diff options
Diffstat (limited to 'activerecord/lib/active_record/relation/batches.rb')
| -rw-r--r-- | activerecord/lib/active_record/relation/batches.rb | 66 |
1 files changed, 43 insertions, 23 deletions
diff --git a/activerecord/lib/active_record/relation/batches.rb b/activerecord/lib/active_record/relation/batches.rb index b069cdce7c..e07580a563 100644 --- a/activerecord/lib/active_record/relation/batches.rb +++ b/activerecord/lib/active_record/relation/batches.rb @@ -27,37 +27,46 @@ module ActiveRecord # # ==== Options # * <tt>:batch_size</tt> - Specifies the size of the batch. Default to 1000. - # * <tt>:start</tt> - Specifies the starting point for the batch processing. + # * <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. # 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 +:start+ option on that worker). + # (by setting the +:begin_at+ and +:end_at+ option on each worker). # # # Let's process for a batch of 2000 records, skipping the first 2000 rows - # Person.find_each(start: 2000, batch_size: 2000) do |person| + # Person.find_each(begin_at: 2000, batch_size: 2000) do |person| # person.party_all_night! # end # # NOTE: It's not possible to set the order. That is automatically set to # ascending on the primary key ("id ASC") to make the batch ordering - # work. This also means that this method only works with integer-based - # primary keys. + # work. This also means that this method only works when the primary key is + # orderable (e.g. an integer or string). # # NOTE: You can't set the limit either, that's used to control # the batch sizes. - def find_each(options = {}) + 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 if block_given? - find_in_batches(options) do |records| + find_in_batches(begin_at: begin_at, end_at: end_at, batch_size: batch_size) do |records| records.each { |record| yield record } end else - enum_for :find_each, options do - options[:start] ? where(table[primary_key].gteq(options[:start])).size : size + enum_for(:find_each, begin_at: begin_at, end_at: end_at, batch_size: batch_size) do + relation = self + apply_limits(relation, begin_at, end_at).size end end end - # Yields each batch of records that was found by the find +options+ as + # Yields each batch of records that was found by the find options as # an array. # # Person.where("age > 21").find_in_batches do |group| @@ -77,34 +86,38 @@ module ActiveRecord # # ==== Options # * <tt>:batch_size</tt> - Specifies the size of the batch. Default to 1000. - # * <tt>:start</tt> - Specifies the starting point for the batch processing. + # * <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. # 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 +:start+ option on that worker). + # (by setting the +:begin_at+ and +:end_at+ option on each worker). # # # Let's process the next 2000 records - # Person.find_in_batches(start: 2000, batch_size: 2000) do |group| + # Person.find_in_batches(begin_at: 2000, batch_size: 2000) do |group| # group.each { |person| person.party_all_night! } # end # # NOTE: It's not possible to set the order. That is automatically set to # ascending on the primary key ("id ASC") to make the batch ordering - # work. This also means that this method only works with integer-based - # primary keys. + # work. This also means that this method only works when the primary key is + # orderable (e.g. an integer or string). # # NOTE: You can't set the limit either, that's used to control # the batch sizes. - def find_in_batches(options = {}) - options.assert_valid_keys(:start, :batch_size) + 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 relation = self - start = options[:start] - batch_size = options[:batch_size] || 1000 - unless block_given? - return to_enum(:find_in_batches, options) do - total = start ? where(table[primary_key].gteq(start)).size : size + 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 (total - 1).div(batch_size) + 1 end end @@ -114,7 +127,8 @@ module ActiveRecord end relation = relation.reorder(batch_order).limit(batch_size) - records = start ? relation.where(table[primary_key].gteq(start)).to_a : relation.to_a + relation = apply_limits(relation, begin_at, end_at) + records = relation.to_a while records.any? records_size = records.size @@ -131,6 +145,12 @@ 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 + relation + end + def batch_order "#{quoted_table_name}.#{quoted_primary_key} ASC" end |