kotovalexarian-likes-github
/
rails--rails
mirror of https://github.com/rails/rails.git
1
0
Fork 0
Code Releases Activity

Move batch finders to Relation

This commit is contained in:
Pratik Naik 2010-02-12 16:53:51 +00:00
parent 5188c11d2e
commit dc3cc6c608
5 changed files with 82 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
activerecord/lib/active_record.rb
View File

@ -55,10 +55,10 @@ module ActiveRecord
autoload :Calculations
autoload :PredicateBuilder
autoload :SpawnMethods
autoload :Batches
end
autoload :Base
autoload :Batches
autoload :Callbacks
autoload :DynamicFinderMatch
autoload :DynamicScopeMatch

3
activerecord/lib/active_record/base.rb
View File

@ -557,6 +557,7 @@ module ActiveRecord #:nodoc:
alias :colorize_logging= :colorize_logging
delegate :find, :first, :last, :all, :destroy, :destroy_all, :exists?, :delete, :delete_all, :update, :update_all, :to => :scoped
delegate :find_each, :find_in_batches, :to => :scoped
delegate :select, :group, :order, :limit, :joins, :where, :preload, :eager_load, :includes, :from, :lock, :readonly, :having, :to => :scoped
delegate :count, :average, :minimum, :maximum, :sum, :calculate, :to => :scoped
@ -2394,7 +2395,7 @@ module ActiveRecord #:nodoc:
# #save_with_autosave_associations to be wrapped inside a transaction.
include AutosaveAssociation, NestedAttributes
include Aggregations, Transactions, Reflection, Batches, Serialization
include Aggregations, Transactions, Reflection, Serialization
end
end

79
activerecord/lib/active_record/batches.rb
View File

@ -1,79 +0,0 @@
module ActiveRecord
module Batches # :nodoc:
extend ActiveSupport::Concern
# When processing large numbers of records, it's often a good idea to do
# so in batches to prevent memory ballooning.
module ClassMethods
# Yields each record that was found by the find +options+. The find is
# performed by find_in_batches with a batch size of 1000 (or as
# specified by the <tt>:batch_size</tt> option).
#
# Example:
#
# Person.find_each(:conditions => "age > 21") do |person|
# person.party_all_night!
# end
#
# Note: This method is only intended to use for batch processing of
# large amounts of records that wouldn't fit in memory all at once. If
# you just need to loop over less than 1000 records, it's probably
# better just to use the regular find methods.
def find_each(options = {})
find_in_batches(options) do |records|
records.each { |record| yield record }
end
self
end
# Yields each batch of records that was found by the find +options+ as
# an array. The size of each batch is set by the <tt>:batch_size</tt>
# option; the default is 1000.
#
# You can control the starting point for the batch processing by
# supplying the <tt>:start</tt> option. 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 <tt>:start</tt>
# option on that worker).
#
# 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 mean that this method only works with integer-based
# primary keys. You can't set the limit either, that's used to control
# the the batch sizes.
#
# Example:
#
# Person.find_in_batches(:conditions => "age > 21") do |group|
# sleep(50) # Make sure it doesn't get too crowded in there!
# group.each { |person| person.party_all_night! }
# end
def find_in_batches(options = {})
raise "You can't specify an order, it's forced to be #{batch_order}" if options[:order]
raise "You can't specify a limit, it's forced to be the batch_size" if options[:limit]
start = options.delete(:start).to_i
batch_size = options.delete(:batch_size) || 1000
with_scope(:find => options.merge(:order => batch_order, :limit => batch_size)) do
records = find(:all, :conditions => [ "#{table_name}.#{primary_key} >= ?", start ])
while records.any?
yield records
break if records.size < batch_size
records = find(:all, :conditions => [ "#{table_name}.#{primary_key} > ?", records.last.id ])
end
end
end
private
def batch_order
"#{table_name}.#{primary_key} ASC"
end
end
end
end

2
activerecord/lib/active_record/relation.rb
View File

@ -5,7 +5,7 @@ module ActiveRecord
MULTI_VALUE_METHODS = [:select, :group, :order, :joins, :where, :having]
SINGLE_VALUE_METHODS = [:limit, :offset, :lock, :readonly, :create_with, :from]
include FinderMethods, Calculations, SpawnMethods, QueryMethods
include FinderMethods, Calculations, SpawnMethods, QueryMethods, Batches
delegate :length, :collect, :map, :each, :all?, :include?, :to => :to_a
delegate :insert, :to => :arel

78
activerecord/lib/active_record/relation/batches.rb Normal file
View File

@ -0,0 +1,78 @@
module ActiveRecord
module Batches # :nodoc:
# Yields each record that was found by the find +options+. The find is
# performed by find_in_batches with a batch size of 1000 (or as
# specified by the <tt>:batch_size</tt> option).
#
# Example:
#
# Person.where("age > 21").find_each do |person|
# person.party_all_night!
# end
#
# Note: This method is only intended to use for batch processing of
# large amounts of records that wouldn't fit in memory all at once. If
# you just need to loop over less than 1000 records, it's probably
# better just to use the regular find methods.
def find_each(options = {})
find_in_batches(options) do |records|
records.each { |record| yield record }
end
self
end
# Yields each batch of records that was found by the find +options+ as
# an array. The size of each batch is set by the <tt>:batch_size</tt>
# option; the default is 1000.
#
# You can control the starting point for the batch processing by
# supplying the <tt>:start</tt> option. 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 <tt>:start</tt>
# option on that worker).
#
# 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 mean that this method only works with integer-based
# primary keys. You can't set the limit either, that's used to control
# the the batch sizes.
#
# Example:
#
# Person.where("age > 21").find_in_batches do |group|
# sleep(50) # Make sure it doesn't get too crowded in there!
# group.each { |person| person.party_all_night! }
# end
def find_in_batches(options = {})
relation = self
if (finder_options = options.except(:start, :batch_size)).present?
raise "You can't specify an order, it's forced to be #{batch_order}" if options[:order].present?
raise "You can't specify a limit, it's forced to be the batch_size" if options[:limit].present?
relation = apply_finder_options(finder_options)
end
start = options.delete(:start).to_i
batch_size = options.delete(:batch_size) || 1000
relation = relation.except(:order).order(batch_order).limit(batch_size)
records = relation.where(primary_key.gteq(start)).all
while records.any?
yield records
break if records.size < batch_size
records = relation.where(primary_key.gt(records.last.id)).all
end
end
private
def batch_order
"#{@klass.table_name}.#{@klass.primary_key} ASC"
end
end
end