aboutsummaryrefslogtreecommitdiffstats
path: root/activerecord/lib/active_record/relation/batches.rb
diff options
context:
space:
mode:
authorPratik Naik <pratiknaik@gmail.com>2010-02-12 16:53:51 +0000
committerPratik Naik <pratiknaik@gmail.com>2010-02-12 22:31:03 +0000
commitdc3cc6c608b93209b23bbebd2ade04835abd6f6c (patch)
tree4eab79705115229d73d4c38c84e5499638bfd3f9 /activerecord/lib/active_record/relation/batches.rb
parent5188c11d2eb7053a2471222de52cad5786febfc3 (diff)
downloadrails-dc3cc6c608b93209b23bbebd2ade04835abd6f6c.tar.gz
rails-dc3cc6c608b93209b23bbebd2ade04835abd6f6c.tar.bz2
rails-dc3cc6c608b93209b23bbebd2ade04835abd6f6c.zip
Move batch finders to Relation
Diffstat (limited to 'activerecord/lib/active_record/relation/batches.rb')
-rw-r--r--activerecord/lib/active_record/relation/batches.rb78
1 files changed, 78 insertions, 0 deletions
diff --git a/activerecord/lib/active_record/relation/batches.rb b/activerecord/lib/active_record/relation/batches.rb
new file mode 100644
index 0000000000..4a260d4caa
--- /dev/null
+++ b/activerecord/lib/active_record/relation/batches.rb
@@ -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 \ No newline at end of file