aboutsummaryrefslogtreecommitdiffstats
path: root/activerecord/lib/active_record/batches.rb
blob: 9e9c8fbbf4fb0781c09413143e91cfa7d208ebc9 (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
module ActiveRecord
  module Batches # :nodoc:
    def self.included(base)
      base.extend(ClassMethods)
    end

    # 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 +batch_size+ option).
      #
      # Example:
      #
      #   Person.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 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 +batch_size+ option; the default is 1000.
      #
      # You can control the starting point for the batch processing by supplying the +start+ 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 +start+ 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

        with_scope(:find => options.merge(:order => batch_order, :limit => options.delete(:batch_size) || 1000)) do
          records = find(:all, :conditions => [ "#{table_name}.#{primary_key} >= ?", start ])

          while records.any?
            yield records
            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