def find_in_batches(start: nil, finish: nil, batch_size: 1000) relation = self unless block_given? - return to_enum(:find_in_batches, begin_at: begin_at, end_at: end_at, batch_size: batch_size) do - total = apply_limits(relation, begin_at, end_at).size + return to_enum(:find_in_batches, start: start, finish: finish, batch_size: batch_size) do + total = apply_limits(relation, start, finish).size (total - 1).div(batch_size) + 1 end end - in_batches(of: batch_size, begin_at: begin_at, end_at: end_at, load: true) do |batch| + in_batches(of: batch_size, start: start, finish: finish, load: true) do |batch| yield batch.to_a end end @@ -153,18 +138,18 @@ module ActiveRecord # ==== Options # * <tt>:of</tt> - Specifies the size of the batch. Default to 1000. # * <tt>:load</tt> - Specifies if the relation should be loaded. Default to false. - # * <tt>:begin_at</tt> - Specifies the primary key value to start from, inclusive of the value. - # * <tt>:end_at</tt> - Specifies the primary key value to end at, inclusive of the value. + # * <tt>:start</tt> - Specifies the primary key value to start from, inclusive of the value. + # * <tt>:finish</tt> - Specifies the primary key value to end at, inclusive of the value. # # This is especially useful if you want to work with the # ActiveRecord::Relation object instead of the array of records, or if # you want multiple workers dealing with the same processing queue. You can # make worker 1 handle all the records between id 0 and 10,000 and worker 2 - # handle from 10,000 and beyond (by setting the +:begin_at+ and +:end_at+ + # handle from 10,000 and beyond (by setting the +:start+ and +:finish+ # option on each worker). # # # Let's process the next 2000 records - # Person.in_batches(of: 2000, begin_at: 2000).update_all(awesome: true) + # Person.in_batches(of: 2000, start: 2000).update_all(awesome: true) # # An example of calling where query method on the relation: # @@ -186,10 +171,10 @@ module ActiveRecord # # NOTE: You can't set the limit either, that's used to control the batch # sizes. - def in_batches(of: 1000, begin_at: nil, end_at: nil, load: false) + def in_batches(of: 1000, start: nil, finish: nil, load: false) relation = self unless block_given? - return BatchEnumerator.new(of: of, begin_at: begin_at, end_at: end_at, relation: self) + return BatchEnumerator.new(of: of, start: start, finish: finish, relation: self) end if logger && (arel.orders.present? || arel.taken.present?) @@ -197,7 +182,7 @@ module ActiveRecord end relation = relation.reorder(batch_order).limit(of) - relation = apply_limits(relation, begin_at, end_at) + relation = apply_limits(relation, start, finish) batch_relation = relation loop do @@ -225,9 +210,9 @@ module ActiveRecord private - def apply_limits(relation, begin_at, end_at) - relation = relation.where(table[primary_key].gteq(begin_at)) if begin_at - relation = relation.where(table[primary_key].lteq(end_at)) if end_at + def apply_limits(relation, start, finish) + relation = relation.where(table[primary_key].gteq(start)) if start + relation = relation.where(table[primary_key].lteq(finish)) if finish relation end diff --git a/activerecord/lib/active_record/relation/batches/batch_enumerator.rb b/activerecord/lib/active_record/relation/batches/batch_enumerator.rb index 153aae9584..c6e39814dd 100644 --- a/activerecord/lib/active_record/relation/batches/batch_enumerator.rb +++ b/activerecord/lib/active_record/relation/batches/batch_enumerator.rb @@ -3,11 +3,11 @@ module ActiveRecord class BatchEnumerator include Enumerable - def initialize(of: 1000, begin_at: nil, end_at: nil, relation:) #:nodoc: + def initialize(of: 1000, start: nil, finish: nil, relation:) #:nodoc: @of = of @relation = relation - @begin_at = begin_at - @end_at = end_at + @start = start + @finish = finish end # Looping through a collection of records from the database (using the @@ -34,7 +34,7 @@ module ActiveRecord def each_record return to_enum(:each_record) unless block_given? - @relation.to_enum(:in_batches, of: @of, begin_at: @begin_at, end_at: @end_at, load: true).each do |relation| + @relation.to_enum(:in_batches, of: @of, start: @start, finish: @finish, load: true).each do |relation| relation.to_a.each { |record| yield record } end end @@ -46,7 +46,7 @@ module ActiveRecord # People.in_batches.update_all('age = age + 1') [:delete_all, :update_all, :destroy_all].each do |method| define_method(method) do |*args, &block| - @relation.to_enum(:in_batches, of: @of, begin_at: @begin_at, end_at: @end_at, load: false).each do |relation| + @relation.to_enum(:in_batches, of: @of, start: @start, finish: @finish, load: false).each do |relation| relation.send(method, *args, &block) end end @@ -58,7 +58,7 @@ module ActiveRecord # relation.update_all(awesome: true) # end def each - enum = @relation.to_enum(:in_batches, of: @of, begin_at: @begin_at, end_at: @end_at, load: false) + enum = @relation.to_enum(:in_batches, of: @of, start: @start, finish: @finish, load: false) return enum.each { |relation| yield relation } if block_given? enum end diff --git a/activerecord/test/cases/batches_test.rb b/activerecord/test/cases/batches_test.rb index da65336305..3602ee7ba2 100644 --- a/activerecord/test/cases/batches_test.rb +++ b/activerecord/test/cases/batches_test.rb @@ -38,7 +38,7 @@ class EachTest < ActiveRecord::TestCase if Enumerator.method_defined? :size def test_each_should_return_a_sized_enumerator assert_equal 11, Post.find_each(batch_size: 1).size - assert_equal 5, Post.find_each(batch_size: 2, begin_at: 7).size + assert_equal 5, Post.find_each(batch_size: 2, start: 7).size assert_equal 11, Post.find_each(batch_size: 10_000).size end end @@ -101,16 +101,16 @@ class EachTest < ActiveRecord::TestCase def test_find_in_batches_should_start_from_the_start_option assert_queries(@total) do - Post.find_in_batches(batch_size: 1, begin_at: 2) do |batch| + Post.find_in_batches(batch_size: 1, start: 2) do |batch| assert_kind_of Array, batch assert_kind_of Post, batch.first end end end - def test_find_in_batches_should_end_at_the_end_option + def test_find_in_batches_should_finish_the_end_option assert_queries(6) do - Post.find_in_batches(batch_size: 1, end_at: 5) do |batch| + Post.find_in_batches(batch_size: 1, finish: 5) do |batch| assert_kind_of Array, batch assert_kind_of Post, batch.first end @@ -175,7 +175,7 @@ class EachTest < ActiveRecord::TestCase def test_find_in_batches_should_not_modify_passed_options assert_nothing_raised do - Post.find_in_batches({ batch_size: 42, begin_at: 1 }.freeze){} + Post.find_in_batches({ batch_size: 42, start: 1 }.freeze){} end end @@ -184,7 +184,7 @@ class EachTest < ActiveRecord::TestCase start_nick = nick_order_subscribers.second.nick subscribers = [] - Subscriber.find_in_batches(batch_size: 1, begin_at: start_nick) do |batch| + Subscriber.find_in_batches(batch_size: 1, start: start_nick) do |batch| subscribers.concat(batch) end @@ -311,15 +311,15 @@ class EachTest < ActiveRecord::TestCase def test_in_batches_should_start_from_the_start_option post = Post.order('id ASC').where('id >= ?', 2).first assert_queries(2) do - relation = Post.in_batches(of: 1, begin_at: 2).first + relation = Post.in_batches(of: 1, start: 2).first assert_equal post, relation.first end end - def test_in_batches_should_end_at_the_end_option + def test_in_batches_should_finish_the_end_option post = Post.order('id DESC').where('id <= ?', 5).first assert_queries(7) do - relation = Post.in_batches(of: 1, end_at: 5, load: true).reverse_each.first + relation = Post.in_batches(of: 1, finish: 5, load: true).reverse_each.first assert_equal post, relation.last end end @@ -371,7 +371,7 @@ class EachTest < ActiveRecord::TestCase def test_in_batches_should_not_modify_passed_options assert_nothing_raised do - Post.in_batches({ of: 42, begin_at: 1 }.freeze){} + Post.in_batches({ of: 42, start: 1 }.freeze){} end end @@ -380,7 +380,7 @@ class EachTest < ActiveRecord::TestCase start_nick = nick_order_subscribers.second.nick subscribers = [] - Subscriber.in_batches(of: 1, begin_at: start_nick) do |relation| + Subscriber.in_batches(of: 1, start: start_nick) do |relation| subscribers.concat(relation) end @@ -441,32 +441,11 @@ class EachTest < ActiveRecord::TestCase assert_equal 2, person.reload.author_id # incremented only once end - def test_find_in_batches_start_deprecated - assert_deprecated do - assert_queries(@total) do - Post.find_in_batches(batch_size: 1, start: 2) do |batch| - assert_kind_of Array, batch - assert_kind_of Post, batch.first - end - end - end - end - - def test_find_each_start_deprecated - assert_deprecated do - assert_queries(@total) do - Post.find_each(batch_size: 1, start: 2) do |post| - assert_kind_of Post, post - end - end - end - end - if Enumerator.method_defined? :size def test_find_in_batches_should_return_a_sized_enumerator assert_equal 11, Post.find_in_batches(:batch_size => 1).size assert_equal 6, Post.find_in_batches(:batch_size => 2).size - assert_equal 4, Post.find_in_batches(batch_size: 2, begin_at: 4).size + assert_equal 4, Post.find_in_batches(batch_size: 2, start: 4).size assert_equal 4, Post.find_in_batches(:batch_size => 3).size assert_equal 1, Post.find_in_batches(:batch_size => 10_000).size end |